PROGRAM
www.icip2015.org
ICIP 2015 – Contents | 3
CONTENTS
Program at a Glance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Organizing Committee . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Welcome from the General Chairs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Technical Program Chairs’ Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
Technical Program Committee Members . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
Social Events . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
Plenary Talks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
Tutorials . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
Awards . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
SPS Administrative Meetings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
Program . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
Sunday September 27 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46
Monday September 28 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
Tuesday September 29 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 101
Wednesday September 30 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 155
Sponsors & Exhibitors . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205
Useful Information . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 209
Index of Authors and Session Chairs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 216
Index of Reviewers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 233
Meeting Rooms Floor Layout . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 245
Hotels & Restaurants map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 246
Notes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 247
4 | ICIP 2015 – Program at a Glance
206AB 204AB 205A
SUNDAY
09:00Deep Learning in Image
Processing & Vision
Visual Saliency: Fundamentals,
Applications, & Recent Progress
12:30 Lunch
13:30ComputationalPhotography
Symbolic & Structural Models for Image
Understanding
Spectral Methods in 3D Data Analysis
19:00 Welcome Reception (La Citadelle de Québec)
Poster A Poster B Poster C Poster D Poster E Poster F Poster G Poster H Poster J Poster K
MONDAY
08:00 Opening Ceremony (200AB)
09:00 PLENARY - DEEP LEARNING (200AB)
10:00 Break (2000 BCD)
10:30Visual
Content Analysis
Video Retrieval
Content Summarization
&Understanding
Saliency I
Saliency II
Saliency III
Motion Estimation, Restoration
& Super-resolution
TomographyImage
Analysis & Synthesis
Imaging Systems
12:30 Lunch
14:00Image
& Scene Analysis
Feature Detection &
Tracking
Texture Synthesis
Facial Features /
Gender/Age Recognition
Visual Tracking
I
Visual Tracking
II
Visual Tracking
III
Low-level Feature
Extraction & Classification
Sparse Recovery
Hyperspectral Imaging
16:00 Break (2000 BCD)
16:30Detection &
ClassificationIndexing & Retrieval
Biometric Applications
Optical Flow & Motion Estimation
Face Processing
Edge & Shape
Detection
Face & Gesture II
Face & Gesture I
Image & Video Restoration
& Enhancement
Image Enhancement
& Segmentation
19:00 Banquet co*cktail (Foyer 2)
20:00 Banquet (200AB)
ICIP 2015 – Program at a Glance | 5
PROGRAM AT A GLANCE
206AB 204AB 205A
SUNDAY
09:00Deep Learning in Image
Processing & Vision
Visual Saliency: Fundamentals,
Applications, & Recent Progress
12:30 Lunch
13:30ComputationalPhotography
Symbolic & Structural Models for Image
Understanding
Spectral Methods in 3D Data Analysis
19:00 Welcome Reception (La Citadelle de Québec)
Poster A Poster B Poster C Poster D Poster E Poster F Poster G Poster H Poster J Poster K
MONDAY
08:00 Opening Ceremony (200AB)
09:00 PLENARY - DEEP LEARNING (200AB)
10:00 Break (2000 BCD)
10:30Visual
Content Analysis
Video Retrieval
Content Summarization
&Understanding
Saliency I
Saliency II
Saliency III
Motion Estimation, Restoration
& Super-resolution
TomographyImage
Analysis & Synthesis
Imaging Systems
12:30 Lunch
14:00Image
& Scene Analysis
Feature Detection &
Tracking
Texture Synthesis
Facial Features /
Gender/Age Recognition
Visual Tracking
I
Visual Tracking
II
Visual Tracking
III
Low-level Feature
Extraction & Classification
Sparse Recovery
Hyperspectral Imaging
16:00 Break (2000 BCD)
16:30Detection &
ClassificationIndexing & Retrieval
Biometric Applications
Optical Flow & Motion Estimation
Face Processing
Edge & Shape
Detection
Face & Gesture II
Face & Gesture I
Image & Video Restoration
& Enhancement
Image Enhancement
& Segmentation
19:00 Banquet co*cktail (Foyer 2)
20:00 Banquet (200AB)
205B 205C
Image Processing for
Cinema
HEVC/H .265 Video Coding Standard
Lunch
Perceptual Metrics for Image & Video Quality in
a Broader Context
Example-based Super Resolution
Welcome Reception (La Citadelle de Québec)
Poster L Poster M Poster N Poster O 202 203 204A 204B 205A 205B 205C
Opening Ceremony (200AB)
PLENARY - DEEP LEARNING (200AB)
Break (2000 BCD)
Texture Estimation & Classification
Color Imaging
I
Color Imaging
II
High-efficiency
Video Coding
II
Edge &
Shape Models
Bio-inspired Modeling
High-efficiency
Video Coding I
Image &
Graphs
3D Modeling&
Reconstruction
Color Imaging
& Applications
Image Reconstruction
Lunch
Radar Imaging
Seismic & Remote Sensing Imaging
Data Hiding I
Data Hiding II
Graph-based Image & Video
Coding
Pose & Gesture
Recognition
Classification I
Object Detection
& Tracking I
HDR Imaging
Big Media Data
Processing & Analysis…
Curvilinear System Analysis
Break (2000 BCD)
Image Denoising &
Recovery
Image Restoration &
Denoising
Image Recovery &
Enhancement
Video Streaming Learning I
Visualization & Image
Rendering
Saliency Analysis
ObjectTracking
Multimedia Retrieval & Indexing
Big Data Processing & Analysis for
Film and Media Production
Forensic Video &
Surveillance
Banquet co*cktail (Foyer 2)
Banquet (200AB)
6 | ICIP 2015 – Program at a Glance
Poster A Poster B Poster C Poster D Poster E Poster F Poster G Poster H Poster J Poster K
TUSEDAY
09:00 PLENARY - ADVANCES IN COMPUTATIONAL IMAGING (200AB)
10:00 Break (2000 BCD)
10:30
Foreground / Background Separation
I
Foreground / Background Separation
II
Human Activity
Recognition I
Human Activity
Recognition II
Automated Detection & Tracking in Biomedical Images II
Automated Detection & Tracking in Biomedical Images I
Image Processing Systems
3D Models & Applications
Stereoscopic, Multiview & 3-D Coding
Multi-dimensional Processing
12:30 Lunch
14:00Human Body Analysis & Tracking
Local Features
Multimedia Content Analysis
Image Segmentation
I
Image Segmentation
II
Multi-image & Video Super-Resolution & Restoration
Medical Image Analysis
Object-based Representation
Image Representation
Content & Privacy Protection
16:00 Break (2000BCD)
16:30
Object Detection &
Tracking II
Object Detection &
Classification
Visual Learning
with Domain
Adaptation
Scene Analysis
I
Scene Analysis
II
Single-image Super-
resolution
Energy- & Graph-based Approaches
Neurological Feature
Extraction & Classification
Visual Signal Analysis
Computer-assisted
Screening & Diagnosis
WEDNESDAY
09:00 PLENARY - CHALLENGES AND OPPORTUNITIES IN BIOLOGICAL IMAGING (200AB)
10:00 Break (2000 BCD)
10:30
Action Detection & Recognition
I
Action Detection & Recognition
II
Activity & Face
Recognition
Focus & Lens
Parametric & Energy-based Segmentation
Restoration, Denoising &
Demosaicking
Linear and Non-Linear
Filtering
Video Quality & Image-
based Specific Application Assessment
Hardware, Parallel, & Distributed
System
Industry Special Session
I
12:30 Lunch
14:00
Machine Learning for Image
Segmentation
Video Analysis
Object Recognition
I
Object Recognition
II
Hystocytological Feature
Extraction & Classification
Image Registration,
Fusion & Mosaicking I
Image Registration,
Fusion & Mosaicking II
Sparse Representations & Applications
Social & Affective Media
Infrared, Multispectral
& Hyperspectral
imaging
16:00 Break (2000 BCD)
16:30Classification
III
Video Surveillance
II
Video Surveillance
I
Active Contours
& Levelset Methods
Object Detection &
Tracking III
Image Processing Applications
I
Image Processing Applications
II
Face Image Anaylsis
I
Face Image Anaylsis
II
Supervised & Dictionary-
based Approaches
ICIP 2015 – Program at a Glance | 7
Poster L Poster M Poster N Poster O 202 203 204A 204B 205A 205B 205C
PLENARY - ADVANCES IN COMPUTATIONAL IMAGING (200AB)
Break (2000 BCD)
Image & Video Coding
I
Image & Video Coding
II
Image & Video Coding
III
Image & Video Coding
IV
Computational Imaging
3D Image Processing
Tomographic Imaging
Image Enhancement, Deblurring &
Denoising
Image Segmentation
& Classification
Classification II
Face Recognition
I
Lunch
Robust Hashing
& Counterforensics
Text & Characters in
Images
3D Object & Scene
Reconstruction II
3D Object & Scene
Reconstruction I
Video Coding I
Multiview / 3D Video
Coding
Image Retrieval
Texture Representation
Face Recognition
II
Compact Descriptor for Visual
Search
Learning II
Break (2000 BCD)
Image & Video Quality Assessment
I
Image & Video Quality Assessment
II
Image & Video Quality Assessment
III
Image Quality
Assessment
Image/Video Indexing & Retrieval for Healthcare
Discriminative Local
Features
Image Denoising
Compressed Sensing
Document Analysis
Visual Biometrics
Plenary - Challenges and Opportunities in Biological Imaging (200AB)
Break (2000 BCD)
Industry Special Session
II
Industry Special Session
III
Media Analysis
& Understanding
Video Communication
& Networking
Multiview Processing
Multimedia Forensics
Automated Segmentation
of Radiology
images
Visual Aesthetics & Quality
Assessment
Image Segmentation
III
Perceptual Video
Compression –
For HEVC & Beyond
Lunch
Stereo Image
Processing
Multiview Image
Processing
Video Coding
II
Video Coding
III
Omnidirectional Imaging
& Plenoptics
Image Segmentation
IV
Image Super-
resolution
Machine Learning
& Scene
Analysis
3D Visual Quality
Privacy & Security
in the New Generation
Video Coding Systems
Break (2000 BCD)
Multiresolution &
WaveletsFiltering
Medical Feature
Extraction & Analysis
II
Medical Feature
Extraction & Analysis
I
Pose Estimation
&Human Activity
Recognition
Object Detection in Very High Resolution
Satellite Images
Inpainting &
Stitching
Superpixel Segmentation
Learning-based Visual Applications
Very High Resolution
Satellite Image
Information Extraction
8 | ICIP 2015 – Organizing Committee
ORGANIZING COMMITTEE
General Co-ChairsAndré MORIN, OptelisJean-Luc DUGELAY, Eurecom
Technical Co-ChairsJean-Philippe THIRAN, École Polytechnique Fédérale de Lausanne (EPFL)
Fabrice LABEAU, McGill University
Finance/TreasurerJean FORTIN, DRDC-Valcartier
Plenary Sessions Co-ChairsStéphane COULOMBE, École de technologie supérieure (ÉTS)
Kenneth ROSE, University of California
Special sessions Co-ChairsÉric DUBOIS, University of OttawaOscar C . AU, Hong Kong University of Science and Technology
Tutorial Co-ChairsAndré ZACCARIN, Université LavalJanusz KONRAD, Boston University
Local Arrangements ChairPaul FORTIER, Université Laval
Registration ChairXavier MALDAGUE, Laval University
Exhibit/industry Co-ChairsBranislav KISACANIN, InterphaseKhaled EL-MALEH, Qualcomm
Students Activities ChairsGuoliang FAN, Oklahoma State UniversitySylvie DANIEL, Laval University
Publicity Co-ChairsMaria Aishy AMER, Concordia University Patrick LE CALLET, Université de Nantes
Publication ChairMireille BOUTIN, Purdue University
Electronic Media Co-ChairsAbdulmotaleb EL SADDIK, University of OttawaBenoît HUET, Eurecom
International LiaisonsWan-Chi SIU, The Hong Kong Polytechnic UniversityOlga Regina PEREIRA BELLON, IMAGO Research Group
Awards ChairPhil CHOU, Microsoft
ICIP 2015 – Welcome from the General Chairs | 9
WELCOME FROM THE GENERAL CHAIRS
Bienvenue à Québec !
On behalf of the IEEE Signal Processing Society and Organizing Committee, it is with great pleasure that we welcome you in Québec City for the 2015 edition of the IEEE International Conference on Image Processing .
The road to making ICIP 2015 happen was long one that started at ICIP 2009 in Cairo . The conference you are about to attend is therefore the result of six years of work by a dedicated team . While writing this welcome, we found ourselves wondering how many people were involved and the answer is, give or take a few, an astounding 4,000 people, including the organizing committee, the area chairs, the tutorials instructors, the plenary speakers, the reviewers, the authors, the suppliers, the SPS staff, the volunteers, and finally you, participants from over 60 countries, for whom we have worked hard so that you get the most of your attendance and stay in Québec .
Assembling such an impressive team of diverse origins, ages, cultures and backgrounds is a challenge but also a guarantee of diversity of opinions, and of ways of thinking from which great ideas emerge . Inevitably, and despite the lessons learned from the previous editions, there will have been a few mishaps here and there, and through the myriad of decisions taken, some that were probably not optimal . Nonetheless, we remain convinced that all who contributed to the organization gave the best of themselves, with their heart and talent to yield a program we are proud of .
The conference program assembled by our Technical Program Co-Chairs Jean-Phillippe Thiran and Fabrice Labeau, to whom we extend our warmest thanks, is obviously the focus of the conference . But if conferences are a place to learn and exchange, we believe they also are an excellent opportunity to learn about and discover new places and cultures . In that sense, Québec City, the oldest permanently inhabited settlement north of Mexico, is an ideal destination, combining the charms of its narrow streets reminiscent of Europe with the proximity of the wilderness typical of the Americas . This hybridization is also perceptible in the architecture that blends the traditions of the French and British empires that successively reigned over the country . What better place to start the adventure then than the 300-years old Citadelle de Québec, where we will greet you for the Welcome Reception . The Citadelle, cornerstone of the City defense system and the highest point in the City, was first erected by the French to defend against the British Empire and then
10 | ICIP 2015 – Welcome from the General Chairs
perfected by the British to defend against the American invasion attempts . The Citadelle is also a perfect location to admire the main tower of the Château Frontenac, Québec City’s skyline hallmark signature . Good food, impressive sightline, history-laden location, and a romantic supermoon full eclipse around 21:00 should conjugate for a perfect Welcome .
Food is also part of the discoveries travel brings and the conference banquet will allow attendees to appreciate Québec City renowned gastronomy . Just after dinner, the traditional Awards Ceremony will see the iconic Mrs . Lena Söderberg present the best student paper, best conference paper, best 3MT video, and the newly introduced best industry paper awards . The banquet will conclude on sensational entertainment offering a unique blend of participation, music and humor that shall make this banquet a memorable one .
This year’s edition also introduces new activities and events, notably the Students-Employers Get Together Luncheon and the 3-minute thesis video contest, and we are indebted to Sylvie Daniel and Guoliang Fan for having taken care of these . The Women-in-Signal Processing Luncheon is another first held under the auspices of our colleagues Rabab Ward and Antonia Papandreou .
The success of any conference is tightly linked to its publicity and our thanks go to Aishy Amer and Patrick Le Callet for their help in this respect . ICIP 2015 also maintained a sustained presence on all major social networks with the precious support of Benoît Huet and Abdulmotaleb El Saddik .
This welcome would not be complete without thanks to our patrons which significant contributions played a major role in the conference overall quality while maintaining a balanced budget, handled by our finance chair Jean Fortin .
We are also obliged to the whole Organizing Committee without the support of whom none of this would have been possible . Finally, other key players, which names do not appear elsewhere, also deserve our heartfelt thanks, including Mr . Alexis Levasseur from Conférium, Mrs . Diane Bussières from Bussières Communications who diligently handled the web site and printed material production, the Citadelle de Québec, the Québec City Tourism Office, and most particularly Mrs . Nathalie Nault and Mr . Jocelyn Guertin from the Québec City Convention Centre, whose indefectible faith in this project was invaluable .
Très cordialement,
Jean-Luc DUGELAY André MORINGeneral Co-chair General Co-chairEURECOM, Sophia Antipolis Optelis, Québec City
ICIP 2015 – Technical Program Chairs’ Overview | 11
TECHNICAL PROGRAM CHAIRS’ OVERVIEW
On behalf of the Technical Program committee, we would like to welcome you to Québec City, for the 22nd edition of ICIP, the premier international conference in Image Processing . The whole team has put together a Technical Program that we hope you will find innovative and stimulating .
Once again this year, the international image community has mobilized for this event, and we have received 2,306 paper submissions . Submissions were received from all over the world, including 64 different countries, with roughly 48% from the Asia/Pacific region, 28% from Europe, the Middle East, and Africa, 19% from the USA and Canada, and 3% from Latin America . Each submitted paper has gone through a rigorous review process, conducted by a total of 1,111 expert volunteers . Collectively, they have produced 6,860 reviews . 57 Area Chairs managed this process; they are all well-known leaders in the areas covered by the conference, and several are members of the Signal Processing Society Technical Committees, and in particular the Image, Video, and Multidimensional Signal Processing TC, the Multimedia Signal Processing TC, the Bio Imaging and Signal Processing TC and the Information Forensics and Security TC . Based on the reviews collected, the Area Chairs have formulated recommendations for each of the submitted papers, which formed the basis for the final decisions made by the Technical Program Chairs .
This year, the Technical Program of ICIP will feature 1,098 presentations: 1,048 of them are regular papers (45% acceptance rate), 16 are presentations related to recently accepted IEEE Signal Processing Letters articles, and 34 will form the Show & Tell program . Among the regular papers, 62 will be grouped in 10 special sessions, which explore new and timely directions in the area of image processing . Overall, as an attendee, you will be offered a choice of 59 oral sessions and 126 poster sessions in which to learn about new research, interact with authors, and get inspired . A special mention must be made of the hard work carried out by the Awards Committee, under Awards Chair Phil Chou’s leadership, for selecting amongst all these papers recipients for the Best Paper, Best Student Paper and Best Industry Paper Awards .
Putting together such a large program requires the efforts of many volunteers; we would like to take this opportunity to thank all the contributors to the review process and the
12 | ICIP 2015 – Technical Program Chairs’ Overview
creation of the program: the reviewers, Area Chairs and Special Session organizers have all expended tremendous effort and worked with outstanding professionalism . Thanks to the dedication of these experts, ICIP 2015 will again propose a top-notch technical program, in keeping with its international reputation .
Plenary Chairs Kenneth Rose and Stéphane Coulombe have put together a set of three exciting plenary lectures . In these plenaries, world-leading researchers will present advances in specific topics of great interest to the ICIP community . On Monday morning, Yoshua Bengio from the University of Montreal will propose a talk on Deep Learning, a topic of incredible growing interest in image processing, as also attested by the record number of registrations for his tutorial on the same topic; then on Tuesday morning, Shree K . Nayar from the Columbia University will give his plenary talk on “Advances in Computational Imaging” and on Wednesday morning, Michael Unser from the École Polytechnique Fédérale de Lausanne, Switzerland, will give a lecture on “Challenges and Opportunities in Biological Imaging” . The main conference program is preceded by 9 exciting tutorials selected by the Tutorials Chairs André Zaccarin and Janusz Konrad . These tutorials are meant as introductions to the state-of-the-art in key areas of image and video processing . Additionally, Special Session Chairs Éric Dubois and Oscar C . Au have gathered a program of 10 special sessions that focus on emerging areas of growing interest . The papers in the special sessions have all undergone peer review identical to that of the regular papers . Among these special sessions, the Industry Special Session will take place on Wednesday morning, where 14 posters will present applied research conducted in companies around the world . We hope that you take advantage of these special opportunities to open up to new and emerging topics . ICIP 2015 also features Show & Tell sessions that will be an opportunity to see live demonstrations of some of the new technologies being developed in academic and industrial laboratories . We have selected 34 presentations for 9 Show & Tell sessions that will take place all along the Conference .
To end this short message, as Technical Program Chairs, we must thank all the contributors that make a conference such as ICIP 2015 what it is: the plenary speakers, the tutorial presenters, the special session organizers, the reviewers, the session chairs, the Plenary, Tutorial, Special Session and Awards Chairs, the awards committees and all authors and presenters . Each individual’s invaluable contribution adds up to deliver the quality of the conference that you will be attending . Special thanks go to our PCO Conférium for its excellent work .
We hope that you will enjoy ICIP 2015 and Quebec City!
Fabrice Labeau and Jean-Philippe ThiranICIP 2015 Technical Program Chairs
New for ICIP 2016: • maximize the visibility of your work via early free access: Papers accepted to ICIP 2016 will (upon author approval) be
available on IEEE Xplore, freely accessible and downloadable by all in their final format from August 20, 2016 through September 30, 2016.
• nominate an individual or team for the Visual Innovation Award by March 31, 2016: The Visual Innovation Award was created to recognize pioneers of transformative technologies and business models in areas within the technical scope of the IEEE ICIP conference series.
• maximize the visibility of your work through reproducible research: ICIP 2016 supports reproducible research by allowing authors to submit supplementary material, including code and data.
• maximize your networking and career connections: attendees will be given the opportunity to upload their CVs to be shared among interested recruiters for full-time, part-time, and consulting job opportunities.
• experience state-of-the-art visual technology products and prototypes at the ICIP 2016 Visual Technology Showcase.
For more details on this and other new initiatives at ICIP 2016, visit 2016.ieeeicip.org and connect on social media.
Important Deadlines: Challenge Session Proposals: October 30, 2015 Special Session/Tutorial Proposals: November 16, 2015 Paper Submissions: January 25, 2016 Visual Innovation Award Nomination: March 31, 2016
@MSFTResearch/microsoftresearch
Capturing imaginations. Researching problems. Developing solutions.
research.microsoft.com
Job Opportunities at Disney ResearchDisney Research has a number of Fall, Spring and Summer internship positions available in our respective Computer Vision groups in Pittsburgh and Zurich . Candidates should be currently enrolled in a PhD program in Computer Science, or related discipline, have at least one publication in a top-tier vision conference, and have excellent written and oral communication skills .
Interested candidates should submit CVs to:careers@disneyresearch .com . For further information please contact Leonid Sigal (lsigal@disneyresearch .com) orIainMatthews (iainm@disneyresearch .com) from Disney Research Pittsburgh, or Alexander Sorkine-Hornung (alex@disneyresearch .com) from the Disney Research lab in Zurich . Please use subject lines: DRP-CV-INTERN-2015 or DRZ-CV-INTERN-2015, respectively .Disney Research labs provide a research foundation for the many business units within the Walt Disney Company . For example: Walt Disney Feature Animation, Walt Disney Imagineering, Parks & Resorts, Walt Disney Studios Motion Pictures, Disney Interactive, ESPN, Marvel, Industrial Light and Magic and Pixar Animation Studios . Disney Research has labs located in Pittsburgh, Zurich, Los Angeles and Boston . The labs in Pittsburgh and Zurich are co-located with Carnegie Mellon University and ETH Zurich, respectively . Cast members are encouraged to interact with the established Computer Vision and Graphics groups at both Universities . As an active member of the research community we support and assist with publications at top venues .
We have opportunities for internships in a variety of fields in computer vision, including:*Semantic image understanding * Language and vision * Video sequence analysis and/or modeling * Activity and action recognition * Deep learning architectures * Pose estimation and tracking * Object detection and tracking * Face modeling, tracking and analysis* Machine learning * Big visual data* Light fields * Image-based 3D reconstruction and rendering* Vision for graphics
mailto:[emailprotected]
mailto:[emailprotected]
mailto:[emailprotected]
mailto:[emailprotected]
mailto:[emailprotected]
ICIP 2015 – Technical Program Committee Members | 15
TECHNICAL PROGRAM COMMITTEE MEMBERS
Technical Program ChairsLABEAU, Fabrice, McGill UniversityTHIRAN, Jean-Philippe, EPFL
Area ChairsALATAN, A . Aydin; Middle East Technical UniversityBAS, Erhan; GE Global ResearchBOULGOURIS, Nikolaos; Brunel University LondonBRANKOV, Jovan; Illinois Institute of TechnologyCAMPISI, Patrizio; Università degli Studi Roma TreCETIN, Mujdat; Sabanci UniversityCHEUNG, Gene; National Institute of InformaticsCHEUNG, Sen-Ching Samson; University of KentuckyCOMESAÑA ALFARO, Pedro; University of VigoDE VLEESCHOUWE, Christophe; Université catholique de LouvainDERRODE, Stéphane; École Centrale, LyonDOËRR, Gwenaël; TechnicolorDONG, Xu; Nanyang Technological UniversityENGAN, Kjersti; University of StavangerFOI, Alessandro; Tampere University of TechnologyFOWLER, James; Mississippi State UniversityGARCIA, Christophe; INSA LyonGUILLEMOT, Christine; INRIAGULERYUZ, Onur; Polytechnic UniversityHIRAKAWA, Keigo; University of DaytonKARAM, Lina; Arizona State UniversityKIYA, Hitoshi; Tokyo Metropolitan University
16 | ICIP 2015 – Technical Program Committee Members
KOUAMÉ, Denis; University Paul SabatierLE CALLET, Patrick; Université de NantesLEE, Sanghoon; Yonsei UniversityLI, Xuelong; Chinese Academy of SciencesLI, Zhu; Samsung Research AmericaLIN, Weisi; Nanyang Technological UniversityLU, Fang; University of Science and Technology of ChinaLU, Yue; Harvard UniversityMEI, Tao; Microsoft ResearchMENEGAZ, Gloria; University of VeronaMRAK, Marta; BBC R&DMUÑOZ BARRUTIA, Arrate; Universidad Carlos IIIPANKANTI, Sharath; IBM T J Watson ResearchPENG, Hanchuan; Allen Institute for Brain SciencePESQUET, Béatrice; Telecom ParisTechRABBANI, Majid; Eastman KodakREIBMAN, Amy; Purdue UniversityROSS, Arun; Michigan State UniversityROYSAM, Badri; University of HoustonSCHELKENS, Peter; Vrije Universiteit BrusselSHARMA, Gaurav; University of RochesterSMOLIC, Aljoša; Disney ResearchSRINIVASA, Gowri; PESIT Bangalore South CampusSTEINBACH, Eckehard; Technical University of MunichSUN, Changming; CSIROTAN, Yap-Peng; Nanyang Technological UniversityTIAN, Qi; University of Texas at San AntonioTONG, Zhang; Hewlett-Packard LabsTOSIC, Ivana; Ricoh InnovationsTUBARO, Stefano; Politecnico di MilanoWINKLER, Stefan; Advanced Digital Sciences CenterWU, Feng; University of Science and Technology of ChinaYE, Jong Chul; Korea Advanced Institute of Science & TechnologyZHANG, Xiao-Ping; Ryerson UniversityZOSSO, Dominique; University of California Los Angeles
ICIP 2015 – Social Events | 17
Sunday, September 27
ICIP 2015 Welcome Reception at the Citadelle de QuébecThe Citadelle of Québec is the largest British fortress in North America and Canada’s oldest military building, dating back to 1693 and the French Regime . It is an integral part of the Québec fortifications and is located on Cape Diamond, the city’s highest point . Its walls enclose 300 years of history from the time of New France until today . Known as the Gibraltar of the Americas due of its strategic location, the citadel was recognized as a National Historic Site of Canada in 1980 and is part of the Historic District of Old Québec, which was placed on UNESCO’s World Heritage List in 1985 .
Location: The Citadelle de Québec (see directions below)Date: Sunday, September 27, 2015Time: 19:00 – 22:00Cost: Free with registration .
Please confirm attendance during registration IMPORTANT: pick your badge at registration desk beforehand
Dress code: Casual, warm clothes for those wishing to explore a little
Directions:• From the main entrance of the Québec City Convention Centre:• Turn left towards Avenue Honoré-Mercier• Turn right (uphill) on Honoré-Mercier towards Grande-Allée/Saint-Louis street• Continue straight at the roundabout until you reach Grande-Allée/Rue-Louis• Turn left on rue Saint-Louis• Turn right on Côte de la Citadelle immediately after crossing the Saint-Louis gate• Follow indications for ICIP 2015
Monday, September 28
Women in Signal Processing LuncheonThe IEEE Signal Processing Society is hosting theWomen in Signal Processing(WISP) lunch reception at ICIP .
You are invited to attendtheWomen in Signal Processinglunch receptionwhose purpose is to foster support and offernetworking opportunities by engaging women across the
SOCIAL EVENTS
18 | ICIP 2015 – Social Events
signal processing profession to exchange ideas and experiences from academia, research and industry in an informal setting . The lunch reception is scheduled forMonday, 28 September 2015, from 12:30 to 14:00 at the Centre des Congrès de Quebec . Hors d›oeuvres will be served .
The WISP Luncheon is hosted by Dr . Rabab Ward, the IEEE Signal Processing Society’s President Elect and features a presentation by Dr . Amy Reibman .
This event has a limited number of seats . Requests will be honored on a first-come first-served basis up to maximum capacity, Reserve your place while registering to the conference .
Rabab WARD Biography
Rabab Kreidieh Ward has around 40 years of experience in academic, education, research, development and leadership . Her main research interests are in broad areas of signal and image processing and their applications . She has published around 500 publications in refereed journals and conferencesand book chapters, and holds six patents .Some of her work has been licensed to US and Canadian industry .She is a Fellow ofthe Royal Society of Canada, the IEEE,the Canadian Academy of Engineers and the Engineering Institute of Canada .Amongst herlarge number of awards are the UBC Senior KillamMentoringAward and UBC Killam Research Prize . She has served and provided leadership to IEEE and other professional societies and is presently the President -Elect of theIEEE Signal Processing Society .
Amy REIBMAN Biography
Dr . Amy Riebman received her PhD degree in Electrical Engineering at Duke University in 1987 . She worked at AT&T for 23 years, as the lead member of technical staff . She is currently a Professor at Purdue University . Her research interests include image and video quality estimation, video transport over networks, and video analytics . She was awarded IEEE Fellow in 2005 and served as a Distinguished Lecturer for theIEEE Signal Processing Society in 2009 .
Location: Room 206B, Québec City Convention CentreDate: Monday, September 28, 2015Time: 12:30 – 14:00Cost: CAD 7Host: Dr . Rabab WARDPresenter: Dr . Amy REIBMAN
ICIP 2015 – Social Events | 19
ICIP 2015 Banquet & Awards CeremonyThe Monday Banquet features a co*cktail and dinner . Following dinner, the traditional Awards Ceremony will see the iconic Mrs . Lena Söderberg present the best student paper, best conference paper, best 3MT video, and the newly introduced best industry paper awards . The banquet will conclude on sensational entertainment offering a unique blend of participation, music and humor that shall make this banquet a memorable one .
Location: Québec City Convention CentreDate: Monday, September 28, 2015Time: co*cktail: 19:00 – 20:00
Banquets 20:00 – 23:00Cost: CAD 150Dress code: Business or Business Casual
Tuesday, September 29
Get-Together Students-Employers Luncheon
The purpose of this lunch event is to provide opportunities for students to find a job or postdoctoral position, for industry employers to meet potential candidates, and for researchers to find postgrad students . The event will also provide networking opportunities and a forum of discussion between participants . Graduate students will be able to interact with senior researchers and to discuss their research and future career in an informal context .
Tables will be set up for companies, organizations or institutions to meet and interact with students . Food and refreshments will be served during the activity . The names of the organizations, institutions and companies attending this event will be publicized on this page .
This event has a limited number of seats . Requests will be honored on a first-come first-served basis up to maximum capacity . Students should reserve their place while registering . Employees and organizations should contact students@icip2015 .org
Location: Room 206B, Québec City Convention CentreDate: Tuesday, September 29, 2015Time: 12:30 – 14:00Cost: Students
CAD 20 after July 31, 2015 Employers Free for employers and researchers . Reserve your spot by contacting students@icip2015 .org
20 | ICIP 2015 – Social Events
Young Professionals Event
The IEEE Signal Processing Society (SPS) Young Professionals Subcommittee and the Quebec SPS/COM Chapter invite you to network with other young professionals and practicing engineers during an event in conjunction with ICIP 2015 in Quebec this September .
Join us on Tuesday, 29 September from 17:00 – 19:00 at the gorgeous National Assembly Library to discuss career advancement and professional development opportunities with fellow professionals and colleagues from all walks in an informal setting . Come unwind with some food and drink and connect with members of Quebec’s local engineering community!
Please let us know whether you’d like to attend by completing the RSVP form no later than Tuesday, 22 September . The National Assembly Library is located at 1045 Rue des Parlementaires, Québec, QC, Canada .
If you have any questions about this event or other SPS events and activities, please contact SPS Membership and Content Administrator, Jessica Perry, at jessica .perry@ieee .org .
Location The Québec National Assembly Library 1045 Rue des Parlementaires
Date Tuesday, September 29, 2015Time 17:00 – 19:00Cost Free (but reservation required by September 22, 2015)
ICIP 2015 – Plenary Talks | 21
PLENARY TALKS
Deep LearningYoshua Bengio
Professor, University of Montreal Department of Computer Science and Operations Research Canada Research Chair in Statistical Learning Algorithms
AbstractAlthough neural networks have long been considered lacking in theory
and much remains to be done, theoretical evidence is mounting and will be discussed, to support distributed representations, depth of representation, the non-convexity of the training objective, and the probabilistic interpretation of learning algorithms (especially of the auto-encoder type, which were lacking one) . Empirical work in a variety of applications has demonstrated that, when well trained, such deep architectures can be highly successful, remarkably breaking through previous state-of-the-art in many areas, including speech recognition, object recognition, language models, and transfer learning . This talk will summarize the advances that have made these breakthroughs possible, and end with questions about some major challenges still ahead of researchers in order to continue our climb towards AI-level competence .
BiographyYoshua Bengio received a PhD in Computer Science from McGill University, Canada in 1991 . After two post-doctoral years, one at M .I .T . with Michael Jordan and one at AT&T Bell Laboratories with Yann LeCun and Vladimir Vapnik, he became professor at the Department of Computer Science and Operations Research at Université de Montréal . He is the author of two books and more than 300 publications, the most cited being in the areas of deep learning, recurrent neural networks, probabilistic learning algorithms, natural language processing and manifold learning . He is among the most cited Canadian computer scientists and is or has been associate editor of the top journals in machine learning and neural networks .
Since ‘2000 he holds a Canada Research Chair in Statistical Learning Algorithms, since ‘2006 an NSERC Industrial Chair, since ‘2005 his is a Fellow of the Canadian Institute for Advanced Research and since 2014 he co-directs its program focused on deep learning . He is on the board of the NIPS foundation and has been program chair and general chair for NIPS . He has co-organized the Learning Workshop for 14 years and co-created the new International Conference on Learning Representations .
His current interests are centered around a quest for AI through machine learning, and include fundamental questions on deep learning and representation learning, the geometry of generalization in high-dimensional spaces, manifold learning, biologically inspired learning algorithms, and challenging applications of statistical machine learning .
22 | ICIP 2015 – Plenary Talks
Advances in Computational ImagingShree K. Nayar
T. C. Chang Professor of Computer Science Columbia University
AbstractComputational imaging uses new optics to capture a coded image, and an appropriate algorithm to decode the captured image . This approach
of manipulating images before there are recorded and processing recorded images before they are presented has three key benefits .
First, it enables us to implement imaging functionalities that would be difficult, if not impossible, to achieve using traditional imaging . Second, it can be used to significantly reduce the hardware complexity of an imaging system . Lastly, under appropriate imaging conditions, it allows us to break the limits of traditional imaging . In this talk, I will show recent examples of cameras that demonstrate these benefits .
BiographyShree K . Nayar is the T . C . Chang Professor of Computer Science at Columbia University . He heads the Columbia Vision Laboratory (CAVE), which develops advanced computer vision systems . His research is focused on three areas - the creation of novel cameras that provide new forms of visual information, the design of physics based models for vision and graphics, and the development of algorithms for understanding scenes from images . His work is motivated by applications in the fields of digital imaging, computer graphics, robotics and human-computer interfaces .
Nayar received his PhD degree in Electrical and Computer Engineering from the Robotics Institute at Carnegie Mellon University . For his research and teaching he has received several honors including the David Marr Prize (1990 and 1995), the David and Lucile Packard Fellowship (1992), the National Young Investigator Award (1993), the NTT Distinguished Scientific Achievement Award (1994), the Keck Foundation Award for Excellence in Teaching (1995), the Columbia Great Teacher Award (2006), and the Carnegie Mellon Alumni Achievement Award (2009) . For his contributions to computer vision and computational imaging, he was elected to the National Academy of Engineering in 2008, the American Academy of Arts and Sciences in 2011, and the National Academy of Inventors in 2014 .
ICIP 2015 – Plenary Talks | 23
Challenges and Opportunities in Biological ImagingMichael Unser
Professor, École Polytechnique Fédérale de Lausanne Biomedical Imaging Group
AbstractWhile the major achievements in medical imaging can be traced back
to the end the 20th century, there are strong indicators that we have recently entered the golden age of cellular/biological imaging . The enabling modality is fluorescence microscopy which results from the combination of highly specific fluorescent probes (Nobel Prize 2008) and sophisticated optical instrumentation (Nobel Prize 2014) . Modern microscopy centers are providing biologists with unprecedented amounts of data in 3D + time .
To address the computational aspects, two nascent fields have emerged in which image processing is expected to play a significant role . The first is “digital optics” where the idea is to combine optics with advanced signal processing in order to increase spatial resolution while reducing acquisition time . The second area is “bioimage informatics” which is concerned with the development of image analysis software to make microscopy more quantitative . The key issue here is reliable image segmentation as well as the ability to track structures of interest over time . We shall discuss specific examples and describe state-of-the-art solutions for bioimage reconstruction and analysis . This will help us build a list of challenges and opportunities to guide further research in bioimaging .
BiographyMichael Unser is professor and director of EPFL’s Biomedical Imaging Group, Lausanne, Switzerland . His primary area of investigation is biomedical image processing . He is internationally recognized for his research contributions to sampling theory, wavelets, the use of splines for image processing, stochastic processes, and computational bioimaging . He has published over 250 journal papers on those topics . He is the author with P . Tafti of the book “An introduction to sparse stochastic processes”, Cambridge University Press 2014 .
From 1985 to 1997, he was with the Biomedical Engineering and Instrumentation Program, National Institutes of Health, Bethesda USA, conducting research on bioimaging .
Dr . Unser has held the position of associate Editor-in-Chief (2003-2005) for the IEEE Transactions on Medical Imaging . He is currently member of the editorial boards of SIAM J . Imaging Sciences, IEEE J . Selected Topics in Signal Processing, and Foundations and Trends in Signal Processing . He is the founding chair of the technical committee on Bio Imaging and Signal Processing (BISP) of the IEEE Signal Processing Society .
Prof . Unser is a fellow of the IEEE (1999), an EURASIP fellow (2009), and a member of the Swiss Academy of Engineering Sciences . He is the recipient of several international prizes including three IEEE-SPS Best Paper Awards and two Technical Achievement Awards from the IEEE (2008 SPS and EMBS 2010) .
24 | ICIP 2015 – Tutorials
TUTORIALS
TAM-T1 (Invited) – Deep Learning in Image Processing and Vision
InstructorsYoshua BENGIO and Roland MEMISEVIC, Université de Montréal, Canada
Classroom206AB
Course Motivation and DescriptionMachine learning enables computers to learn about the world around us but also holds fundamentally hard challenges associated with the so-called curse of dimensionality: the huge number of possible observations, events, or configurations of variables . Deep learning has been introduced to face that challenge by adding to the rich science of machine learning the notion of deep representation, the idea that better models can be learned if the machine constructs and discovers rich and abstract representations of the data . Past and future advances in deep learning hold incredible promises of technological advances on the path towards AI . This realization has strongly influenced information technology markets recently and there are already impressive fallouts from these investments in science and technology .
This tutorial will cover some of the main current topics in deep learning research and applications, starting from the theoretical underpinnings of distributed representations and depth, as well as a detailed description of the most commonly used method for obtaining parameter gradients, i .e ., the backpropagation algorithm . It will show how these ideas are incorporated in convolutional neural networks (for images) and recurrent neural networks (for capturing sequential structure) . Although the deep learning breakthroughs started with unsupervised learning, most of the current applications have focused on supervised learning, as many challenges but also major promises remain, in the land of deep unsupervised learning . A brief introduction will be given to the current state-of-the-art in this area and how these ideas are motivated the point of view of geometry (manifold learning) and the discovery of underlying causal factors . The tutorial will close with the lighter subject of applications of deep learning in industry, with a focus on computer vision and image processing .
Course OutlineThe course will cover the following aspects:
- Motivations for deep learning- Theoretical underpinnings, distributed representations & depth- Multi-layer networks and backpropagation- Convolutional networks and recurrent neural networks- Underlying factors, unsupervised learning and transfer learning- Auto-encoders and deep generative models- Applications to computer vision, speech and language understanding
All tutorials are half-day long and will be held on Sunday, Sept. 27, 2015 in either the morning (TAM) or afternoon (TPM).
ICIP 2015 – Tutorials | 25
Course PrerequisitesUndergraduate degree in mathematical sciences, or the equivalent .
Distributed Material- Copy of the slides
- Free access to draft chapters of the Deep Learning book (MIT Press, to appear) .
BibliographiesYoshua BENGIO (PhD in Computer Science, McGill University, 1991) did two post-docs at M .I .T . (Michael Jordan) and AT&T Bell Labs (Yann LeCun), then became professor at the Department of Computer Science and Operations Research at Université de Montréal . He authored two books and around 200 publications, the most cited being in the areas of deep learning, recurrent networks, probabilistic learning, natural language and manifold learning . He is among the most cited Canadian computer scientists and is or has been associate editor of the top journals in machine learning and neural networks . Since ‘2000 he holds a Canada Research Chair in Statistical Learning Algorithms, since ‘2006 an NSERC Industrial Chair, since ‘2005 is a Fellow of the Canadian Institute for Advanced Research . He is on the the NIPS foundation board and has been program chair and general chair for NIPS . He has co-organized the Learning Workshop for 14 years and co-created the new International Conference on Learning Representations . His current interests are centered around a quest for AI through machine learning, and include fundamental questions on deep learning and representation learning, the geometry of generalization in high-dimensional spaces, manifold learning, biologically inspired learning algorithms, and challenging applications of statistical machine learning .
Roland MEMISEVIC (PhD in Computer Science, University of Toronto, 2008) held positions as research scientist at PNYLab, Princeton, as post-doc at the University of Toronto and at ETH Zurich, and as a junior professor at the University of Frankfurt, Germany . In 2012, he joined the University of Montreal as an assistant professor in Computer Science . His research interests are in deep learning and computer vision with a focus on approaches that extend deep learning beyond object recognition towards more general tasks in vision and AI . His scientific contributions include approaches to learning motion and transformation patterns from images and videos, and approaches to learning invariance from data . He presented his work at conferences such as NIPS, CVPR, ICCV, ICML, AAAI, and in journals including PAMI, Neural Networks, Neural Computation . He served as a program committee member or reviewer for most of these and other conferences and journals in machine learning and computer vision . Roland Memisevic has been invited speaker at numerous deep learning events and tutorials .
TAM-T2 – HEVC/H.265 Video Coding Standard (v. 2) Including Range, Scalable, and Multiview Extensions
InstructorsDan GROIS, Fraunhofer Heinrich Hertz Institute, Germany Benjamin BROSS, Fraunhofer Heinrich Hertz Institute, Germany Detlev MARPE, Fraunhofer Heinrich Hertz Institute, Germany Karsten SUEHRING, Fraunhofer Heinrich Hertz Institute, Germany
Classroom205C
26 | ICIP 2015 – Tutorials
Course Motivation and DescriptionThe High-Efficiency Video Coding (HEVC) standard is the latest standard developed by a Joint Collaborative Team on Video Coding (JCT-VC), the first version of which was established by both ITU-T Video Coding Experts Group (VCEG) and the ISO/IEC Moving Pictures Expert Group (MPEG) in January, 2013 . When compared to its predecessor, i .e . the H .264/MPEG-4 Advanced Video Coding (AVC) standard, H .265/MPEG-H HEVC allowed achieving dramatic bit-rate savings due to employing state-of-the-art technological achievements . H .265/MPEG-H HEVC was also especially designed for the High Definition (HD) as well as to the Ultra-High Definition (UHD) video content, which often refers to both 3840x2160 (4K) or 7680x4320 (8K) resolutions in terms of luma samples, the demand for which is expected to dramatically increase in the near future .
This tutorial will be focused on the second version of the HEVC video coding standard, which was officially issued in October 2014, further including the combined extensions: RExt – the range extensions, SHVC – the scalable extension, and MV-HEVC – the multiview extension .
First, the speakers will provide a brief overview of the H .264/MPEG-4 AVC standard, followed by a detailed overview of the HEVC coding tools, which led to such significant improvements in coding efficiency compared to H .264/MPEG-4 AVC (including the quadtree coding structure, intra/inter-prediction, in-loop filtering, high-level syntax, transform coding, entropy coding, parallel coding tools, etc .), further making a special emphasis on the compression efficiency and performance . Second, the speakers will give an overview on the HEVC extensions: particularly, the range extensions (including extended bit depth, chroma format support, etc .), the scalable extension (including the up-sampling process, inter-layer prediction process, etc .), and the multiview extension (including the inter-view prediction, etc .) . Finally, this talk will be concluded by a discussion regarding further research directions and challenges .
Course Outline- Brief review of H .264/MPEG-4 Advanced Video Coding (AVC) standard;
- H .265/MPEG-H HEVC version 1 standard;
- H .265/MPEG-H HEVC version 2 standard, including RExt – the Range Extensions, SHVC – the Scalable Extension, and MV-HEVC – the Multiview Extension .
Course PrerequisitesThere are no course pre-requisites since the tutorial is aimed at an audience from very diverse backgrounds .
Distributed MaterialAttendees will receive the slides presented during the tutorial .
BiographiesDan GROIS received Ph .D . degree at the Communication Systems Engineering Department, Ben-Gurion University of the Negev (BGU), Israel, 2011 . From 2011 to 2013, Dan was a Senior Researcher at the Communication Systems Engineering Department, BGU . Starting from the middle of 2013, Dan is a Post-Doctoral Senior Researcher at the Image Processing & Analytics Department of the Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute (HHI), Germany . Dan is an author and co-author of about 40 publications in the area of image/video coding and data processing, which have been presented at top-tier international conferences, and published in various scientific journals, books, etc . In addition, Dan is a referee of top-tier conferences and international journals, such as the IEEE Trans . in Image Processing, IEEE Trans .
ICIP 2015 – Tutorials | 27
on Multimedia, IEEE Trans . on Signal Processing, Journal of Visual Comm . and Image Repres ., Elsevier, IEEE Sensors, SPIE Optical Engineering, etc . In 2013, Dan also served as a Guest Editor of the SPIE Optical Engineering journal . During his academic carrier, Dan was granted various fellowships, including Kreitman Fellowships and the ERCIM Alain Bensoussan Fellowship, which was provided by the FP7 Marie Curie Actions COFUND Programme . In addition, Dan currently is a Fellow of the PROVISION ITN project, which is a part of the European Union’s Marie Skłodowska-Curie Actions of the European Commission . Dan is a Senior Member of the IEEE, a Member of the ACM and SMPTE societies . Dan’s research interests include image and video coding and processing, video coding standards, particularly H .265 | MPEG-H High-Efficiency Video Coding (HEVC), region-of-interest scalability, computational complexity and bit-rate control, network communication and protocols, and future multimedia applications/systems .
Benjamin BROSS is a Project Manager at the Image Processing & Analytics Department of the Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Berlin and a part-time lecturer at the HTW University of Applied Sciences Berlin . He received the Dipl .-Ing . degree in electrical engineering from RWTH University Aachen, Germany in 2008 . During his studies he was working on three-dimensional image registration in medical imaging and on decoder side motion vector derivation in H .264/MPEG-4 Advanced Video Coding (AVC) . Since the development of the new H .265 | MPEG-H High-Efficiency Video Coding (HEVC) Standard, which started in 2010, Benjamin was very actively involved in the standardization process as a technical contributor and coordinator of core experiments . In July 2012, Benjamin was appointed as a co-chair of the editing Ad Hoc Group and became the chief editor of the HEVC video coding standard . At the Heinrich Hertz Institute, he is currently responsible for the development of HEVC conforming real-time encoders and decoders . Besides giving talks about the emerging HEVC video coding standard, Benjamin Bross is an author or co-author of several fundamental HEVC-related publications, and an author of two book chapters on HEVC and Inter-Picture Prediction Techniques in HEVC . He received the IEEE Best Paper Award at the 2013 IEEE International Conference on Consumer Electronics – Berlin in 2013 and the SMPTE Journal Certificate of Merit in 2014 .
Detlev MARPE is Head of the Image Processing & Analytics Department and Head of the Image & Video Coding Group of the Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute, Berlin . He is also active as a part-time lecturer at Technical University Berlin . He received the Dipl .-Math . degree from the Technical University of Berlin (TUB), Berlin, Germany and the Dr .-Ing . degree from the University of Rostock, Germany . For over a decade, he has successfully contributed to the standardization activities of ITU-T VCEG, ISO/IEC JPEG, and ISO/IEC MPEG for still image and video coding . During the development of the H .264 | MPEG-4 Advanced Video Coding (AVC) standard, he was chief architect of the CABAC entropy coding scheme as well as one of the main technical and editorial contributors to the so-called Fidelity Range Extensions (FRExt) with the addition of the High Profile in H .264 | MPEG-4 AVC . He was also one of the key people in designing the basic architecture of Scalable Video Coding (SVC) and Multiview Video Coding (MVC) as algorithmic and syntactical extensions of H .264 | MPEG-4 AVC . During the recent development of the H .265 | MPEG-H High-Efficiency Video Coding (HEVC) standard, he made significant contributions to the design of its fundamental building blocks . In addition, he also made successful proposals to the recent standardization of its Range Extensions and 3D Extensions . For his substantial contributions to the field of video coding, he received numerous awards, including, amongst many others, a nomination for the 2012 German Future Prize, the Karl Heinz Beckurts Award 2011, and two Emmy Engineering Awards in 2008 and 2009 . Detlev Marpe is author or co-author of more than 200 publications in the area of video coding and signal processing, . He is an IEEE Fellow and Member of the German Information Technology Society . He also serves as an Associate Editor of the IEEE Transactions on Circuits and Systems for Video Technology . His current research interests include image and video coding, signal processing for communications as well as computer vision and information theory .
28 | ICIP 2015 – Tutorials
Karsten SUEHRING is a Project Manager at the Video Coding & Analytics Department of the Fraunhofer Institute for Telecommunications - Heinrich Hertz Institute . He received the Dipl .-Inf . (FH) degree in applied computer science from the University of Applied Sciences, Berlin, Germany, in 2001 . Already as a student he was involved in MPEG standardization activities as maintainer of one of the reference implementations for MPEG-4 Part 2 . When the JCT-VC was founded in 2001, has was appointed as coordinator of the JM reference software of H .264/MPEG-4 AVC . Since June 2011 he was chairing the JCT-VC ad-hoc group on software development and is one of the coordinators for the HM reference software for HEVC . His current research interests include coding and transmission of video and audio content, as well as software design and optimization . At the Heinrich Hertz Institute, he is currently responsible for the development of H .264/AVC and HEVC decoder test products .
TAM-T3 – Image Processing for Cinema
InstructorsMarcelo BERTALMÍO, Universitat Pompeu Fabra, Spain
Classroom205B
Course Motivation and DescriptionThis tutorial provides a detailed overview of the relevant image processing techniques that are used in practice in cinema, covering a wide range of topics showing how image processing has become ubiquitous in movie-making, from shooting to exhibition . It is intended primarily for advanced undergraduate and graduate students in applied mathematics, image processing, computer science and related fields, for researchers from academia, and also for professionals from the movie industry .
The tutorial does not deal with visual effects or computer-generated images, but rather with all the ways in which image processing algorithms are used to enhance, restore, adapt or convert moving images, their purpose being to make the images look as good as possible while exploiting all the capabilities of cameras, projectors and displays .
Current digital cinema cameras match or even surpass film cameras in color capabilities, dynamic range and resolution, and several of the largest camera makers have ceased production of film cameras . On the exhibition side, film has practically disappeared from American movie theaters . And while many mainstream and blockbuster movies are still being shot on film, they are all digitized for postproduction . Therefore, in this tutorial we will equate «cinema» with «digital cinema», considering only digital cameras and digital movies, and not discussing algorithms for problems that are inherent to film, like the restoration of film scratches or color fading .
The tutorial is structured in three parts . The first one covers some fundamentals on optics and color . The second part explains how cameras work and details all the image processing algorithms that are applied in-camera . The last part is devoted to image processing algorithms that are applied off-line in order to solve a wide range of problems, presenting state-of-the-art methods . The mathematical presentation of all methods will concentrate on their purpose and idea, leaving formal proofs and derivations for the interested reader in the cited references .
ICIP 2015 – Tutorials | 29
Course Outline- Fundamentals on color, optics, photography;
- In-camera image processing: Image processing pipeline, Image sensors, Exposure control, Focus control, White balance, Color transformation, Gamma correction and quantization, Edge enhancement, Output formats;
- Noise and dynamic range: Classic denoising ideas, Non-local approaches, New trends and optimal denoising, High dynamic range imaging, Tone mapping;
- Color correction: Human color constancy, Computational color constancy under uniform illumination, Retinex and related methods, Cinema and colors at night, Color matching, Color stabilization;
- Image stabilization: Rolling shutter compensation, Compensation of camera motion;
- Zoom-In and Slow Motion;
- Gamut mapping: Color gamuts, Gamut reduction, Gamut extension, Validating a gamut mapping algorithm;
- In-painting: Video in-painting for specific problems, Video in-painting in a general setting, Video inpainting for stereoscopic 3D cinema .
Course PrerequisitesThere are no course pre-requisites since the tutorial is aimed at an audience from very diverse backgrounds .
Distributed MaterialAttendees will receive the slides presented during the tutorial .
BiographiesMarcelo BERTALMÍO received the Ph .D . degree in electrical and computer engineering from the University of Minnesota in 2001 . He is an Associate Professor at Universitat Pompeu Fabra, Spain .
His publications total some 7,000 citations . He was awarded the 2012 SIAG/IS Prize of the Society for Industrial and Applied Mathematics of the USA (SIAM) for co-authoring the most relevant image processing work published in the period 2008-2012 . Has received the Femlab Prize, the Siemens Best Paper Award, the Ramón y Cajal Fellowship, and the ICREA Academia Award, among other honors . He is an Associate Editor for SIAM-SIIMS and the secretary of SIAM’s activity group on imaging . Has an ERC-Starting Grant for his project “Image processing for enhanced cinematography” . Has written a book titled “Image Processing for Cinema”, published by CRC Press / Taylor & Francis . Has directed two award-winning feature-length films .
His current research interests are in developing image processing algorithms allowing to shoot cinema with no more artificial lighting than what people present at the scene need to be able to see . The approach is to work out software methods mimicking neural processes in the human visual system, and apply them to images captured with a regular digital movie camera .
30 | ICIP 2015 – Tutorials
TAM-T5 – Visual saliency: Fundamentals, Applications, and Recent Progress
InstructorsAli BORJI, University of Wisconsin-Milwaukee, USA Neil D . B . BRUCE, University of Manitoba, Canada Ming-Ming CHENG, Nankai University, China Jian LI, National University of Defense Technology, China
Classroom204B
Course Motivation and DescriptionRecently, visual saliency has received extensively growing attention across many disciplines including cognitive psychology, neurobiology, image processing, and computer vision . Based on our observed reaction times and estimated signal transmission times along biological pathways, human attention theories hypothesize that the human visual system processes only parts of an image in detail, with only limited processing of areas outside of the focus of attention . From an engineering perspective, such visual attention mechanisms have inspired a series of key research topics in the last few decades . One of the key forces behind these rapid developments is the vast amount of successful applications . These applications, marked by different requirements and points of emphasis have resulted in a rich kinship between fixation prediction, salient object detection, and objectness proposal generation .
It is noted that there has consistently been many papers about visual saliency appearing in ICIP over the past decade . While there are still many open issues and challenges (sometimes diverging arguments and debates) that need to be addressed in this area, the field of saliency computing continues to grow very rapidly . In this tutorial, we will introduce basic ideas, important models and applications of visual attention and saliency . Some key research issues will be discussed including top-down vs . bottom-up attention, and the relationship between fixation prediction, salient object detection, object proposal generation, etc . Recent advances in fixation prediction, salient object detection, and objectness proposals will be introduced in detail, with a significant emphasis on their respective potential applications . Finally, we will discuss the fairness of model evaluation criteria, model benchmarking, divergent opinions, open challenges, and potential future work .
Course OutlineThis tutorial will consist of 5 talks (about 35-40 minutes for each talk) . This begins with the fundamental knowledge and important classical models . Then, we discuss the divergence of, and correlation among different subareas (fixation prediction, salient object detection, and objectness proposals), followed by detailed introduction to each subarea . Finally, we discuss topics relating to model evaluation and benchmarking . The contents of the tutorial are as follows .
- Fundamentals of visual attention and saliency and some important models . [Dr . Bruce]- Top-down vs . bottom-up attention, relationship between fixation predictions, salient object detection,
object proposal generation, etc . [Dr . Borji]- Recent advances in fixation prediction, evaluation metrics and ground truth, and potential applications .
[Dr .Jian]
ICIP 2015 – Tutorials | 31
- Recent advances in salient object detection, and objectness proposals, and potential applications . [Dr .Cheng]
- The fairness of model evaluation criteria (for both fixation prediction and salient regions detection) and model benchmarking . [Dr . Borji]
Course PrerequisitesThe attendee only needs to have basic knowledge of digital image processing in order to follow the course .
Distributed MaterialAll materials will be distributed to the attendees electronically via webpage downloads . No physical materials will be distributed .
BibliographiesAli BORJI received his B .S . and M .S . degrees in computer engineering from the Petroleum University of Technology, Tehran, Iran, 2001 and Shiraz University, Shiraz, Iran, 2004, respectively . He received his Ph .D . degree in computational neurosciences from the Institute for Studies in Fundamental Sciences (IPM) in Tehran, 2009 . He then spent a year at University of Bonn as a postdoc . Before coming to the University of Wisconsin-Milwaukee in the fall of 2014, Dr . Borji was a postdoctoral scholar at iLab, University of Southern California, Los Angeles for four years .
Ming-Ming CHENG is an associate professor with College of Computer and Control Engineering, Nankai University . He received his PhD degree from Tsinghua University in 2012 under guidance of Prof . Shi-Min Hu, and working closely with Prof . Niloy Mitra . Then he worked as a research fellow for 2 years, working with Prof . Philip Torr in Oxford . Dr . Cheng’s research primarily centers on algorithmic issues in image understanding and processing, including image segmentation, editing, retrieval, etc . During the past 5 years, he has published a serials of influential papers in several sub-areas of visual saliency modeling, including salient object detection (e .g . his CVPR 2011 paper has received 790+ citations), objectness estimation (e .g . his CVPR 2014 oral paper has received 70+ citations and 3000+ source code downloads), and visual saliency based applications (e .g . his SIGGRAPH Asia 2009 paper ‘Sketch2Photo’ has received 250+ citations, and been reported by ‘The Telegraph’ from UK and ‘Spiegel’ from Germany) .
Neil D. B. BRUCE is an Assistant Professor at the University of Manitoba in Canada . His research interests include a variety of topics including both computer vision and human vision, image processing, visual attention, machine learning, computational neuroscience, information theory, sparse coding, 3D modeling and reconstruction, natural image statistics, and statistical and graphical models . Prior to joining the University of Manitoba he completed two post-doctoral fellowships, one at the Centre for Vision Research at York University, and the other at INRIA Sophia Antipolis . Previously, he completed a Ph .D . in the department of Computer Science and Engineering in 2008 as a member of the Centre for Vision Research at York University, Toronto, Canada . In 2003, he completed a M . A . Sc . in System Design Engineering at the University of Waterloo, and received an Honors B .Sc . with a double major in Computer Science and Mathematics from the University of Guelph in 2001 .
Jian LI is an assistant professor with National University of Defense Technology . He received the B .E . degree, the M .E . degree and the PhD Degree from National University of Defense Technology (NUDT), Changsha, P .R . China . From Jan 2010 to Jan 2011, he was a visiting Ph .D . student (Academic Trainee) at Center for Intelligent Machines (CIM) in McGill University under the supervision of Prof . Martin Levine .
32 | ICIP 2015 – Tutorials
TPM-T1 (Invited) – Computational Photography
InstructorsMohit GUPTA, Columbia University, USA Jean-François LALONDE, Université Laval, Canada
Classroom206AB
Course Motivation and DescriptionIn the last decade, computational photography has emerged as a vibrant field of research . A computational camera uses a combination of unconventional optics and novel algorithms to produce images that cannot otherwise be captured with traditional cameras . The design of such cameras involves the following two main aspects:
• Optical coding – modifying the design of a traditional camera by introducing programmable optical elements and light sources to capture maximal amount of scene information in images;
• Algorithm design – developing algorithms that take information captured by conventional or modified cameras, and create a visual experience that goes beyond the capabilities of traditional systems .
Examples of computational cameras that are already making an impact in the consumer market include wide field-of-view cameras (Omnicam), light-field cameras (Lytro), high dynamic range cameras (mobile cameras), multispectral cameras, motion sensing cameras (Leap Motion) and depth cameras (Kinect) .
This course serves as an introduction to the basic concepts in programmable optics and computational image processing needed for designing a wide variety of computational cameras, as well as an overview of the recent work in the field .
Course OutlineA brief history of photography − Camera Obscura − Film, Digital and Computational photography;
Coded photography − Novel camera designs and functionalities, including:
- Optical coding approaches: Aperture, Image plane, and Illumination coding; Camera arrays,
- Novel functionalities: Light field cameras − Extended DOF cameras, Hyperspectral cameras − Ultra high-resolution cameras (Gigapixel) − HDR cameras − Post-capture refocusing and Post-capture resolution trade-offs,
- Depth cameras: Structured light − Time-of-flight,
- Compressive sensing: Single pixel and High speed cameras;
Augmented photography: algorithmic tools for novel visual experiences:
- Multiple viewpoints: Image stitching, panoramas − Gigapixel imaging − Large-scale structure from motion,
- Data-driven approaches: Texture transfer − Object transfer − Color/attribute/style transfer,
- 2D image plane vs 3D scene: Scene geometry estimation − Light, geometry, and object editing,
ICIP 2015 – Tutorials | 33
- Smarter tools: Content-aware inpainting − Edit propagation in image collections − Matte cutouts,
- Smartphone photography: Cheap optics / powerful computing − Virtual tripod, Burst-mode HDR and denoising − Video stabilization,
- Motion magnification and visual microphone;
Future and impact of photography:
- «Social/collaborative photography» or the Internet of Cameras,
- Wearable and flexible cameras,
- Seeing the invisible: seeing around corners, through walls, laser speckle photography,
- Image forensics,
- Next generation applications (personalized health monitoring, robotic surgery, self-driving cars, astronomy) .
Course PrerequisitesBasic knowledge of linear algebra and probability .
Distributed MaterialCourse PowerPoint / keynote slides .
BibliographiesJean-François LALONDE is an assistant professor in Electrical and Computer Engineering at Laval University, Quebec City . Previously, he was a Post-Doctoral Associate at Disney Research, Pittsburgh . He received a B .Eng . degree in Computer Engineering with honors from Laval University, Canada, in 2004 . He earned his M .S at the Robotics Institute at Carnegie Mellon University in 2006 and received his Ph .D ., also from Carnegie Mellon, in 2011 . His Ph .D . thesis won the 2010-11 CMU School of Computer Science Distinguished Dissertation Award, and was partly supported by a Microsoft Research Graduate Fellowship . After graduation, he became a Computer Vision Scientist at Tandent, where he helped develop LightBrush™, the first commercial intrinsic imaging application, and introduced the technology of intrinsic videos at SIGGRAPH 2012 . His work focuses on lighting-aware image understanding and synthesis by leveraging large amounts of data . More details about his research can be found here .
Mohit GUPTA will start as an assistant professor in the CS department at the University of Wisconsin-Madison in January ’16 . He is currently a research scientist in the CAVE lab at Columbia University . He received a B .Tech . in computer science from Indian Institute of Technology Delhi in 2003, an M .S . from Stony Brook University in 2005 and a Ph .D . from the Robotics Institute, Carnegie Mellon University in 2011 . His research interests are in computer vision and computational imaging . His focus is on designing computational cameras that enable computer vision systems to perform robustly in demanding real-world scenarios, as well as capture novel kinds of information about the physical world . Details can be found here .
34 | ICIP 2015 – Tutorials
TPM-T2 – Example-based Super Resolution
InstructorsJordi SALVADOR, Technicolor – Deutsche Thomson, Germany Mehmet TÜRKAN, Technicolor, France & Izmir University of Economics, Turkey
Classroom205C
Course Motivation and DescriptionSuper Resolution has been one of the most popular research disciplines in image processing during the last years . From the research perspective, the reasons for this success include the interesting solutions to combinations of different image processing problems (registration, deblurring, denoising…) or the increasing understanding of the subspace of natural images and its proper application in recent statistical models . Besides, the introduction of new imaging standards with progressively higher resolutions favors the interest on new upscaling algorithms also in the industry . When properly designed, super-resolution methods are capable of adapting legacy contents to the resolution offered by the latest display technologies, either during postproduction or directly at the end user’s devices, thus offering optimal visual experiences .
During the last years, research on example-based super resolution has received the main focus of attention essentially due to two reasons: In first place, in contrast with classic multi-frame super resolution, the use of more advanced image priors alleviates the requirement of having different captures of the same scene with subpixel shifts . Furthermore, numerical stability problems that might arise when reconstructing a super-resolved image under the commonly over-simplified parametric models in multi-frame super resolution are also avoided by using more meaningful non-parametric image priors .
This tutorial is designed to present an evolutionary timeline of the many existing and continuously improving state-of-the-art approaches that benefit from the favorable features of example-based super resolution, with insights on the theoretical background, implementation issues (including parallelization) and discussion on the practical applicability .
Course OutlineThe tutorial provides a thorough introduction and overview of example-based super-resolution, covering the most successful algorithmic approaches, the theory behind them, implementation insights, and some hints about current challenges and expected outcomes for the near future . The list of covered topics is as follows .
Introduction to super resolution
This section introduces early (non-example-based) super-resolution pipelines and the rationale of the example-based concept covered by the rest of the tutorial .
- A historic view of super resolution
- Multi-frame super resolution
- Example-based super resolution
ICIP 2015 – Tutorials | 35
Self-similarity-based super resolution
This part of the tutorial describes super-resolution models where examples are learned from one or more scales of the input data . This strategy can be efficiently implemented when hardware solutions for block search are available, and has the nice property of being implicitly adaptive to the input contents .
- High-frequency transfer
- Locally linear embedding
- Robust self-similarity
Super resolution by external learning
This section will cover super-resolution strategies where larger amounts of data can be exploited to build suitable regression models during an offline training stage . These models can then be efficiently applied during the online inference stage . Under proper configurations, the generalizability of these machine-learning approaches can be virtually as high as that of self-similarity-based approaches and the reconstruction quality is often superior .
- Dictionaries
- Anchored neighbors and variations
- Hybrid models: self-similarity and regression
- Regression trees
- Deep learning
Course PrerequisitesThe attendees should be familiar with basic concepts in image processing, probability and statistics (undergraduate courses suffice), but the tutorial is self-contained for the most part .
Distributed MaterialAll registered attendees shall receive a copy of of the supporting slides .
BibliographiesJordi SALVADOR is project leader at Technicolor R&I in Germany, where he started working in 2011, and member of Technicolor’s Fellowship Network since 2014 . His main research focus is on machine learning for example-based super resolution and image restoration . Formerly, he received a M .Sc . in Telecommunications (equivalent to Electrical) Engineering in 2006 and a M .Sc . in the European MERIT program in 2008, both from the Universitat Politècnica de Catalunya (UPC) in Barcelona . He obtained the Ph .D . degree in 2011, also from UPC, where he contributed to projects of the Spanish Science and Technology System (VISION, PROVEC) and to a European FP6 project (CHIL) as research assistant on multi-camera 3D reconstruction . He has also served as reviewer in conferences and journals like EUSIPCO and IEEE Transactions on Image Processing . His research interests include 3D reconstruction, real-time and parallel algorithms, new computer-human interfaces, image and video restoration, super resolution, inverse problems and machine learning .
36 | ICIP 2015 – Tutorials
Mehmet TÜRKAN is a researcher at Technicolor R&I in Cesson-Sévigné, France, since 2011 . He will be joining the Engineering and Computer Science Faculty of Izmir University of Economics, Izmir, Turkey, in Sept 2015 . He obtained his PhD degree in computer science from INRIA-Bretagne Atlantique- and University of Rennes 1, Rennes, France . He received his MSc and BSc (Hhons) degrees both in electrical and electronics engineering from Bilkent University, Ankara, and Eskisehir Osmangazi University, Eskisehir, Turkey, respectively . He was involved with the European Commission (EC) 6th Framework Program (FP6) Multimedia Understanding through Semantics, Computation and Learning Network of Excellence (MUSCLE-NoE), EC FP6 Integrated Three-Dimensional Television–Capture, Transmission, and Display Network of Excellence (3-DTV-NoE), and European UltraHD-4U research projects . His general research interests are in the area of signal processing with an emphasis on image and video processing and compression, pattern recognition and classification, and computer vision . Dr . Türkan was the recipient of the Best Student Paper Award in the 2010 IEEE International Conference on Image Processing (ICIP) and was a nominee for the Best Student Paper Award in the 2011 IEEE ICIP .
TPM-T3 – Perceptual Metrics for Image and Video Quality in a Broader Context: From Perceptual Transparency to Structural Equivalence
InstructorsThrasyvoulos N . PAPPAS, Northwestern University, Evanston, Illinois, USA Sheila S . HEMAMI, Northeastern University, Boston, Massachusetts, USA
Classroom205B
Course Motivation and DescriptionWe will examine objective criteria for the evaluation of image quality that are based on models of visual perception . Our primary emphasis will be on image fidelity, i .e ., how close an image is to a given original or reference image, but we will broaden the scope of image fidelity to include structural equivalence . We will also discuss no-reference and limited-reference metrics . We will examine a variety of applications with special emphasis on image and video compression . We will examine near-threshold perceptual metrics, which explicitly account for human visual system (HVS) sensitivity to noise by estimating thresholds above which the distortion is just-noticeable, and supra-threshold metrics, which attempt to quantify visible distortions encountered in high compression applications or when there are losses due to channel conditions . We will also consider metrics for structural equivalence, whereby the original and the distorted image have visible differences but both look natural and are of equally high visual quality . We will also take a close look at procedures for evaluating the performance of quality metrics, including database design, models for generating realistic distortions for various applications, and subjective procedures for metric development and testing . Throughout the course, we will discuss both the state of the art and directions for future research .
This course will enable you to:
- Gain a basic understanding of the properties of the human visual system and how current applications (image and video compression, restoration, retrieval, etc .) that attempt to exploit these properties .
- Gain an operational understanding of existing perceptually-based and structural similarity metrics, the types of images/artifacts on which they work, and their failure modes .
ICIP 2015 – Tutorials | 37
- Understand current distortion models for different applications, and how they can be used to modify or develop new metrics for specific contexts .
- Understand the differences between sub-threshold and supra-threshold artifacts, the HVS responses to these two paradigms, and the differences in measuring that response .
- Understand criteria by which to select and interpret a particular metric for a particular application .
- Understand the capabilities and limitations of full-reference, limited-reference, and no-reference metrics, and why each might be used in a particular application .
Course Outline- Applications: Image and video compression, restoration, retrieval, graphics, etc .
- Human visual system review
- Near-threshold perceptual quality metrics
- Supra-threshold perceptual quality metrics
- Structural similarity metrics
- Perceptual metrics for texture analysis and compression – structural texture similarity metrics
- No-reference and limited-reference metrics
- Models for generating realistic distortions for different applications
- Design of databases and subjective procedures for metric development and testing
- Metric performance comparisons, selection, and general use and abuse
- Embedded metric performance, e .g ., for rate-distortion optimized compression or restoration
- Metrics for specific distortions, e .g ., blocking and blurring
- Metrics for specific attributes, e .g ., contrast, roughness, and glossiness
- Multimodal applications
Course Prerequisites- Basic understanding of image compression algorithms
- Background in digital signal processing and basic statistics: frequency-based representations, filtering, distributions .
- Level: Intermediate
Distributed MaterialPDF of PowerPoint presentation
BibliographiesThrasyvoulos N. PAPPAS received the S .B ., S .M ., and Ph .D . degrees in electrical engineering and computer science from MIT in 1979, 1982, and 1987, respectively . From 1987 until 1999, he was a Member of the Technical Staff at Bell Laboratories, Murray Hill, NJ . He is currently a professor in the Department of Electrical and Computer Engineering at Northwestern University, which he joined in 1999 . His research interests are in image and video quality and compression, image and video analysis, content-based retrieval, perceptual
38 | ICIP 2015 – Tutorials
models for multimedia processing, model-based halftoning, and tactile and multimodal interfaces . Prof . Pappas will be serving as Vice-President Publications, IEEE Signal Processing Society (2015-107) . He has served as editor-in-chief of the IEEE Transactions on Image Processing (2010-12), elected member of the Board of Governors of the Signal Processing Society of IEEE (2004-06), chair of the IEEE Image and Multidimensional Signal Processing (now IVMSP) Technical Committee, technical program co-chair of ICIP-01 and ICIP-09, and co-chair of the 2011 IEEE IVMSP Workshop on Perception and Visual Analysis . He has also served as co-chair of the 2005 SPIE/IS&T Electronic Imaging Symposium, and since 1997 he has been co-chair of the SPIE/IS&T Conference on Human Vision and Electronic Imaging . Dr . Pappas is a Fellow of IEEE and SPIE .
Sheila S. HEMAMI received the B .S .E .E . degree from the University of Michigan in 1990, and the M .S .E .E . and Ph .D . degrees from Stanford University in 1992 and 1994, respectively . She was with Hewlett-Packard Laboratories in Palo Alto, California in 1994 and was with the School of Electrical Engineering at Cornell University from 1995-2013 . She is currently Professor and Chair of the Department of Electrical & Computer Engineering at Northeastern University in Boston, MA . Dr . Hemami’s research interests broadly concern communication of visual information from the perspectives of both signal processing and psychophysics . She was elected a Fellow of the IEEE in 2009 for her for contributions to robust and perceptual image and video communications . Dr . Hemami has held various visiting positions, most recently at the University of Nantes, France and at École Polytechnique Fédérale de Lausanne, Switzerland . She has received numerous university and national teaching awards, including Eta Kappa Nu’s C . Holmes MacDonald Award . She will be serving as Vice-President Publications Products and Services, IEEE (2015) . She was a Distinguished Lecturer for the IEEE Signal Processing Society in 2010-11, was editor-in-chief for the IEEE Transactions on Multimedia from 2008-10 . She has held various technical leadership positions in the IEEE .
TPM-T4 – Spectral Methods in 3D Data Analysis
InstructorsMichael BRONSTEIN, University of Lugano, Switzerland & Perceptual Computing, Intel
Classroom205A
Course Motivation and DescriptionOver the last decade, the intersections between 3D shape analysis and image processing have become a topic of increasing interest in the computer graphics community . Nevertheless, when attempting to apply current image analysis methods to 3D shapes (feature-based description, registration, recognition, indexing, etc .) one has to face fundamental differences between images and geometric objects . Shape analysis poses new challenges that are non-existent in image analysis .
The purpose of this course is to overview the foundations of shape analysis and to formulate state-of-the-art theoretical and computational methods for shape description based on their intrinsic geometric properties . The emerging field of spectral and diffusion geometry provides a generic framework for many methods in the analysis of geometric shapes and objects . The course will present in a new light the problems of shape analysis based on diffusion geometric constructions such as manifold embeddings using the Laplace-Beltrami and heat operator, 3D feature detectors and descriptors, diffusion and commute-time metrics, functional correspondence, and spectral symmetry .
ICIP 2015 – Tutorials | 39
Course OutlineThe course is divided in four sections, covering the topics listed below .
Theoretical foundations
Diffusion operators, their spectral properties, Fourier analysis on manifolds, similarities to the classical case − Heat diffusion equation on a Riemannian manifold − The Laplace-Beltrami operator − Diagonalization of Laplacians, relation to joint approximate diagonalization problems − The fundamental solution based on the heat kernel − The discrete heat operator and its basic algebraic properties − Scale-space and heat diffusion − The diffusion and the commute-time distances .
Shape representation
Manifold embedding using the heat operator − Relationship with Laplacian embedding and diffusion embeddings − Geometric and photometric diffusion − Local and global diffusion geometry − Feature detection and feature description − Heat and wave kernel signatures − Optimal spectral descriptors . Convolutional neural networks on manifolds − Volumetric vs surface diffusion .
Applications
Minimum-distortion similarity and correspondences − Functional correspondence, relation to sparse coding and matrix completion problems − Intrinsic symmetry detection − Shape retrieval, bag-of-feature methods − Benchmarks .
Implementation and application examples
Live demos in MATLAB to exemplify the main concepts of the tutorial .
Course PrerequisitesBasic knowledge of signal/image processing, Fourier analysis
Distributed MaterialCourse slides will be available online .
BibliographiesMichael BRONSTEIN is a professor in the Faculty of Informatics at the University of Lugano (USI), Switzerland and a Research Scientist at the Perceptual Computing group, Intel, Israel . Michael got his B .Sc . in Electrical Engineering (2002) and Ph .D . in Computer Science (2007), both from the Technion, Israel . His main research interests are theoretical and computational methods in spectral and metric geometry and their application to problems in computer vision, pattern recognition, computer graphics, image processing, and machine learning . His research appeared in international media and was recognized by numerous awards . In 2012, Michael received the highly competitive European Research Council (ERC) grant . In 2014, he was invited as a Young Scientist to the World Economic Forum New Champions meeting, an honor bestowed on forty world’s leading scientists under the age of 40 . Besides academic work, Michael is actively involved in the industry . He was the co-founder of the Silicon Valley start-up company Novafora, where he served as VP of technology (2006-2009), responsible for the development of algorithms for large-scale video analysis . He was one of the principal inventors and technologists at Invision, an Israeli startup developing 3D sensing technology acquired by Intel in 2012 and released under the RealSense brand .
40 | ICIP 2015 – Tutorials
TPM-T5 – Sparse stochastic processes: A unifying statistical framework for modern image processing
InstructorsMichael UNSER, EPFL, Switzerland
Classroom204B
Course Motivation and DescriptionSparsity and compressed sensing are very popular topics in image processing . More and more, researchers are relying on the related l1-type minimization schemes to solve a variety of ill-posed problems in imaging . The paradigm is well established with a solid mathematical foundation, although the arguments that have been put forth in the past are mostly deterministic . In this tutorial, we shall introduce the participants to the statistical side of this story . As an analogy, think of the foundational role of Gaussian stationary processes: these justify the use of the Fourier transform or DCT and lend themselves to the formulation of MMSE/MAP estimators based on the minimization of quadratic functionals .
The relevant objects here are sparse stochastic processes (SSP), which are continuous-domain processes that admit a parsimonious representation in a matched wavelet-like basis . Thus, they exhibit the kind of sparse behavior that has been exploited by researchers in recent years for designing second-generation algorithms for image compression (JPEG 2000), compressed sensing, and the solution of ill-posed inverse problems (l1vs . l2 minimization) .
The construction of SSPs is based on an innovation model that is an extension of the classical filtered-white-noise representation of a Gaussian stationary process . In a nutshell, the idea is to replace 1) the traditional white Gaussian noise by a more general continuous-domain entity (Lévy innovation) and 2) the shaping filter by a more general linear operator . We shall present the functional tools for the complete characterization of these generalized processes and the determination of their transform-domain statistics . We shall also describe self-similar models (non-Gaussian variants of fBm) that are well suited for image processing .
We shall then apply those models to the derivation of statistical algorithms for solving ill-posed problems in imaging . This allows for a reinterpretation of popular sparsity-promoting processing schemes—such as total-variation denoising, LASSO, and wavelet shrinkage—as MAP estimators for specific types of SSPs . It also suggests novel alternative Bayesian recovery procedures that minimize the estimation error (MMSE solution) . The concepts will be illustrated with concrete examples of sparsity-based image processing including denoising, deconvolution, tomography, and MRI reconstruction from non-Cartesian k-space samples .
Course OutlineIntroduction
- Classical reconstruction algorithms and the Gaussian hypothesis
- Variational formulations: from l2- to l1-norm minimization
- Compressed sensing
ICIP 2015 – Tutorials | 41
Part I: Statistical modeling An introduction to sparse stochastic processes
- Generalized innovation model
- Statistical characterization of signals
Part II: Recovery of sparse signals Reconstruction of biomedical images
- Discretization of inverse problems
- Generic MAP estimator (iterative reconstruction algorithm)
- Applications: deconvolution microscopy, MRI, x-ray tomography
From MAP to MMSE estimation
- MMSE estimation of Markov processes
- Iterative wavelet-domain MMSE denoising
Course PrerequisitesBasic knowledge of statistical signal processing (MAP estimation), optimization techniques (iterative algorithms), and functional analysis (Fourier transform, generalized functions, differential equations)
Distributed MaterialCopies of the slides Complete lecture notes for the tutorial (and beyond) are available on the web at http://www .sparseprocesses .org
BibliographiesMichael UNSER is Professor and Director of EPFL’s Biomedical Imaging Group, Lausanne, Switzerland . His main research area is biomedical image processing . He has a strong interest in sampling theories, multiresolution algorithms, wavelets, the use of splines for image processing, and, more recently, stochastic processes . He has published about 250 journal papers on those topics . He is the leading author of “An introduction to sparse stochastic processes”, Cambridge University Press, 2014 .
From 1985 to 1997, he was with the Biomedical Engineering and Instrumentation Program, National Institutes of Health, Bethesda USA, conducting research on bioimaging and heading the Image Processing Group .
Dr . Unser is a fellow of the IEEE (1999), an EURASIP fellow (2009), and a member of the Swiss Academy of Engineering Sciences . He is the recipient of several international prizes including three IEEE-SPS Best Paper Awards and two Technical Achievement Awards from the IEEE (2008 SPS and EMBS 2010) .
42 | ICIP 2015 – Awards
AWARDS
ICIP 2015 presents five types of awards and recognition that have been attributed to accepted papers after a careful selection process conducted by an experienced award committee:
• Top 10% Paper Recognition . Based on reviewer scores and recommendations, 127 papers have been specifically recognized as the “Top 10%” papers in ICIP 2015 based on the average score of all reviewers . These papers are identified by a « in the technical program .
• Best Paper Award . A panel of experts reviewed the top papers of ICIP 2015 as well as papers recommended by reviewers and Area Chairs . Based on these careful reviews, two papers were selected for the award of “Best Paper at ICIP 2015 .” The awards will be announced during the conference banquet .
• Best Student Paper Awards. The same panel of experts reviewed the same pool of top papers and selected three papers whose first author was a student at the time of submission . These papers will receive the award of “Best Student Paper at ICIP 2015” at the conference banquet .
• Best Industry Paper Award . In addition, a new Signal Processing Society level award will be established at ICIP 2015 for Best Industry Paper, for a paper whose primary authors are from industry . Industry will be broadly defined to include government and non-profit in addition to commercial entities . Judging will be based on general quality, novelty, maturity of the technology, and industrial impact of the described work .
• Best Three-Minute Thesis (3MT) Video Contest. Newly introduced at ICIP 2015, this award recognizes the academic, presentation, research communication skills and students’ capacity to explain their research in a language appropriate to an educated but non-specialist audience .
ICIP 2015 – SPS Administrative Meetings | 43
SPS ADMINISTRATIVE MEETINGS
Sunday, Sept. 27
Welcome Reception 19:00-22:00 Room: La Citadelle
Monday, Sept. 28
Opening Ceremony 08:00-09:00 Room: 200AB
Image, Video, and Multidimensional Signal Processing Technical Committee 12:30-14:00 Room: 2105 Meeting
Women in Signal Processing Luncheon 12:30-14:00 Room: 206B
Banquet co*cktail 19:00-20:00 Room: Foyer 2
Banquet 20:00-23:00 Room: 200AB
Tuesday, Sept. 29
IEEE Transactions on Computational 07:30-09:00 Room: 2105 Imaging Editorial Board Meeting
Conference Board Executive Subcommittee 08:00-10:00 Room: 207 Meeting
CISIG-L: Computational Imaging Special 12:30-14:00 Room: 2105 Interest Group Meeting
ICIP to ICIP Meeting 12:30-14:00 Room: 207
Get-Together Students-Employers Luncheon 12:30-14:00 Room: 206B
SPS Young Professionals and Practicing 17:00-19:00 Room: National Assembly Library Engineers Networking Event
Publication Board Dinner 18:00-19:00 Room: 2104AB
Publication Board Meeting 19:00-23:00 Room: 2105
44 | ICIP 2015 – SPS Administrative Meetings
Wednesday, Sept. 30
Executive Committee Lunch 12:30-16:30 Room: 2105
IEEE Transactions on Image 12:30-14:00 Room: 207 Processing Editorial Board Meeting
AE Best Practice Discussion 17:00-19:00 Room: 207
Conference Board Dinner 18:00-19:00 Room: 2101
Conference Board Meeting 19:00-23:00 Room: 2105
Thursday, Oct. 1
Board of Governors Breakfast 08:00-09:00 Room: 310
Board of Governors Meeting 09:00-17:00 Room: 311
Board of Governors Lunch 12:00-13:00 Room: 310
ICIP 2015 – Technical Program | 45
PROGRAM
46 | ICIP 2015 – Technical Program
SUNDAY SEPTEMBER 27
TAM-T1: Deep Learning in Image Processing and Vision Sunday, 09:00-12:30TUTORIAL Room: 206ABSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TAM-T2: HEVC/H.265 Video Coding Standard (v. 2) Including Range, Scalable, and Multiview Extensions Sunday, 09:00-12:30TUTORIAL Room: 205CSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TAM-T3: Image Processing for Cinema Sunday, 09:00-12:30TUTORIAL Room: 205BSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TAM-T5: Visual saliency: Fundamentals, Applications, and Recent Progress Sunday, 09:00-12:30TUTORIAL Room: 204BSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TPM-T1: Computational Photography Sunday, 13:30-17:00TUTORIAL Room: 206ABSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TPM-T2: Example-based Super Resolution Sunday, 13:30-17:00TUTORIAL Room: 205CSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TPM-T3: Perceptual Metrics for Image and Video Quality in a Broader Context: From Perceptual Transparency to Structural Equivalence Sunday, 13:30-17:00TUTORIAL Room: 205BSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
ICIP 2015 – Technical Program | 47
TPM-T4: Spectral Methods in 3D Data Analysis Sunday, 13:30-17:00TUTORIAL Room: 205ASession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
TPM-T5: Sparse Stochastic Processes: A unifying Statistical Framework for Modern Image Processing Sunday, 13:30-17:00TUTORIAL Room: 204BSession Chair(s): Janusz KONRAD, Boston University André ZACCARIN, Laval University
WLCM-E: Welcome Reception Sunday, 19:00-22:00SOCIAL EVENT Room: LA CITADELLE DE QUÉBECSession Chair(s): Paul FORTIER, Laval University
48 | ICIP 2015 – Technical Program
MONDAY SEPTEMBER 28
PLE-N1: Plenary – Deep Learning Monday, 09:00-10:00PLENARY Room: 200ABSession Chair(s): Stéphane COULOMBE, École de technologie supérieure Kenneth ROSE, University of California
PresenterYoshua Bengio, Professor, Department of Computer Science and Operations Research, University of Montreal; Canada Research Chair in Statistical Learning Algorithms
SummaryAlthough neural networks have long been considered lacking in theory and much remains to be done, theoretical evidence is mounting and will be discussed, to support distributed representations, depth of representation, the non-convexity of the training objective, and the probabilistic interpretation of learning algorithms (especially of the auto-encoder type, which were lacking one). Empirical work in a variety of applications has demonstrated that, when well trained, such deep architectures can be highly successful, remarkably breaking through previous state-of-the-art in many areas, including speech recognition, object recognition, language models, and transfer learning. This talk will summarize the advances that have made these breakthroughs possible, and end with questions about some major challenges still ahead of researchers in order to continue our climb towards AI-level competence.
ARS-O4: Edge and Shape Models Monday, 10:30-12:30LECTURE Room: 202Session Chair(s): Paul FIEGUTH, University of Waterloo
10:30 ARS-O4.1 – RECURSIVE ORIENTATION ESTIMATION BASED ON HYPERSURFACE RECONSTRUCTIONSalma DOGHRAJI, IMS, UMR 5218Marc DONIAS, IMS, UMR 5218Yannick BERTHOUMIEU, IMS, UMR 5218
10:50 ARS-O4.2 – PROBABILISTIC CONTINUOUS EDGE DETECTION USING LOCAL SYMMETRYGerald MWANGI, University of HeidelbergPaul FIEGUTH, University of WaterlooChristoph S . GARBE, University of Heidelberg
11:10 « ARS-O4.3 – COMPLEX-VALUED HOUGH TRANSFORMS FOR CIRCLESMarcelo CICCONET, New York UniversityDavi GEIGER, New York UniversityMichael WERMAN, The Hebrew University of Jerusalem
ICIP 2015 – Technical Program | 49
11:30 ARS-O4.4 – STOCHASTIC MODEL FOR CURVILINEAR STRUCTURE RECONSTRUCTION USING MORPHOLOGICAL PROFILESSeong-Gyun JEONG, InriaYuliya TARABALKA, InriaJosiane ZERUBIA, Inria
11:50 « ARS-O4.5 – ON THE ROLE OF NON-LOCAL MENGER CURVATURE IN IMAGE PROCESSINGGuy GILBOA, TechnionEli APPLEBOIM, TechnionEmil SAUCAN, TechnionYehoshua Y . ZEEVI, Technion
12:10 ARS-O4.6 – ACTIVE SHAPE MODEL UNLEASHED WITH MULTI-SCALE LOCAL APPEARANCEQiang ZHANG, University of WarwickAbhir BHALERAO, University of WarwickEmma HELM, University Hospitals Coventry and WarwickshireCharles HUTCHINSON, University Hospitals Coventry and Warwickshire
ARS-P27: Saliency I Monday, 10:30-12:30POSTER Room: POSTER DSession Chair(s): Patrick LE CALLET, Polytech Nantes – Université de Nantes
ARS-P27.1 – SALIENCY DETECTION WITH MULTI-SCALE SUPERPIXELSHuchuan LU, Dalian University of TechnologyXiang RUAN, Omron Corporation
ARS-P27.2 – SALIENCY DETECTION USING A BACKGROUND PROBABILITY MODELJunling LI, Communication University of ChinaFang MENG, Communication University of ChinaYichun ZHANG, China Art Science and Technology Institute
ARS-P27.3 – STRUCTURED SALIENCY FUSION BASED ON DEMPSTERSHAFER THEORYXingxing WEI, Tianjin UniversityZhiqiang TAO, Tianjin UniversityChangqing ZHANG, Tianjin UniversityXiaochun CAO, Tianjin University
ARS-P27.4 – SALIENCY DETECTION USING TWO-STAGE SCORINGYaqi LIU, Beijing Technology and Business UniversityQiang CAI, Beijing Technology and Business UniversityXiaobin ZHU, Beijing Technology and Business UniversityJian CAO, Beijing Technology and Business UniversityHaisheng LI, Beijing Technology and Business University
ARS-P27.5 – A LOCATION-AWARE SCALE-SPACE METHOD FOR SALIENT OBJECT DETECTIONDan XIANG, Soochow UniversityBaojiang ZHONG, Soochow UniversityKai-Kuang MA, Nanyang Technological University
«
«
«
«
50 | ICIP 2015 – Technical Program
ARS-P34: Visual Content Analysis Monday, 10:30-12:30POSTER Room: POSTER ASession Chair(s): Sanghoon LEE, Yonsei University
ARS-P34.1 – LARGE VISUAL WORDS FOR LARGE SCALE IMAGE CLASSIFICATIONSheng TANG, Institute of Computing Technology, Chinese Academy of SciencesHui CHEN, Institute of Computing Technology, Chinese Academy of SciencesKe LV, University of Chinese Academy of SciencesYongdong ZHANG, Institute of Computing Technology, Chinese Academy of Sciences
ARS-P34.2 – DYNAMIC TIME-ALIGNMENT K-MEANS KERNEL CLUSTERING FOR TIME SEQUENCECLUSTERINGJoseph SANTARCANGELO, Ryerson UniversityXiao-Ping ZHANG, Ryerson University
ARS-P34.3 – EXEMPLAR BASED METRIC LEARNING FOR ROBUST VISUAL LOCALIZATIONCedric LE BARZ, THALESNicolas THOME, Sorbonne University UPMC LIP6Matthieu CORD, Sorbonne University UPMC LIP6Stephane HERBIN, ONERAMartial SANFOURCHE, ONERA
ARS-P34.4 – INDEXING FINGERPRINT DATABASE WITH MINUTIAE BASED COAXIAL GAUSSIAN TRACK CODE AND QUANTIZED LOOKUP TABLEKamlesh TIWARI, Indian Institute of Technology KanpurPhalguni GUPTA, Indian Institute of Technology Kanpur
ARS-P34.5 – T-CLUSTERING: IMAGE CLUSTERING BY TENSOR DECOMPOSITIONAmara TARIQ, University of Central FloridaHassan FOROOSH, University of Central Florida
ARS-P41: Video Retrieval Monday, 10:30-12:30POSTER Room: POSTER BSession Chair(s): Jean-Philippe THIRAN, EPFL
ARS-P41.1 – FRAME-LEVEL MATCHING OF NEAR DUPLICATE VIDEOS BASED ON TERNARY FRAME DESCRIPTOR AND ITERATIVE REFINEMENTKyung-Rae KIM, Korea UniversityWon-Dong JANG, Korea UniversityChang-Su KIM, Korea University
ARS-P41.2 – THE THU MULTI-VIEW FACE DATABASE FOR VIDEOCONFERENCESLinhao DONG, Tsinghua UniversityXiaoming TAO, Tsinghua UniversityYang LI, Tsinghua UniversityJichuan LU, Tsinghua UniversityZizhuo ZHANG, Tsinghua University
ICIP 2015 – Technical Program | 51
ARS-P41.3 – TEMPORAL AGGREGATION FOR LARGE-SCALE QUERY-BY-IMAGE VIDEO RETRIEVALAndre ARAUJO, Stanford UniversityJason CHAVES, Stanford UniversityRoland ANGST, Stanford UniversityBernd GIROD, Stanford University
ARS-P41.4 – FAST OBJECT INSTANCE SEARCH IN VIDEOS FROM ONE EXAMPLEJingjing MENG, Nanyang Technological UniversityJunsong YUAN, Nanyang Technological UniversityYap-Peng TAN, Nanyang Technological UniversityGang WANG, Nanyang Technological University
ARS-P42: Saliency II Monday, 10:30-12:30POSTER Room: POSTER ESession Chair(s): Patrick LE CALLET, Polytech Nantes – Université de Nantes
ARS-P42.1 – SPARSE CODING-BASED SPATIOTEMPORAL SALIENCY FOR ACTION RECOGNITIONTao ZHANG, Shanghai Jiaotong UniversityWenjing JIA, University of Technology, SydneyLong XU, Shanghai Jiaotong UniversityPengfei SHI, Shanghai Jiaotong UniversityJie YANG, Shanghai Jiaotong University
ARS-P42.2 – A VIDEO SALIENCY DETECTION METHOD BASED ON SPATIAL AND MOTION INFORMATIONKang XUE, Samsung R&C Institute China-BeijingXiying WANG, Samsung R&C Institute China-Beijing
ARS-P42.3 – SALIENT OBJECT DETECTION USING NORMALIZED CUT AND GEODESICSKeren FU, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityChen GONG, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityIrene Yu-Hua GU, Chalmers University of TechnologyJie YANG, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityPengfei SHI, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University
ARS-P42.4 – VISUAL SALIENCY BY EXTENDED QUANTUM CUTSCaglar AYTEKIN, Tampere University of TechnologyEzgi Can OZAN, Tampere University of TechnologySerkan KIRANYAZ, Tampere University of TechnologyMoncef GABBOUJ, Tampere University of Technology
ARS-P42.5 – MULTI-SCALE SALIENCY OF 3D COLORED MESHESAnass NOURI, Université de CaenChristophe CHARRIER, Université de CaenOlivier LEZORAY, Université de Caen
«
52 | ICIP 2015 – Technical Program
ARS-P42.6 – SALIENT OBJECT DETECTION FROM DISTINCTIVE FEATURES IN LOW CONTRAST IMAGESXin XU, Wuhan University of Science and TechnologyNan MU, Wuhan University of Science and TechnologyHong ZHANG, Wuhan University of Science and TechnologyXiaowei FU, Wuhan University of Science and Technology
ARS-P43: Saliency III Monday, 10:30-12:30POSTER Room: POSTER FSession Chair(s): Patrick LE CALLET, Polytech Nantes – Université de Nantes
ARS-P43.1 – SALIENCY MAP BASED IMPROVED SEGMENTATIONPrerana MUKHERJEE, Indian Institute of Technology, Delhi, IndiaBrejesh LALL, Indian Institute of Technology, Delhi, IndiaArchit SHAH, Indian Institute of Technology, Delhi, India
ARS-P43.2 – A SALIENCY MODEL FOR AUTOMATED TUMOR DETECTION IN BREAST ULTRASOUND IMAGESHaoyang SHAO, Harbin Institute of TechnologyYingtao ZHANG, Harbin Institute of TechnologyMin XIAN, Utah State UniversityHengda CHENG, Utah State UniversityFei XU, Utah State University,Jianrui DING, Harbin Institute of Technology
ARS-P43.3 – SALIENT OBJECT CARVINGAvik HATI, Indian Institute of Technology BombaySubhasis CHAUDHURI, Indian Institute of Technology BombayRajbabu VELMURUGAN, Indian Institute of Technology Bombay
ARS-P43.4 – ONE GAZE IS WORTH TEN THOUSAND (KEY-)WORDSStephanie LOPEZ, University of Nice Sophia Antipolis (UNS)Arnaud REVEL, University of La RochelleDiane LINGRAND, University of Nice Sophia Antipolis (UNS)Frederic PRECIOSO, University of Nice Sophia Antipolis (UNS)
ARS-P43.5 – SALIENT OBJECT DETECTION VIA OBJECTNESS MEASURESai SRIVATSA R ., Indian Institute of Technology, KharagpurVenkatesh Babu RADHAKRISHNAN, Indian Institute of Science
ARS-P43.6 – SALIENCY CUTS BASED ON ADAPTIVE TRIPLE THRESHOLDINGShuzhen LI, Nanjing UniversityRan JU, Nanjing UniversityTongwei REN, Nanjing UniversityGangshan WU, Nanjing University
ICIP 2015 – Technical Program | 53
ARS-P5: Content Summarization and Understanding Monday, 10:30-12:30POSTER Room: POSTER CSession Chair(s): Amit ROY-CHOWDHURY, University of California, Riverside
ARS-P5.1 – A MULTI-VIEW VIDEO SYNOPSIS FRAMEWORKPankaj SA, NIT RourkelaAnsuman MAHAPATRA, NIT RourkelaBanshidhar MAJHI, NIT Rourkela
ARS-P5.2 – CASCADE OF CLASSIFIERS BASED ON BINARY, NON-BINARY AND DEEP CONVOLUTIONAL NETWORK DESCRIPTORS FOR VIDEO CONCEPT DETECTIONFoteini MARKATOPOULOU, Centre for Research and Technology HellasVasileios MEZARIS, Centre for Research and Technology HellasIoannis PATRAS, Queen Mary University of London
ARS-P5.3 – CO-REGULARIZED DEEP REPRESENTATIONS FOR VIDEO SUMMARIZATIONOlivier MORÈRE, Université Pierre et Marie CurieHanlin GOH, Institute for Infocomm ResearchAntoine VEILLARD, Université Pierre et Marie CurieVijay CHANDRASEKHAR, Institute for Infocomm ResearchJie LIN, Institute for Infocomm Research
ARS-P5.4 – FACIAL IMAGE ANALYSIS BASED ON TWO-DIMENSIONAL LINEAR DISCRIMINANT ANALYSIS EXPLOITING SYMMETRYKonstantinos PAPACHRISTOU, Aristotle University of ThessalonikiAnastasios TEFAS, Aristotle University of ThessalonikiIoannis PITAS, Aristotle University of Thessaloniki
ARS-P5.5 – VIDEO SUMMARIZATION THROUGH CHANGE DETECTION IN A NON-OVERLAPPING CAMERA NETWORKShu ZHANG, University of California, RiversideAmit ROY-CHOWDHURY, University of California, Riverside
COM-O1: High-efficiency Video Coding I Monday, 10:30-12:30LECTURE Room: 204ASession Chair(s): Onur GULERYUZ, LG Electronics
10:30 COM-O1.1 – HIGH THROUGHPUT PARALLEL SCHEME FOR HEVC DEBLOCKING FILTERAlaa ELDEKEN, Military Technical CollegeRichard DANSEREAU, Carleton UniversityMohamed FOUAD, Military Technical CollegeGouda SALAMA, Military Technical College
10:50 COM-O1.2 – FAST CU SIZE DECISION AND PU MODE DECISION ALGORITHM IN HEVC INTRA CODINGXiwu SHANG, School of Communication and Information Engineering, Shanghai UniversityGuozhong WANG, School of Communication and Information Engineering, Shanghai UniversityTao FAN, School of Communication and Information Engineering, Shanghai UniversityYan LI, School of Communication and Information Engineering, Shanghai University
54 | ICIP 2015 – Technical Program
11:10 COM-O1.3 – TEXTURE BASED SUB-PU MOTION INHERITANCE FOR DEPTH CODINGYing CHEN, Qualcomm Technologies Inc.Hongbin LIU, Qualcomm Technologies Inc.Xin ZHAO, Qualcomm Technologies Inc.
11:30 COM-O1.4 – PALETTE MODE - A NEW CODING TOOL IN SCREEN CONTENT CODING EXTENSIONS OF HEVCYu-Chen SUN, MediaTek Inc.Tzu-Der CHUANG, MediaTek Inc.Polin LAI, MediaTek USA Inc.Yi-Wen CHEN, MediaTek Inc.Shan LIU, MediaTek USA Inc.Yu-Wen HUANG, MediaTek Inc.Shawmin LEI, MediaTek Inc.
11:50 « COM-O1.5 – A NOVEL MOTION ESTIMATION ALGORITHM BASED ON QUADRATIC PREDICTIONLongfei GAO, Peking University Shenzhen Graduate SchoolShengfu DONG, Peking University Shenzhen Graduate SchoolWenmin WANG, Peking University Shenzhen Graduate SchoolRonggang WANG, Peking University Shenzhen Graduate SchoolWen GAO, Peking University Shenzhen Graduate School
12:10 COM-O1.6 – BLOCK STRUCTURE REUSE FOR MULTI-RATE HIGH EFFICIENCY VIDEO CODINGDamien SCHROEDER, Technische Universität MünchenPatrick REHM, Technische Universität MünchenEckehard STEINBACH, Technische Universität München
COM-P1: High-efficiency Video Coding II Monday, 10:30-12:30POSTER Room: POSTER OSession Chair(s): Edson Mintsu HUNG, Universidade de Brasília
COM-P1.1 – RATE DISTORTION ANALYSIS OF HIGH DYNAMIC RANGE VIDEO CODING TECHNIQUESJunaid MIR, University of SurreyAnil FERNANDO, University of SurreyDumidu S . TALAGALA, University of SurreyHemantha KODIKARA ARACHCHI, University of Surrey
COM-P1.2 – CONTEXT ADAPTIVE MODE SORTING FOR FAST HEVC MODE DECISIONSaverio G . BLASI, Queen Mary University of LondonEduardo PEIXOTO, Universidade de BrasiliaBruno MACCHIAVELLO, Universidade de BrasiliaEdson Mintsu HUNG, Universidade de BrasiliaIvan ZUPANCIC, Queen Mary University of LondonEbroul IZQUIERDO, Queen Mary University of London
«
ICIP 2015 – Technical Program | 55
COM-P1.3 – FAST INTER MODE DECISION FOR HEVC BASED ON TRANSPARENT COMPOSITE MODELNan HU, University of WaterlooEn-Hui YANG, University of Waterloo
COM-P1.4 – COPY MODE FOR STATIC SCREEN CONTENT CODING WITH HEVCThorsten LAUDE, Leibniz Universität HannoverJörn OSTERMANN, Leibniz Universität Hannover
ELI-O2: 3D Modeling and Reconstruction Monday, 10:30-12:30LECTURE Room: 205ASession Chair(s): Pascal VASSEUR, LITIS, University of Rouen
10:30 ELI-O2.1 – ENSEMBLE CLASSIFIER FOR JOINT OBJECT INSTANCE AND CATEGORY RECOGNITION ON RGBD DATAViktor SEIB, University of Koblenz-LandauRaphael MEMMESHEIMER, University of Koblenz-LandauDietrich PAULUS, University of Koblenz-Landau
10:50 ELI-O2.2 – DCSLAM: A REAL-TIME SLAM WITH DYNAMIC CONSTRAINTSDatta RAMADASAN, institut pascalMarc CHEVALDONNÉ, isitThierry CHATEAU, institut pascal
11:10 « ELI-O2.3 – MOTION ESTIMATION FOR NON-OVERLAPPING CAMERAS BY IMPROVEMENT OF FEATURE POINTS MATCHING BASED ON URBAN 3D STRUCTUREAtsushi KAWASAKI, Graduate School of Science and Technology Keio universityHideo SAITO, Graduate School of Science and Technology Keio universityKosuke HARA, Denso IT Laboratory
11:30 ELI-O2.4 – AUTOMATIC VIDEO TO POINT CLOUD REGISTRATION IN A STRUCTURE-FROM-MOTION FRAMEWORKEsteban VIDAL, Huawei Technologies Co. Ltd., European Research CenterNicola PIOTTO, Huawei Technologies Co. Ltd., European Research CenterGiovanni CORDARA, Huawei Technologies Co. Ltd., European Research CenterFrancisco MORAN BURGOS, Universidad Politecnica de Madrid
11:50 ELI-O2.5 – 3D TRAJECTORY RECONSTRUCTION UNDER REFRACTION AT A CYLINDRICAL SURFACEByung-Kuk SEO, Fraunhofer IGDJungsik PARK, Hanyang UniversityJong-il PARK, Hanyang University
12:10 ELI-O2.6 – ACCURATE SCALE ESTIMATION BASED ON UNSYNCHRONIZED CAMERA NETWORKRawia MHIRI, LITIS insa de rouen université de rouenPascal VASSEUR, LITIS université de rouenStéphane MOUSSET, LITIS insa de rouenRémi BOUTTEAU, IRSEEMAbdelaziz BENSRHAIR, LITIS insa de rouen
56 | ICIP 2015 – Technical Program
ELI-P3: Color Imaging I Monday, 10:30-12:30POSTER Room: POSTER MSession Chair(s): Jiying ZHAO, University of Ottawa
ELI-P3.1 – A CLUSTERING CLASSIFICATION FRAMEWORK FOR COLOUR CONSTANCYBozhi LIU, the University of NottinghamGuoping QIU, the University of Nottingham
ELI-P3.2 – COMPENSATION OF SPECTRAL MISMATCH TO ENHANCE WRGB DEMOSAICKINGPo-Hsun SU, National Taiwan UniversityPo-Chang CHEN, Himax Imaging IncHomer CHEN, National Taiwan University
ELI-P3.3 – REFLECTANCE ESTIMATION AND WHITE BALANCING USING MULTIPLE IMAGESRyo MATSUOKA, The university of kitakyushuTatsuya BABA, The university of kitakyushuMasahiro OKUDA, The university of kitakyushu
ELI-P3.4 – SIMPLE EFFECTIVE IMAGE AND VIDEO COLOR CORRECTION USING QUATERNION DISTANCE METRICSoo-Chang PEI, Graduate Institute of Communication Engineering, National Taiwan UniversityYu Zhe HSIAO, Graduate Institute of Communication Engineering, National Taiwan University
ELI-P3.5 – ADAPTIVE RESIDUAL INTERPOLATION FOR COLOR IMAGE DEMOSAICKINGYusuke MONNO, Tokyo Institute of TechnologyDaisuke KIKU, Tokyo Institute of TechnologyMasayuki TANAKA, Tokyo Institute of TechnologyMasatoshi OKUTOMI, Tokyo Institute of Technology
ELI-P12: Color Imaging II Monday, 10:30-12:30POSTER Room: POSTER NSession Chair(s): Jiying ZHAO, University of Ottawa
ELI-P12.1 – OPTIMIZATION OF COLOR QUANTIZATION WITH TOTAL LUMINANCE FOR DLP PROJECTOR AND ITS EVALUATION SYSTEMGou KOUTAKI, Kumamoto UniversityHiroshi OKAJIMA, Kumamoto UniversityNobutomo MATSUNAGA, Kumamoto UniversityKeiichi UCHIMURA, Kumamoto University
ELI-P12.2 – EFFICIENT NATURAL COLOR IMAGE DENOISING BASED ON GUIDED FILTERChia-Liang TSAI, National Taiwan UniversityWei-Chih TU, National Taiwan UniversityShao Yi CHIEN, National Taiwan University
ELI-P12.3 – INVERSE HALFTONING WITH GROUPING SINGULAR VALUE DECOMPOSITIONJun YANG, Sun Yat-sen UniversityJun GUO, Sun Yat-sen UniversityHongyang CHAO, Sun Yat-sen University
«
ICIP 2015 – Technical Program | 57
ELI-P12.4 – ONE-FRAME DELAY FOR DYNAMIC PHOTOMETRIC COMPENSATION IN A PROJECTOR-CAMERA SYSTEMPanagiotis-Alexandros BOKARIS, LIMSI-CNRS, University of Paris-SudMichèle GOUIFFÈS, LIMSI-CNRS, University of Paris-SudChristian JACQUEMIN, LIMSI-CNRS, University of Paris-SudJean-Marc CHOMAZ, LadHyX, CNRS, École Polytechnique Alain TRÉMEAU, Laboratoire Hubert Curien, CNRS, Université Jean Monnet
ELI-P12.5 – GRADIENT PRESERVING RGB-TO-GRAY CONVERSION USING RANDOM FORESTByeongju LEE, Seoul National UniversityJongwon CHOI, Seoul National UniversityKimin YUN, Seoul National UniversityJin Young CHOI, Seoul National University
ELI-P12.6 – HYBRID KEY: AN AUTOMATIC TOOL FOR REAL-TIME HIGH QUALITY CHROMA KEYINGLing YIN, University of Ottawa, CanadaJiying ZHAO, University of Ottawa, Canada
NEW-O2: Image and Graphs Monday, 10:30-12:30LECTURE Room: 204BSession Chair(s): Gene CHEUNG, National Institute of Informatics
10:30 NEW-O2.1 – DELAUNAY-SUPPORTED EDGES FOR IMAGE GRAPHSNicholas DAHM, Griffith UniversityYongsheng GAO, Griffith UniversityTerry CAELLI, University of MelbourneHorst BUNKE, University of Bern
10:50 « NEW-O2.2 – SPARSE CONCEPT DISCRIMINANT MATRIX FACTORIZATION FOR IMAGE REPRESENTATIONMeng PANG, Dalian University of TechnologyChuang LIN, Dalian University of TechnologyRisheng LIU, Dalian University of TechnologyXin FAN, Dalian University of TechnologyJifeng JIANG, Dalian University of Technology
11:10 NEW-O2.3 – INTER-BLOCK CONSISTENT SOFT DECODING OF JPEG IMAGES WITH SPARSITY AND GRAPH-SIGNAL SMOOTHNESS PRIORSXianming LIU, Harbin Institute of TechnologyGene CHEUNG, National Institute of InformaticsXiaolin WU, McMaster UniversityDebin ZHAO, Harbin Institute of Technology
11:30 NEW-O2.4 – BAG-OF-WORD BASED BRAND RECOGNITION USING MARKOV CLUSTERING ALGORITHM FOR CODEBOOK GENERATIONYannick BENEZETH, Université de BourgogneAurélie BERTAUX, Université de BourgogneAldric MANCEAU, Université de Bourgogne
«
58 | ICIP 2015 – Technical Program
11:50 NEW-O2.5 – ORTHO-DIFFUSION DECOMPOSITIONS FOR FACE RECOGNITION FROM LOW QUALITY IMAGESSravan GUDIVADA, University of YorkAdrian BORS, University of York
SMR-O1: Bio-inspired Modeling Monday, 10:30-12:30LECTURE Room: 203Session Chair(s): Peter TAY, Western Carolina University
10:30 SMR-O1.1 – BIOLOGICALLY MOTIVATED SQUARE SPIRAL ARCHITECTURE FOR FAST VIDEO PROCESSINGMin JING, University of UlsterSonya COLEMAN, University of UlsterBryan SCOTNEY, University of UlsterMartin MCGINNITY, Nottingham Trent University
10:50 SMR-O1.2 – A VISUAL COMFORT ASSESSMENT METRIC FOR STEREOSCOPIC IMAGESFeng QI, Harbin Institute of TechnologyXiaopeng FAN, Harbin Institute of TechnologyTingting JIANG, Peking UniversityJian ZHANG, Peking UniversityDebin ZHAO, Harbin Institute of Technology
11:10 SMR-O1.3 – A SIMPLE MODEL FOR ASSESSING THE ROLE OF CAMERA FRAME RATE IN MEASURING EYE MOVEMENTMehrdad SANGI, University of AucklandBenjamin THOMPSON, University of AucklandCindy Xiaopeng GUO, University of AucklandJason TURUWHENUA, University of Auckland
11:30 SMR-O1.4 – KNOWLEDGE AS ACTION: A COGNITIVE FRAMEWORK FOR INDOOR SCENE CLASSIFICATIONRui WU, Harbin Institute of TechnologyZhipeng YE, Harbin Institute of TechnologyPeng LIU, Harbin Institute of TechnologyXianglong TANG, Harbin Institute of TechnologyWei ZHAO, Harbin Institute of Technology
11:50 SMR-O1.5 – BIOLOGICALLY INSPIRED DEEP STEREO MODELQingqun KONG, Institute of Automation, Chinese Academy of SciencesYi ZENG, Institute of Automation,Chinese Academy of SciencesQiulei DONG, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
12:10 SMR-O1.6 – A CONJOINTLY WELL LOCALIZED QUADRATURE MIRROR FILTERBANKPeter TAY, Western Carolina University
ICIP 2015 – Technical Program | 59
SMR-P1: Image Analysis and Synthesis Monday, 10:30-12:30POSTER Room: POSTER JSession Chair(s): Hong MAN, Stevens Institute of Technology
SMR-P1.1 – LPI ADAPTIVE DESCREENING METHOD WITH HADAMARD DOMAIN ANAYSISHyun-Seung LEE, Samsung ElectronicsJi-Young LEE, Samsung ElectronicsCho NAM IK, Seoul National University
SMR-P1.2 – A ROBUST NONSYMMETRIC STUDENTS-T FINITE MIXTURE MODEL FORMR IMAGE SEGMENTATIONXu PAN, School of Information Science & Engineering, East China University of Science and TechnologyHongqing ZHU, School of Information Science & Engineering, East China University of Science and TechnologyQunyi XIE, School of Information Science & Engineering, East China University of Science and Technology
SMR-P1.3 – A MAP ESTIMATION FRAMEWORK FOR HDR VIDEO SYNTHESISYuelong LI, Pennsylvania State UniversityChul LEE, The University of Hong KongVishal MONGA, Pennsylvania State University
SMR-P1.4 – LOCALITY SENSITIVE DICTIONARY LEARNING FOR IMAGE CLASSIFICATIONBaodi LIU, China University of PetroleumBin SHEN, Purdue UniversityXue LI, Tsinghua University
SMR-P1.5 – INTERPRETING SPORTS TACTIC BASED ON LATENT CONTEXT-FREE GRAMMARXingzhong XU, Stevens Institute of TechnologyHong MAN, Stevens Institute of Technology
SMR-P1.6 – NOTES ON IMAGE PROCESSING WITH PARTIAL DIFFERENTIAL EQUATIONSBehzad KAMGAR-PARSI, Office of Naval ResearchBehrooz KAMGAR-PARSI, Naval Research LaboratoryKian KAMGAR-PARSI, University of Michigan
SMR-P6: Imaging Systems Monday, 10:30-12:30POSTER Room: POSTER KSession Chair(s): Sanghoon LEE, Yonsei University
SMR-P6.1 – PARAMETER OPTIMISATION FOR VISION GUIDED TERRESTRIAL LOCOMOTION: MULTI-FRAMEGeoffrey DANIELS, University of BristolDavid BULL, University of BristolJeremy BURN, University of Bristol
SMR-P6.2 – USING THE UNITY® GAME ENGINE AS A PLATFORM FOR ADVANCED REAL TIME CINEMA IMAGE PROCESSINGTimothée DE GOUSSENCOURT, SolidanimPascal BERTOLINO, University Grenoble-Alpes
60 | ICIP 2015 – Technical Program
SMR-P6.3 – COMPUTATIONAL 3D RECONSTRUCTION OF FAR AND BIG SIZE OBJECTS USING SYNTHETIC APETURE INTEGRAL IMAGINGLuyan XING, Dalian University of TechnologyYongri PIAO, Dalian University of TechnologyHongjia QU, Dalian University of TechnologyMiao ZHANG, Dalian University of Technology
SMR-P6.4 – ROBUST LASER STRIPE EXTRACTION USING RIDGE SEGMENTATION AND REGION RANKING FOR 3D RECONSTRUCTION OF REFLECTIVE AND UNEVEN SURFACEJia DU, Institute for Infocomm ResearchWei XIONG, Institute for Infocomm ResearchWenyu CHEN, Institute for Infocomm ResearchJierong CHENG, Institute for Infocomm ResearchYue WANG, Institute for Infocomm ResearchYing GU, Institute for Infocomm ResearchShue Ching CHIA, Institute for Infocomm Research
SMR-P9: Texture Estimation and Classification Monday, 10:30-12:30POSTER Room: POSTER LSession Chair(s): Jana EHMANN, LG Electronics
SMR-P9.1 – DYNAMIC TEXTURES CLUSTERING USING A HIERARCHICAL PITMAN-YOR PROCESS MIXTURE OF DIRICHLET DISTRIBUTIONSWentao FAN, Huaqiao UniversityNizar BOUGUILA, Concordia University
SMR-P9.2 – DENOISING OF NATURAL STOCHASTIC COLORED-TEXTURES BASED ON FRACTIONAL BROWNIAN MOTION MODELIdo ZACHEVSKY, Technion - Israel Institute of TechnologyYehoshua Y . ZEEVI, Technion - Israel Institute of Technology
SMR-P9.3 – ARFBF MODEL FOR NON STATIONARY RANDOM FIELDS AND APPLICATION IN HRTEM IMAGES Zhangyun TAN, LISTIC, University Savoy Mont BlancAbdourrahmane ATTO, LISTIC, University Savoy Mont BlancOlivier ALATA, Lab. Hubert Curien, Jean Monnet University of Saint-Étienne Maxime MOREAUD, IFP Energies Nouvelles
SMR-P9.4 – QUEST THE POTENTIAL OF SPATIAL TEXTURE FEATURES FOR DYNAMIC TEXTURE RECOGNITIONFeng YANG, Wuhan UniversityGui-Song XIA, Wuhan UniversityLiangpei ZHANG, Wuhan UniversityXin HUANG, Wuhan University
ICIP 2015 – Technical Program | 61
SMR-P9.5 – TEXTURE CLASSIFICATION USING UNIFORM ROTATION INVARIANT GRADIENTWenteng ZHAO, Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua UniversityZongqing LU, Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua UniversityQingmin LIAO, Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua University
SMR-P9.6 – MULTIVARIATE OPTIMIZATION FOR MULTIFRACTAL-BASED TEXTURE SEGMENTATIONJordan FRECON, Laboratoire de Physique de l’École Normale Supérieure de LyonNelly PUSTELNIK, Laboratoire de Physique de l’École Normale Supérieure de LyonHerwig WENDT, IRITPatrice ABRY, Laboratoire de Physique de l’École Normale Supérieure de Lyon
SNT-S1: Show & Tell I Monday, 10:30-12:30SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S1.1 – USING GOOGLE GLASS TO ASSIST INDIVIDUALS WITH AUTISM IN JOB INTERVIEWSSen-Ching Samson CHEUNG, University of KentuckyNeelkamal SOARES, Geisinger Health SystemThe proposed demonstration is an application on Google Glass platform called LittleHelper to assist individuals with ASD in maintaining appropriate eye contact and speech volume during a social communication between two individuals, typical in a job interview .
SNT-S1.2 – ANTI-COLLUSION VIDEO WATERMARKING WITH REAL-TIME FALSE ALARM PROBABILITIES .Gaetan LE GUELVOUIT, B-Com, Digital Trust & Identity LabsValérie DENIS, B-COMTeddy FURON, B-Com, INRIAForensic watermarking aims at embedding a unique identifier within each copy a video . Its typical use case is the fight against piracy, helping the identification of indelicate customers or traitors in the video processing chain . In this context, we plan to demonstrate our video forensic solution, named Ultra Marker . It provides an ultra-robust video watermarking algorithm and an anti-collusion codes generator and detector . The watermarking part of the solution has been designed to optimize the trade-off between robustness, visual transparency and security
SNT-S1.3 – INTERACTIVE MAX-TREE VISUALIZATION TOOL FOR IMAGE PROCESSING AND ANALYSISLuis TAVARES, University of CampinasRoberto SOUZA, University of CampinasLetícia RITTNER, University of CampinasRubens MACHADO, CTI, CampinasRoberto LOTUFO, University of CampinasThe max-tree is a data structure that represents all possible upper thresholds of an image . We propose a methodology that allows building an interactive max-tree graphical representation that permits the user to navigate through the max-tree nodes, to visualize its connected components and to create node subsets .
«
62 | ICIP 2015 – Technical Program
SS3-O1: Color Imaging and Applications Monday, 10:30-12:30LECTURE Room: 205BSession Chair(s): Christophe CHARRIER, University of Caen Basse Normandie Christine FERNANDEZ-MALOIGNE, University of Poitiers Marius PEDERSEN, Gjøvik University College
10:30 SS3-O1.1 – TEXTURE CLASSIFICATION WITH FUZZY COLOR CO-OCCURRENCE MATRICESAudrey LEDOUX, Laboratoire CRIStAL (UMR CNRS 9189), Université de LilleOlivier LOSSON, Laboratoire CRIStAL (UMR CNRS 9189), Université de LilleLudovic MACAIRE, Laboratoire CRIStAL (UMR CNRS 9189), Université de Lille
10:50 SS3-O1.2 – EVALUATION OF 60 FULL-REFERENCE IMAGE QUALITY METRICS ON THE CID:IQMarius PEDERSEN, Gjøvik University College
11:10 SS3-O1.3 – COLOR DECORRELATION HELPS VISUAL SALIENCY DETECTIONBoris SCHAUERTE, Karlsruhe Instiute of Technology / EyezagTorsten WÖRTWEIN, Karlsruhe Instiute of TechnologyRainer STIEFELHAGEN, Karlsruhe Instiute of Technology
11:30 SS3-O1.4 – ELLIPTICAL MONOGENIC REPRESENTATION OF COLOR IMAGES AND LOCAL FREQUENCY ANALYSISRaphael SOULARD, University of PoitiersPhilippe CARRÉ, University of Poitiers
11:50 «SS3-O1.5 – MULTIVALUED LABEL DIFFUSION FOR SEMI-SUPERVISED SEGMENTATIONPierre BUYSSENS, GreycOlivier LEZORAY, Greyc
12:10 SS3-O1.6 – SCENE STATISTICS OF AUTHENTICALLY DISTORTED IMAGES IN PERCEPTUALLYRELEVANT COLOR SPACES FOR BLIND IMAGE QUALITY ASSESSMENTDeepti GHADIYARAM, The University of Texas at AustinAlan BOVIK, The University of Texas at Austin
TEC-O4: Image Reconstruction Monday, 10:30-12:30LECTURE Room: 205CSession Chair(s): Marcelo V . W . ZIBETTI, Universidade Tecnológica Federal do Paraná
10:30 TEC-O4.1 – DESIRE: DISCONTINUOUS ENERGY SEAM CARVING FOR IMAGE RETARGETING VIA STRUCTURAL AND TEXTURAL ENERGY FUNCTIONALSAkshaya MISHRA, University of WaterlooChristian SCHARFENBERGER, University of WaterlooParthipan SIVA, University of WaterlooFan LI, University of WaterlooAlexander WONG, University of WaterlooDavid CLAUSI, University of Waterloo
ICIP 2015 – Technical Program | 63
10:50 TEC-O4.2 – ROTATIONALLY-INVARIANT NON-LOCAL MEANS FOR IMAGE DENOISING AND TOMOGRAPHYSuhas SREEHARI, Purdue UniversityS . V . VENKATAKRISHNAN, Lawrence Berkeley National LaboratoryLawrence DRUMMY, Air Force Research LaboratoryJeffrey SIMMONS, Air Force Research LaboratoryCharles BOUMAN, Purdue University
11:10 TEC-O4.3 – NEURAL NETWORK BASED X-RAY TOMOGRAPHY FOR FAST INSPECTION OF APPLES ON A CONVEYOR BELT SYSTEMEline JANSSENS, University of AntwerpJan DE BEENHOUWER, University of AntwerpMattias VAN DAEL, KULeuvenPieter VERBOVEN, KU LeuvenBart NICOLAI, KU LeuvenJan SIJBERS, University of Antwerp
11:30 TEC-O4.4 – DISTRIBUTED COMPRESSED SENSING FOR PHOTO-ACOUSTIC IMAGINGK J FRANCIS, Indian Institute of Technology HyderabadSumohana CHANNAPPAYYA, Indian Institute of Technology HyderabadP RAJALAKSHMI, Indian Institute of Technology Hyderabad
11:50 TEC-O4.5 – PARTIALLY DISCRETE MAGNETIC RESONANCE TOMOGRAPHYGabriel RAMOS-LLORDÉN, iMinds-Vision Lab, University of AntwerpHilde SEGERS, iMinds-Vision Lab, University of AntwerpWillem JAN PALENSTIJN, iMinds-Vision Lab, University of AntwerpArnold Jan DENDEKKER, iMinds-Vision Lab, University of AntwerpJan SIJBERS, iMinds-Vision Lab, University of Antwerp
12:10 «TEC-O4.6 – ACCELERATING THE OVER-RELAXED ITERATIVE SHRINKAGE-THRESHOLDING ALGORITHMS WITH FAST AND EXACT LINE SEARCH FOR HIGH RESOLUTION TOMOGRAPHIC IMAGE RECONSTRUCTIONMarcelo V . W . ZIBETTI, UTFPRElias HELOU, USPEduardo MIQUELES, LNLSAlvaro DE PIERRO, CNPq
TEC-P26: Tomography Monday, 10:30-12:30POSTER Room: POSTER HSession Chair(s): Rabab WARD, University of British Columbia
TEC-P26.1 – FACTOR GRAPHS FOR INVERSE PROBLEMS: ACCELERATED PHASE CONTRAST MAGNETIC RESONANCE IMAGINGAdam RICH, The Ohio State UniversityLee POTTER, The Ohio State UniversityJoshua ASH, The Ohio State UniversityRizwan AHMAD, The Ohio State University
«
64 | ICIP 2015 – Technical Program
TEC-P26.2 – MR IMAGE RECONSTRUCTION OF A REGULARLY UNDERSAMPLED SIGNAL USING QUADRATIC PHASE SCRAMBLINGSatoshi ITO, Utsunomiya UniversityShungo YASAKA, Utsunomiya UniversityYoshifumi YAMADA, Utsunomiya University
TEC-P26.3 – ANGULAR UPSAMPLING OF PROJECTION MEASUREMENTS IN 3D COMPUTED TOMOGRAPHY USING A SPARSITY PRIORDavood KARIMI, University of British Columbia Rabab WARD, University of British Columbia Nancy FORD, University of British Columbia
TEC-P26.4 – TOMOGRAPHIC IMAGE RECONSTRUCTION WITH A SPATIALLY VARYING GAUSSIAN MIXTURE PRIORKaterina PAPADIMITRIOU, University of IoanninaChristophoros NIKOU, University of Ioannina
TEC-P26.5 – LEARNING SPACE-TIME DICTIONARIES FOR BLIND COMPRESSED SENSING DYNAMIC MRI RECONSTRUCTIONAngshul MAJUMDAR, IIITDRabab WARD, UBC
TEC-P33: Motion Estimation, Restoration and Superresolution Monday, 10:30-12:30POSTER Room: POSTER GSession Chair(s): Majid RABBANI, Eastman Kodak
TEC-P33.1 – ON SPATIAL NEIGHBOURHOOD OF PATCH-BASED SUPER RESOLUTIONNeeraj KUMAR, Indian Institute of Technology GuwahatiAmit SETHI, Indian Institute of Technology Guwahati
TEC-P33.2 – COLOR DEFLICKERING FOR HIGH-SPEED VIDEO IN THE PRESENCE OF ARTIFICIALLIGHTINGAli KANJ, Université Paris-Est, Laboratoire d’informatique Gaspard MongeHugues TALBOT, Université Paris-Est, Laboratoire d’informatique Gaspard MongeJean-Christophe PESQUET, Université Paris-Est, Laboratoire d’informatique Gaspard MongeRaoul RODRIGUEZ LUPARELLO, Sublab Production
TEC-P33.3 – ILLUMINATION ROBUST OPTICAL FLOW ESTIMATION BY ILLUMINATION-CHROMATICITY DECOUPLINGSungheon PARK, Seoul National UniversityNojun KWAK, Seoul National University
TEC-P33.4 – KERNEL-BASED FACE HALLUCINATION VIA DUAL REGULARIZATION PRIORSJingang SHI, Xi’an Jiaotong UniversityChun QI, Xi’an Jiaotong University
TEC-P33.5 – FIREFLY: A HARDWARE-FRIENDLY REAL-TIME LOCAL BRIGHTNESS ADJUSTMENT METHODNikola BANIC, University of Zagreb Faculty of Electrical Engineering and ComputingSven LONCARIC, University of Zagreb Faculty of Electrical Engineering and Computing
«
«
ICIP 2015 – Technical Program | 65
TEC-P33.6 – DENOISING-BASED IMAGE RECONSTRUCTION FROM PIXELS LOCATED AT NON-INTEGER POSITIONSJan KOLODA, Friedrich-Alexander University (FAU)Jürgen SEILER, Friedrich-Alexander University (FAU)André KAUP, Friedrich-Alexander University (FAU)
MATL-W: Industry Workshop: Matlab Today Monday, 12:30-14:00WORKSHOP Room: 206ASession Chair(s): André MORIN, Optelis Jean-Luc DUGELAY, Eurecom
SummaryMATLAB® has been on a fast track recently, delivering many significant improvements that will affect all aspects of your technical computing work. Come hear the latest from a MathWorks engineer with more than 20 years of experience developing MATLAB and Image Processing Toolbox™. Learn more about: • The new graphics system – an updated look and easier interaction• The new default MATLAB color map – why we changed it and how we designed it• New math, image processing, and computer vision algorithms – for your prototyping and
research• New software developer tools – for managing your code• Improved performance – for tackling bigger problems faster
PresenterSteve Eddins, Senior MATLAB Designer for Language Evolution, MathWorks
WISP-L: Women in Signal Processing Lunch Monday, 12:30-14:00LUNCH Room: 206BSession Chair(s): Rabab WARD, Signal Processing Society
ARS-O1: Classification I Monday, 14:00-16:00LECTURE Room: 204ASession Chair(s): B .S . MANJUNATH, University of California at Santa Barbara
14:00 ARS-O1.1 – STATISTICAL HYPOTHESIS TEST FOR ROBUST CLASSIFICATION ON THE SPACE OF COVARIANCE MATRICESIoana ILEA, Université de Bordeaux, Laboratoire IMS, Groupe Signal et Image; Technical University of Cluj-NaLionel BOMBRUN, Université de Bordeaux, Laboratoire IMS, Groupe Signal et ImageChristian GERMAIN, Université de Bordeaux, Laboratoire IMS, Groupe Signal et ImageRomulus TEREBES, Technical University of Cluj-NapocaMonica BORDA, Technical University of Cluj-Napoca
66 | ICIP 2015 – Technical Program
14:20 ARS-O1.2 – MULTIPLE FEATURES EXTRACTION FOR TIMBER DEFECTS DETECTION AND CLASSIFICATION USING SVMMohamad Mazen HITTAWE, Le2iSatya MUDDAMSETTY, Le2iDesire SIDIBE, University of Burgundy,LE2IFabrice MERIAUDEAU, University of Burgundy,LE2I
14:40 «ARS-O1.3 – LOCAL FEATURE EMBEDDING FOR WEAKLY SUPERVISED IMAGE CLASSIFICATIONJunxia LI, Nanjing University of Science and Technology; Nanyang Technological UniversityDeepu RAJAN, Nanyang Technological UniversityJian YANG, Nanjing University of Science and Technology
15:00 ARS-O1.4 – PHOTOGRAPHIC PAPER CLASSIFICATION VIA LOCAL RADIUS INDEX METRICYuanhao ZHAI, University of MichiganDavid NEUHOFF, University of Michigan
15:20 ARS-O1.5 – DPM REVISITED: UTILIZING ROOT-PART SPATIAL DISTRIBUTION FOR VEHICLEVIEWPOINT ESTIMATIONTao CHEN, Institute for Infocomm Research, Agency for Science, Technology and ResearchShijian LU, Institute for Infocomm Research, Agency for Science, Technology and Research
15:40 ARS-O1.6 – FEATURES WE TRUST!Amir M . RAHIMI, University of California at Santa BarbaraLakshmanan NATARAJ, University of California at Santa BarbaraB .S . MANJUNATH, University of California at Santa Barbara
ARS-O14: Object Detection and Tracking I Monday, 14:00-16:00LECTURE Room: 204BSession Chair(s): Maria Aishy AMER, Concordia University
14:00 ARS-O14.1 – ONLINE LEARNING OF MULTI-FEATURE WEIGHTS FOR ROBUST OBJECT TRACKINGTao ZHOU, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityHarish BHASKAR, Dept. of Elec. & Comp. Engg., Khalifa Univ. of Science Technology and ResearcKai XIE, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityJie YANG, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityXiangjian HE, Faculty of Engineering and Information Technology, University of TechnologyPengfei SHI, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University
ICIP 2015 – Technical Program | 67
14:20 ARS-O14.2 – OBJECT TRACKING WITH ADAPTIVE MOTION MODELING OF PARTICLE FILTER AND SUPPORT VECTOR MACHINESKumara RATNAYAKE, Concordia UniversityMaria Aishy AMER, Concordia University
14:40 ARS-O14.3 – DETECTING REPETITIVE ELEMENTS WITH ACCURATE LOCATIONS AND SHAPES FROM URBAN FAÇADEYongjian LIAN, State Key Laboratory of Virtual Reality Technology and Systems, Beihang UniversityXukun SHEN, State Key Laboratory of Virtual Reality Technology and Systems, Beihang University
15:00 ARS-O14.4 – REPRODUCIBLE EVALUATION OF PAN-TILT-ZOOM TRACKINGGengjie CHEN, Sun Yat-sen UniversityPierre-Luc ST-CHARLES, École Polytechnique de MontréalWassim BOUACHIR, École Polytechnique de MontréalGuillaume-Alexandre BILODEAU, École polytechnique de MontréalRobert BERGEVIN, Université Laval
15:20 ARS-O14.5 – REGULARIZATION IN METRIC LEARNING FOR PERSON RE-IDENTIFICATIONJianlou SI, Beijing University of Posts and TelecommunicationsHonggang ZHANG, Beijing University of Posts and TelecommunicationsChun-Guang LI, Beijing University of Posts and Telecommunications
15:40 ARS-O14.6 – A HIERARCHICAL ANTI-OCCLUSION TRACKING ALGORITHM BASED ON DMPF AND ORBKejia LIU, University of Science and Technology of ChinaBin LIU, University of Science and Technology of ChinaChang CHEN, University of Science and Technology of ChinaChang Wen CHEN, University at Buffalo, the State University of New York
ARS-O16: Pose and Gesture Recognition Monday, 14:00-16:00LECTURE Room: 203Session Chair(s): José ORAMAS M ., KU Leuven
14:00 ARS-O16.1 – SEQUENTIAL NON-RIGID POINT REGISTRATION FOR 3D HUMAN POSE TRACKINGSong GE, Oklahoma State UniversityGuoliang FAN, Oklahoma State University
14:20 ARS-O16.2 – RECOGNIZING HAND-OBJECT INTERACTIONS IN WEARABLE CAMERA VIDEOSTatsuya ISHIHARA, IBM Research - TokyoKris KITANI, Carnegie Mellon UniversityWei-Chiu MA, Carnegie Mellon UniversityHironobu TAKAGI, IBM Research - TokyoChieko ASAKAWA, IBM Research - Tokyo
14:40 ARS-O16.3 – GESTURE RECOGNITION USING ACTIVE BODY PARTS AND ACTIVE DIFFERENCE SIGNATURESHimanshu KUMAR, Rochester Institute of TechnologyRaymond PTUCHA, Rochester Institute of Technology
68 | ICIP 2015 – Technical Program
15:00 ARS-O16.4 – ESTIMATION OF EYE GAZE DIRECTION ANGLES BASED ON ACTIVE APPEARANCE MODELSPetros KOUTRAS, National Technical University of AthensPetros MARAGOS, National Technical University of Athens
15:20 ARS-O16.5 – TOWARDS SIGN LANGUAGE RECOGNITION BASED ON BODY PARTS RELATIONSMarc MARTINEZ-CAMARENA, Universidad Politécnica de ValenciaJosé ORAMAS, KU LeuvenTinne TUYTELAARS, KU Leuven
15:40 «ARS-O16.6 – HEAD POSE ESTIMATION VIA PROBABILISTIC HIGH-DIMENSIONAL REGRESSIONVincent DROUARD, Inria Grenoble Rhône-AlpesSilèye BA, Inria Grenoble Rhône-AlpesGeorgios EVANGELIDIS, Inria Grenoble Rhône-AlpesAntoine DELEFORGE, Friedrich-Alexander-Universität Erlangen-NürnbergRadu HORAUD, Inria Grenoble Rhône-Alpes
ARS-P10: Facial Features/Gender/Age Recognition Monday, 14:00-16:00POSTER Room: POSTER DSession Chair(s): Hairong QI, University of Tennessee
ARS-P10.1 – ROBUST FACIAL LANDMARK LOCALIZATION USING MULTI PARTIAL FEATURESYanchao DONG, Tongji UnviersityYanming WANG, Tongji UnviersityJiguang YUE, Tongji UnviersityZhencheng HU, Kumamoto University
ARS-P10.2 – INVESTIGATING THE FEASIBILITY OF IMAGE-BASED NOSE BIOMETRICSNiv ZEHNGUT, Carnegie Mellon UniversityFelix JUEFEI-XU, Carnegie Mellon UniversityRishabh BARDIA, Carnegie Mellon UniversityDipan PAL, Carnegie Mellon UniversityChandrasekhar BHAGAVATULA, Carnegie Mellon UniversityMarios SAVVIDES, Carnegie Mellon University
ARS-P10.3 – SUPERVISED FRACTIONAL EIGENFACESTiago DE CARVALHO, Universidade Federal de Pernambuco (UFPE)Adriano COSTA, Universidade Federal Rural de Pernambuco (UFRPE)Maria SIBALDO, Universidade Federal de Pernambuco (UFPE)Ing Ren TSANG, Universidade Federal de Pernambuco (UFPE)George CAVALCANTI, Universidade Federal de Pernambuco (UFPE)
ARS-P10.4 – FACIAL FEATURE PARSING AND LANDMARK DETECTION VIA LOW-RANK MATRIX DECOMPOSITIONRui GUO, University of TennesseeHairong QI, University of Tennessee
«
ICIP 2015 – Technical Program | 69
ARS-P10.5 – PRECISE EYE LOCALIZATION WITH IMPROVED SDMMingcai ZHOU, Samsung Research Center-Beijing, SAIT China LabJingu HEO, Samsung Electronics, SAIT, Multimedia Processing LabXiying WANG, Samsung Research Center-Beijing, SAIT China LabDongkyung NAM, Samsung Electronics, SAIT, Multimedia Processing LabHaitao WANG, Samsung Research Center-Beijing, SAIT China Lab
ARS-P10.6 – AN ADAPTIVE MOTION MODEL FOR PERSON TRACKING WITH INSTANTANEOUS HEAD-POSE FEATURESRolf Hugh BAXTER, Heriot-Watt UniversityMichael LEACH, Chemring Technology SolutionsSankha Subhra MUKHERJEE, Heriot-Watt UniversityNeil ROBERTSON, Heriot-Watt University
ARS-P11: Feature Detection and Tracking Monday, 14:00-16:00POSTER Room: POSTER BSession Chair(s): Sébastien ROY, Université de Montréal
ARS-P11.1 – OCCLUSION HANDLING IN FEATURE POINT TRACKING USING RANKED PARTS BASED MODELSKaran RAMPAL, NEC CorporationKazuyuki SAKURAI, NEC CorporationHitoshi IMAOKA, NEC Corporation
ARS-P11.2 – REGRESSION BASED LANDMARK ESTIMATION AND MULTI-FEATURE FUSION FOR VISUAL SPEECH RECOGNITIONXuewu ZHANG, Shenzhen Graduate School, Peking UniversityHong LIU, Shenzhen Graduate School, Peking UniversityPingping WU, Shenzhen Graduate School, Peking University
ARS-P11.3 – BIT: BIO-INSPIRED TRACKERBolun CAI, South China University of TechnologyXiangmin XU, South China University of TechnologyXiaofen XING, South China University of TechnologyChunmei QING, South China University of Technology
ARS-P11.4 – REAL-TIME SOFTWARE SYNCHRONISATION OF WEBCAMS FOR LIVE 3D TRACKINGRania BENRHAIEM, Université de MontréalSébastien ROY, Université de MontréalJean MEUNIER, Université de Montréal
ARS-P11.5 – BACKGROUND-FOREGROUND TRACKING FOR VIDEO OBJECT SEGMENTATIONJuan Manuel PÉREZ RUA, TechnicolorTomas CRIVELLI, TechnicolorPatrick PÉREZ, Technicolor
«
70 | ICIP 2015 – Technical Program
ARS-P15: Image and Scene Analysis Monday, 14:00-16:00POSTER Room: POSTER ASession Chair(s): Haoyu REN, Simon Fraser University
ARS-P15.1 – SUPERPIXEL-BASED STATISTICAL ANOMALY DETECTION FOR SENSE AND AVOIDOdysseas PAPPAS, University of BristolAlin ACHIM, University of BristolDavid BULL, University of Bristol
ARS-P15.2 – OBJECT RECOGNITION BASED ON DEFORMABLE EDGE SETHaoyu REN, Simon Fraser UniversityZe-Nian LI, Simon Fraser University
ARS-P15.3 – CHORD: CASCADED AND A CONTRARIO METHOD FOR HOLE CRACK DETECTIONJierong CHENG, Institute for Infocomm Research, A-STARWei XIONG, Institute for Infocomm Research, A-STARYue WANG, Institute for Infocomm Research, A-STARShue Ching CHIA, Institute for Infocomm Research, A-STARWenyu CHEN, Institute for Infocomm Research, A-STARJia DU, Institute for Infocomm Research, A-STARYing GU, Institute for Infocomm Research, A-STARVictor Ter Shen KOW, National University of Singapore
ARS-P15.4 – BILATERAL SYMMETRY DETECTION BASED ON SCALE INVARIANT STRUCTURE FEATUREIbragim ATADJANOV, Kyung Hee UniversitySeungkyu LEE, Kyung Hee University
ARS-P15.5 – DETECT COHERENT MOTIONS IN CROWD SCENES BASED ON TRACKLETS ASSOCIATIONYi ZOU, Shanghai Jiao Tong UniversityXu ZHAO, Shanghai Jiao Tong UniversityYuncai LIU, Shanghai Jiao Tong University
ARS-P15.6 – REAL TIME RAILWAY EXTRACTION BY ANGLE ALIGNMENT MEASUREHao WU, Hong Kong Polytechnic UniversityWan-Chi SIU, Hong Kong Polytechnic University
ARS-P29: Texture Synthesis Monday, 14:00-16:00POSTER Room: POSTER CSession Chair(s): Mohamed DERICHE, KFUPM
ARS-P29.1 – QUANTUM-COMPUTATION-INSPIRED REVERSE ANALYSIS TEXTURE SYNTHESISJavier PORTILLA, Consejo Superior de Investigaciones Científicas (CSIC)
ARS-P29.2 – FAST IMAGE COMPLETION METHOD USING PATCH OFFSET STATISTICSMartin KOEPPEL, Technical University of BerlinMehdi BEN MAKHLOUF, Technical University of BerlinKarsten MUELLER, Fraunhofer Heinrich Hertz InstituteThomas WIEGAND, Technical University of Berlin
ICIP 2015 – Technical Program | 71
ARS-P29.3 – SUPER-RESOLUTION FROM LEARNING THE ENHANCEMENT RATIO AND TEXTURE/RESIDUAL DICTIONARYFang-Ju LIN, Academia Sinica, Taipei, Taiwan
ARS-P29.4 – TRANSPARENT TEXTURE TRANSFERChan-Tai YEH, National Tsing Hua UniversityTing-Hui TSAI, National Tsing Hua UniversityHwann-Tzong CHEN, National Tsing Hua University
ARS-P29.5 – AN OPTIMIZATION-BASED APPROACH FOR RESTORING MISSING STRUCTURES AND TEXTURES IN IMAGESJian MU, University of Notre DameDanny CHEN, University of Notre Dame
ARS-P36: Visual Tracking I Monday, 14:00-16:00POSTER Room: POSTER ESession Chair(s): Sylvain ROUSSEAU, École Centrale de Lille
ARS-P36.1 – ROBUSTLY TRACKING OBJECTS VIA MULTI-TASK KERNEL DYNAMIC SPARSE MODELZhangjian JI, University of Chinese Academy of Sciences Weiqiang WANG, University of Chinese Academy of Sciences Ke LU, University of Chinese Academy of Sciences
ARS-P36.2 – VISUAL TRACKING VIA GUIDED FILTERDandan DU, Dalian University of TechnologyHuchuan LU, Dalian University of TechnologyFu LI, Dalian University of TechnologyLihe ZHANG, Dalian University of Technology
ARS-P36.3 – VISUAL TRACKING WITH A STRUCTURED LOCAL MODELDandan DU, Dalian University of TechnologyHuchuan LU, Dalian University of TechnologyLihe ZHANG, Dalian University of Technology
ARS-P36.4 – INTERACTIVE IMAGE SEGMENTATION VIA CASCADED METRIC LEARNINGWenbin LI, Nanjing UniversityYinghuan SHI, Nanjing UniversityWanqi YANG, Nanjing UniversityHao WANG, Nanjing UniversityYang GAO, Nanjing University
ARS-P36.5 – PARTS-BASED MULTI-TASK SPARSE LEARNING FOR VISUAL TRACKINGZhengjian KANG, New York UniversityEdward WONG, New York University
ARS-P36.6 – LEARNING A TEMPORALLY INVARIANT REPRESENTATION FOR VISUAL TRACKINGChao MA, Shanghai Jiao Tong UniversityXiaokang YANG, Shanghai Jiao Tong UniversityChongyang ZHANG, Shanghai Jiao Tong UniversityMing-Hsuan YANG, University of California at Merced
«
«
72 | ICIP 2015 – Technical Program
ARS-P37: Visual Tracking II Monday, 14:00-16:00POSTER Room: POSTER FSession Chair(s): Sylvain ROUSSEAU, École Centrale de Lille
ARS-P37.1 – CORRELATED WARPED GUSSIAN PROCESSES FOR GENDER-SPECIFIC AGE ESTIMATIONDifei GAO, University of Electronic Science and Technology of ChinaLili PAN, University of Electronic Science and Technology of ChinaRisheng LIU, School of Software Technology, Dalian University of TechnologyRui CHEN, University of Electronic Science and Technology of ChinaMei XIE, University of Electronic Science and Technology of China
ARS-P37.2 – ROBUST VISUAL TRACKING VIA DISCRIMINATIVE SEQUENTIAL RANKINGGuangyu ZHONG, Dalian University of Technology Risheng LIU, Dalian University of Technology Zhixun SU, Dalian University of Technology
ARS-P37.3 – ROBUST VISUAL TRACKING VIA GUIDED LOW-RANK SUBSPACE LEARNINGDi WANG, Dalian University of TechnologyRisheng LIU, Dalian University of TechnologyZhixun SU, Dalian University of Technology
ARS-P37.4 – DOUBLE LAYER SALIENT PARTS BASED MULTI-PEOPLE TRACKINGZhi ZHOU, Nanyang Technological UniversityYue WANG, Institute for Infocomm Research (I2R)Eam Khwang TEOH, Nanyang Technological University
ARS-P37.5 – VISUAL TRACKING VIA ORTHOGONAL SPARSE CODINGJing WANG, Dalian University of TechnologyYiyang WANG, Dalian University of TechnologyRisheng LIU, Dalian University of TechnologyZhixun SU, Dalian University of Technology
ARS-P37.6 – DICTIONARY LEARNING FOR A SPARSE APPEARANCE MODEL IN VISUAL TRACKINGSylvain ROUSSEAU, École Centrale de LilleChristelle GARNIER, Telecom LillePierre CHAINAIS, École Centrale de Lille
ARS-P38: Visual Tracking III Monday, 14:00-16:00POSTER Room: POSTER GSession Chair(s): Sylvain ROUSSEAU, École Centrale de Lille
ARS-P38.1 – ADAPTIVE VISUAL TARGET DETECTION AND TRACKING USING INCREMENTAL APPEARANCE LEARNINGMahdi YAZDIAN-DEHKORDI, Shiraz UniversityZohreh AZIMIFAR, Shiraz University
ICIP 2015 – Technical Program | 73
ARS-P38.2 – ONLINE MULTI-PERSON TRACKING BASED ON GLOBAL SPARSE COLLABORATIVE REPRESENTATIONSLoïc fa*gOT-BOUQUET, CEA LISTRomaric AUDIGIER, CEA LISTYoann DHOME, CEA LISTFrédéric LERASLE, CNRS, LAAS
ARS-P38.3 – DIRECTIONAL RINGLET INTENSITY FEATURE TRANSFORM FOR TRACKINGEvan KRIEGER, University of DaytonPaheding SIDIKE, University of DaytonTheus ASPIRAS, University of DaytonVijayan ASARI, University of Dayton
ARS-P38.4 – MULTI-TARGET TRACKING VIA PARATACTIC-SERIAL TRACKLET GRAPHHao SHENG, Beihang UniversityJiahui CHEN, Beihang UniversityJiangjian XIAO, Ningbo Institute of Industrial TechnologyChao LI, Beihang UniversityZhang XIONG, Beihang University
ARS-P38.5 – FAST TRACKING VIA CONTEXT DEPTH MODEL LEARNINGZhaoyun CHEN, National University of Defense TechnologyLei LUO, National University of Defense TechnologyMei WEN, National University of Defense TechnologyChunyuan ZHANG, National University of Defense Technology
ARS-P38.6 – CONTEXTUAL OBJECT TRACKER WITH STRUCTURE ENCODINGTanushri CHAKRAVORTY, École polytechnique de MontréalGuillaume-Alexandre BILODEAU, École polytechnique de MontréalEric GRANGER, École de technologie supérieure
COI-P1: Hyperspectral Imaging Monday, 14:00-16:00POSTER Room: POSTER KSession Chair(s): Ronan FABLET, Telecom Bretagne
COI-P1.1 – A SPECTRAL UNMIXING METHOD BASED ON WAVELET WEIGHTED SIMILARITYQingyu PANG, Tsinghua UniversityJing YU, Tsinghua UniversityWeidong SUN, Tsinghua University
COI-P1.2 – HYPERSPECTRAL IMAGE INTERPRETATION BASED ON PARTIAL LEAST SQUARESAndrey Bicalho SANTOS, Federal University of Minas GeraisArnaldo ARAUJO, Federal University of Minas GeraisWilliam Robson SCHWARTZ, Federal University of Minas GeraisDavid MENOTTI, Federal University of Ouro Preto
COI-P1.3 – SPATIO-SPECTRAL GAUSSIAN RANDOM FIELD MODELING APPROACH FOR TARGET DETECTION ON HYPERSPECTRAL DATA OBTAINED IN VERY LOW SNROla AHMAD, University of StrasbourgChristophe COLLET, University of StrasbourgFabien SALZENSTEIN, University of Strasbourg
74 | ICIP 2015 – Technical Program
COI-P1.4 – MULTILAYER MANIFOLD AND SPARSITY CONSTRAINTED NONNEGATIVE MATRIXFACTORIZATION FOR HYPERSPECTRAL UNMIXINGShu ZHENQIU, Nanjing University of Science and TechnologyZhou JUN, Griffith University Tong LEI, Griffith University Bai XIAO, Beihang UniversityZhao CHUNXIA, Nanjing University of Science and Technology
COI-P1.5 – HYPERSPECTRAL CLASSIFICATION VIA LEARNT FEATURESYazhou LIU, Nanjing University of Science and TechnologyGuo CAO, Nanjing University of Science and TechnologyQuansen SUN, Nanjing University of Science and TechnologyMel SIEGEL, Nanjing University of Science and Technology
COI-P1.6 – NON-hom*oGENEOUS PRIORS IN A BAYESIAN LATENT CLASS MODEL FOR OCEAN COLOR INVERSIONBertrand SAULQUIN, ACRI-STRonan FABLET, telecom bretagne
COI-P2: Radar Imaging Monday, 14:00-16:00POSTER Room: POSTER LSession Chair(s): Mihai DATCU, German Aerospace Center (DLR)
COI-P2.1 – NONPARAMETRIC BACKGROUND MODEL BASED CLUTTER MAP FOR X-BAND MARINE RADARYi ZHOU, Information Science and Technology College, Dalian Maritime UniversityXiaoming LIU, Information Science and Technology College, Dalian Maritime UniversityJidong SUO, Information Science and Technology College, Dalian Maritime UniversityChang LIU, Information Science and Technology College, Dalian Maritime UniversityXiaohong SU, Dalian Maritime UniversityLimei LIU, Computer Department of Library, Dalian Maritime University
COI-P2.2 – A NOVEL MOVING PARAMETER ESTIMATION APPROACH OF FAST MOVING TARGETS BASED ON PHASE EXTRACTIONKai TAN, Key Laboratory of Electromagnetic Space Information, Chinese Academy of SciencesWeihai LI, Key Laboratory of Electromagnetic Space Information, Chinese Academy of Sciences
COI-P2.3 – A VALIDATION OF ICA DECOMPOSITION FOR POLSAR IMAGES BY USING MEASURES OF NORMALIZED COMPRESSION DISTANCERadu T . NASE, University Politehnica of BucharestCorina V . DUVA, University Politehnica of BucharestMihai DATCU, German Aerospace CenterDan R . DUCANU, Military Technical Academy
COI-P2.4 – A GENERALIZED FORM OF THE INSAR PHASE UNWRAPPING PROBLEM BASED ON A COMPRESSED SENSING TECHNIQUEWajih BEN ABDALLAH, Higher School of Communications of TunisRiadh ABDELFATTAH, Higher School of Communications of Tunis
ICIP 2015 – Technical Program | 75
COI-P2.5 – STEREO RADARGRAMMETRY USING AIRBORNE SAR IMAGES WITHOUT GCPDaiki MARUKI, Tohoku UniversityShuji SAKAI, Tohoku UniversityKoichi ITO, Tohoku UniversityTakafumi AOKI, Tohoku UniversityJyunpei UEMOTO, National Institute of Information and Communications TechnologySeiho URATSUKA, National Institute of Information and Communications Technology
COI-P2.6 – INTEGRABILITY-REGULARIZED PHASE UNWRAPPING VIA SPARSE ERROR CORRECTIONGarrett WARNELL, U.S. Army Research LaboratoryVishal M PATEL, University of MarylandRama CHELLAPPA, University of Maryland
COI-P3: Seismic and Remote Sensing Imaging Monday, 14:00-16:00POSTER Room: POSTER MSession Chair(s): Stefan WINKLER, Advanced Digital Sciences Center, University of Illinois at Urbana-Champaign
COI-P3.1 – MULTI-LEVEL SEMANTIC LABELING OF SKY/CLOUD IMAGESSoumyabrata DEV, Nanyang Technological University SingaporeYee Hui LEE, Nanyang Technological University SingaporeStefan WINKLER, Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign
COI-P3.2 – TENSOR-BASED SUBSPACE LEARNING FOR TRACKING SALT DOME BOUNDARIESZhen WANG, Georgia Institute of TechnologyZhiling LONG, Georgia Institute of TechnologyGhassan ALREGIB, Georgia Institute of Technology
COI-P3.3 – DESTRIPING ALGORITHM WITH L0 SPARSITY PRIOR FOR REMOTE SENSING IMAGESHai LIU, Central China Normal UniversityZhaoli ZHANG, Central China Normal UniversitySanya LIU, Central China Normal UniversityTingting LIU, Central China Normal UniversityYi CHANG, Central China Normal University
COI-P3.4 – SPARSE ADAPTIVE TEMPLATE MATCHING AND FILTERING FOR 2D SEISMIC IMAGES WITH DUAL-TREE WAVELETS AND PROXIMAL METHODSMai Quyen PHAM, IFP Energies nouvellesCaroline CHAUX, Aix-Marseille Université, CNRS, Centrale Marseille, I2M, UMR 7373Laurent DUVAL, IFP Energies nouvellesJean-Christophe PESQUET, Université Paris-Est LIGM UMR-CNRS 8049
COI-P3.5 – A HYBRID APPROACH FOR SALT DOME DETECTION IN 2D AND 3D SEISMIC DATAAsjad AMIN, KFUPMMohamed DERICHE, KFUPM
76 | ICIP 2015 – Technical Program
ELI-O4: HDR Imaging Monday, 14:00-16:00LECTURE Room: 205ASession Chair(s): David BULL, University of Bristol
14:00 ELI-O4.1 – EXPOSURE BRACKETING VIA AUTOMATIC EXPOSURE SELECTIONReza POURREZA-SHAHRI, University of Texas at DallasNasser KEHTARNAVAZ, University of Texas at Dallas
14:20 ELI-O4.2 – RADIOMETRIC CALIBRATION FOR HDR IMAGINGAhmed SOHAIB, The Australian National UniversityAntonio ROBLES-KELLY, The Australian National Universit, National ICT Australia
14:40 « ELI-O4.3 – CHROMATIC CALIBRATION OF AN HDR DISPLAY USING 3D OCTREE FORESTSJing LIU, UC Santa CruzNikolce STEFANOSKI, Disney Research ZürichTunc AYDIN, Disney Research ZürichAnselm GRUNDHÖFER, Disney Research ZürichAljoša SMOLIC, Disney Research Zürich
15:00 ELI-O4.4 – ADAPTIVE EXPOSURE FUSION FOR HIGH DYNAMIC RANGE IMAGINGSidhdharthkumar PATEL, Ryerson UniversityDimitrios ANDROUTSOS, Ryerson UniversityMatthew KYAN, Ryerson University
15:20 ELI-O4.5 – HIGH DYNAMIC RANGE CONTENT CALIBRATION FOR ACCURATE ACQUISITION AND DISPLAYYang ZHANG, Bristol Vision Institute, University of BristolDimitris AGRAFIOTIS, Bristol Vision Institute, University of BristolDavid BULL, Bristol Vision Institute, University of Bristol
IFS-P2: Data Hiding I Monday, 14:00-16:00POSTER Room: POSTER NSession Chair(s): William PUECH, Université de Montellier
IFS-P2.1 – ROBUST STEGANALYSIS BASED ON TRAINING SET CONSTRUCTION AND ENSEMBLE CLASSIFIERS WEIGHTINGXikai XU, Institute of Automation, Chinese Academy of SciencesJing DONG, Institute of Automation, Chinese Academy of SciencesWei WANG, Institute of Automation, Chinese Academy of SciencesTieniu TAN, Institute of Automation, Chinese Academy of Sciences
IFS-P2.2 – IMAGE FINGERPRINTING SYSTEM BASED ON COLLUSION SECURE CODE AND WATERMARKING METHODMinoru KURIBAYASHI, Kobe UniversityHans Georg SCHAATHUN, Alesund University
IFS-P2.3 – WATERMARKING FOR POSITION-MAPPING-BASED HALFTONINGJing-ming GUO, National Taiwan University of Science and TechnologyYun-Fu LIU, National Taiwan University of Science and TechnologyShih-Hung CHOU, National Taiwan University of Science and TechnologyJiann-Der LEE, Chang Gung University
ICIP 2015 – Technical Program | 77
IFS-P2.4 – REVERSIBLE WATERMARKING USING ENHANCED LOCAL PREDICTIONJiayuan FAN, Agency for Science, Technology and Research (A*STAR)Tao CHEN, Agency for Science, Technology and Research (A*STAR)
IFS-P2.5 – RECURSIVE OPTIMIZATION OF SPHERICAL WATERMARKING USING TRANSPORTATION THEORYYuan-Gen WANG, School of Information, Zhongkai University of Agriculture and EngineeringJian CAO, Shenzhen Graduate School, Harbin Institute of TechnologyGuopu ZHU, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
IFS-P2.6 – FEATURE REGIONS BASED ON GRAPH OPTIMIZATION FOR ROBUST REVERSIBLE WATERMARKINGGuangxue YIN, Xidian UniversityLingling AN, Xidian UniversityXinbo GAO, Xidian UniversityDacheng TAO, University of Technology, Sydney
IFS-P5: Data Hiding II Monday, 14:00-16:00POSTER Room: POSTER OSession Chair(s): William PUECH, Université de Montellier
IFS-P5.1 – ROBUST CONTENT FINGERPRINTING ALGORITHM BASED ON SPARSE CODINGYuenan LI, Tianjin University
IFS-P5.2 – OUTLIER AGGREGATION TO PICK UP SCATTERED WATERMARK ENERGYHasan SHEIKH FARIDUL, Technicolor R&D FranceGwenaël DOËRR, Technicolor R&D France
IFS-P5.3 – A NEW DATA CODING SCHEME USING CONTRAST-CONTROLLABLE COLOR INTERSECTIONYi-Chong ZENG, Institute for Information IndustryWen-Tsung CHANG, Institute for Information Industry
IFS-P5.4 – IMAGE TRANSMORPHING WITH JPEGLin YUAN, EPFLTouradj EBRAHIMI, EPFL
IFS-P5.5 – HIGH CAPACITY DATA-HIDING FOR 3D MESHES BASED ON STATIC ARITHMETIC CODINGVincent ITIER, LIRMMWilliam PUECH, LIRMMJean-Pierre PEDEBOY, STRATEGIES
NEW-O1: Graph-based Image & Video Coding Monday, 14:00-16:00LECTURE Room: 202Session Chair(s): Riccardo LEONARDI, Univerity of Brescia
14:00 «NEW-O1.1 – PREDICTIVE GRAPH CONSTRUCTION FOR IMAGE COMPRESSIONGiulia FRACASTORO, Politecnico di TorinoEnrico MAGLI, Politecnico di Torino
«
78 | ICIP 2015 – Technical Program
14:20 NEW-O1.2 – UNIFYING THE RANDOM WALKER ALGORITHM AND THE SIR MODEL FOR GRAPH CLUSTERING AND IMAGE SEGMENTATIONChristos BAMPIS, University of Texas at AustinPetros MARAGOS, National Technical University of Athens
14:40 « NEW-O1.3 – SUPERPIXEL-DRIVEN GRAPH TRANSFORM FOR IMAGE COMPRESSIONGiulia FRACASTORO, Politecnico di TorinoFrancesco VERDOJA, Università degli Studi di TorinoMarco GRANGETTO, Università degli Studi di TorinoEnrico MAGLI, Politecnico di Torino
15:00 « NEW-O1.4 – GRAPH-BASED MOTION ESTIMATION AND COMPENSATION FOR DYNAMIC 3D POINT CLOUD COMPRESSIONDorina THANOU, EPFLPhilip CHOU, Microsoft ResearchPascal FROSSARD, EPFL
15:20 NEW-O1.5 – GRAPH-BASED TRANSFORMS FOR INTER PREDICTED VIDEO CODINGHilmi E . EGILMEZ, University of Southern CaliforniaAmir SAID, LG ElectronicsYung-Hsuan CHAO, University of Southern CaliforniaAntonio ORTEGA, University of Southern California
SNT-S2: Show & Tell II Monday, 14:00-16:00SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S2.1 – AN INTERACTIVE AND REALTIME DEPTH COMPOSITING TOOL FOR CINEMA PREVIZ ON-SET Timothée DE GOUSSENCOURT, Gipsa-lab & SolidanimPascal BERTOLINO, Gipsa-labIn this demonstration, we will present a tool for virtual production in movie making . We will present a hardware implementation as well as the processing steps . To illustrate our demonstration, 2 scenarios will be shown in which people will be able to interact with virtual contents .
SNT-S2.2 – EASY SEMI-SUPERVISED SEGMENTATION OF COMPLEX OBJECTSPierre BUYSSENS, Normandie UniversitéOlivier LEZORAY, Normandie UniversitéWe will demonstrate a novel semi-supervised segmentation on a set of provided images . This demonstration basically consists in placing seeds with 2 (foreground/background) or more labels to get a desired segmentation result, such as the ones in the paper . The demo will interactively show the diffusion of the labels on the image from the seeds provided by the user on the application .
ICIP 2015 – Technical Program | 79
SNT-S2.3 – TOWARDS FAST HEVC ENCODINGSaverio G . BLASI, Queen Mary University of LondonEduardo PEIXOTO, Universidade de BrasiliaBruno MACCHIAVELLO, Universidade de BrasiliaEdson Mintsu HUNG, Universidade de BrasiliaIvan ZUPANCIC, Queen Mary University of LondonIn this demo, the results of several algorithms developed with the objective of reducing the complexity of HEVC encoder implementations will be demonstrated . The demo will show the visual quality of various full-HD sequences encoded using each of the algorithms separately or combining several algorithms together, comparing it with reference encoder implementations, while presenting the time needed to encode each of the presented sequences .
SNT-S2.4 – QUANTUM CIRCLE DETECTION: APPLICATIONS IN CELL COUNTING AND PEOPLE TRACKINGDavi GEIGER, University of New YorkThis demo shows the use of quantum methods for circle detection, with applications in cell-counting and people (head) tracking . Replacing the positive numbers classically used in the parameter space of the Hough transforms by complex numbers allows cancellation effects when adding up the votes . Cancellation and the computation of shape likelihood via a complex number’s magnitude square lead to more robust solutions than the classic algorithms .
SS8-O2: Big Media Data Processing and Analysis: Ad memoriam of Prof. A.N. Venetsanopoulos Monday, 14:00-16:00LECTURE Room: 205BSession Chair(s): Ioannis PITAS, Aristotle University of Thessaloniki
14:00 «SS8-O2.1 – MULTIPASS ENCODING FOR REDUCING PULSING ARTIFACTS IN CLOUD BASED VIDEO TRANSCODINGYao-Chung LIN, Google Inc.Hugh DENMAN, Google Inc.Anil KOKARAM, Google Inc.
14:20 SS8-O2.5 – VISUAL ATTENTION FOR CONTENT BASED IMAGE RETRIEVALAlex PAPUSHOY, University of YorkAdrian BORS, University of York
14:40 SS8-O2.3 – FACE2GPS: ESTIMATING GEOGRAPHIC LOCATION FROM FACIAL FEATURESMohammad ISLAM, University of KentuckyScott WORKMAN, University of KentuckyNathan JACOBS, University of Kentucky
15:00 SS8-O2.4 – LARGE-SCALE NONLINEAR FACIAL IMAGE CLASSIFICATION BASED ON APPROXIMATE KERNEL EXTREME LEARNING MACHIINEAlexandros IOSIFIDIS, Aristotle University of ThessalonikiAnastasios TEFAS, Aristotle University of ThessalonikiIoannis PITAS, Aristotle University of Thessaloniki
80 | ICIP 2015 – Technical Program
15:20 SS8-O2.2 – TRAFFIC FLOW FROM A LOW FRAME RATE CITY CAMERAEvgeny TOROPOV, CMULiangyan GUI, CMUShanghang ZHANG, CMUSatwik KOTTUR, CMUJose MOURA, CMU
TEC-O8: Curvilinear System Analysis Monday, 14:00-16:00LECTURE Room: 205CSession Chair(s): Jan KYBIC, Czech Technical University
14:00 TEC-O8.1 – IMAGE ANALYSIS OF VIDEOKYMOGRAPHIC DATAAdam NOVOZÁMSKÝ, Institute of Information Theory and Automation, Academy of Sciences of the Czech RepublicJiri SEDLAR, Institute of Information Theory and Automation, Academy of Sciences of the Czech RepublicAles ZITA, Institute of Information Theory and Automation, Academy of Sciences of the Czech RepublicBarbara ZITOVA, Institute of Information Theory and Automation, Academy of Sciences of the Czech RepublicFilip SROUBEK, Institute of Information Theory and Automation, Academy of Sciences of the Czech RepublicJan G . SVEC, Voice Research Lab, Department of Biophysics, Palack´y UniversityJitka VYDROVA, Voice Centre Prague, Medical Healthcom, Ltd.Jan FLUSSER, Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic
14:20 TEC-O8.2 – USER-GUIDED GRAPH REDUCTION FOR FAST IMAGE SEGMENTATIONHoussem-Eddine GUEZIRI, École de technologie supérieureMichael J . MCGUFFIN, École de technologie supérieureCatherine LAPORTE, École de technologie supérieure
14:40 TEC-O8.3 – FAST 3D TRACKING AND QUANTIZATION OF SMALL VASCULAR STRUCTURES IN 3D MEDICAL IMAGESYusuf AFIFI, Ain Shams UniversityMahmoud KHALIL, Ain Shams UniversityHazem ABBAS, The German Univesity in Cairo
15:00 TEC-O8.4 – IMAGE-BASED EVALUATION OF TREATMENT RESPONSES OF FACIAL WRINKLESUSING LDDMM REGISTRATION AND GABOR FEATURESNazre BATOOL, Inria Sophia-AntipolisJosiane ZERUBIA, Inria Sophia-Antipolis
15:20 TEC-O8.5 – GEOMETRICAL GRAPH MATCHING USING MONTE CARLO TREE SEARCHMiguel Amável PINHEIRO, Czech Technical University in PragueJan KYBIC, Czech Technical University in Prague
ICIP 2015 – Technical Program | 81
TEC-P15: Low-level Feature Extraction and Classification Monday, 14:00-16:00POSTER Room: POSTER HSession Chair(s): Neslihan BAYRAMOGLU, University of Oulu
TEC-P15.1 – A NOVEL FEATURE DESCRIPTOR BASED ON MICROSCOPY IMAGE STATISTICSNeslihan BAYRAMOGLU, Center for Machine Vision Research, University of OuluJuho KANNALA, Center for Machine Vision Research, University of OuluMalin AKERFELT, Centre for Biotechnology, University of TurkuMika KAAKINEN, Faculty of Biochemistry and Molecular Medicine, University of OuluLauri EKLUND, Faculty of Biochemistry and Molecular Medicine, University of OuluMatthias NEES, Centre for Biotechnology, University of TurkuJanne HEIKKILÄ, Center for Machine Vision Research, University of Oulu
TEC-P15.2 – A STUDY ON COMPACT AND DISCRIMINATIVE PARAMETER INITIALIZATION OF EXTREME LEARNING MACHINE FOR IMAGE CLASSIFICATIONXiao LIU, School of Information Science and Engineering, Qufu Normal UniversityJun MIAO, Institute of Computing Technology, Chinese Academy of SciencesLaiyun QING, School of Computer and Control Engineering, University of Chinese Academy of SciencesBaoxiang CAO, School of Information Science and Engineering, Qufu Normal UniversityJun WANG, Department of Mechanical and Automation Engineering, Chinese University of Hong Kong
TEC-P15.3 – A TWO-STAGE HOG FEATURE EXTRACTION PROCESSOR EMBEDDED WITH SVM FOR PEDESTRIAN DETECTION Xu YUAN, Shenzhen Key Lab of Advanced Communication and Information Processing College of Information EngineeringLi CAINIAN, Shenzhen Key Lab of Advanced Communication and Information Processing College of Information EngineeringXu XIAOLIANG, Shenzhen Key Lab of Advanced Communication and Information Processing College of Information EngineeringJiang MEI, Shenzhen Key Lab of Advanced Communication and Information Processing College of Information EngZhang JIANGUO, Shenzhen Key Lab of Advanced Communication and Information Processing College of Information Eng
TEC-P15.4 – SCALE- AND ORIENTATION-INVARIANT KEYPOINTS IN HIGHER-DIMENSIONAL DATABlaine RISTER, Stanford UniversityDaniel REITER, Rice UniversityHejia ZHANG, Princeton UniversityDaniel VOLZ, Rice UniversityMark HOROWITZ, Stanford UniversityRefaat GABR, University of Texas Health Science Center at HoustonJoseph CAVALLARO, Rice University
TEC-P15.5 – A SUPERVISED LINEAR FEATURE EXTRACTION METHOD FOR MULTICLASS CLASSIFICATION PROBLEMS USING INFORMATION-THEORETIC LEARNINGFarid OVEISI, University of BoltonShahrzad OVEISI, Azad UniversityJack LUO, University of Bolton
82 | ICIP 2015 – Technical Program
TEC-P15.6 – A LOCAL MUTUAL INFORMATION-BASED METHOD FOR LARGE SCALE ACTIVE LEARNING Farid OVEISI, University of BoltonShahrzad OVEISI, Azad UniversityJack LUO, University of Bolton
TEC-P24: Sparse Recovery Monday, 14:00-16:00POSTER Room: POSTER JSession Chair(s): Konstantinos N . PLATANIOTIS, University of Toronto
TEC-P24.1 – RECONSTRUCTION OF COMPRESSIVELY SENSED ULTRASOUND RF ECHOES BY EXPLOITING NON-GAUSSIANITY AND TEMPORAL STRUCTURERichard PORTER, University of BristolVladislav TADIC, University of BristolAlin ACHIM, University of Bristol
TEC-P24.2 – SPARSE TENSOR RECOVERY VIA COMBINED FIRST AND SECOND ORDER HIGH-ACCURACY TOTAL VARIATIONMahdi S . HOSSEINI, University of TorontoKonstantinos N . PLATANIOTIS, University of Toronto
TEC-P24.3 – DISCRIMINATIVE LABEL CONSISTENT DICTIONARY LEARNINGAngshul MAJUMDAR, IIITD
TEC-P24.4 – SPATIAL-TEMPORAL RECOVERY FOR HIERARCHICAL FRAME BASED VIDEO COMPRESSED SENSINGWenbin CHE, Dept. of Computer Science and Technology, Harbin Institute of TechnologyXinwei GAO, Dept. of Computer Science and Technology, Harbin Institute of TechnologyXiaopeng FAN, Dept. of Computer Science and Technology, Harbin Institute of TechnologyFeng JIANG, Dept. of Computer Science and Technology, Harbin Institute of TechnologyDebin ZHAO, Dept. of Computer Science and Technology, Harbin Institute of Technology
TEC-P24.5 – COMPRESSIVE SENSING OF VIDEO WITH WEIGHTED SENSING AND MEASUREMENT ALLOCATIONKhanh DINH, Sungkyunkwan UniversityThuong NGUYEN CANH, Sungkyunkwan UniversityByeungwoo JEON, Sungkyunkwan University
TEC-P24.6 – MULTI-SCALE/MULTI-RESOLUTION KRONECKER COMPRESSIVE IMAGINGThuong NGUYEN CANH, School of Electronic and Electrical Engineering, Sungkyunkwan UniversityKhanh DINH, School of Electronic and Electrical Engineering, Sungkyunkwan UniversityByeungwoo JEON, School of Electronic and Electrical Engineering, Sungkyunkwan University
«
ICIP 2015 – Technical Program | 83
ARS-O13: Multimedia Retrieval and Indexing Monday, 16:30-18:30LECTURE Room: 205ASession Chair(s): Edward J . DELP, Purdue University
16:30 ARS-O13.1 – CONTENT BASED VIDEO RETRIEVAL ON MOBILE DEVICES: HOW MUCH CONTENT IS ENOUGH?Khalid TAHBOUB, Purdue UniversityNeeraj GADGIL, Purdue UniversityEdward J . DELP, Purdue University
16:50 ARS-O13.2 – CROSS-MODALITY HASHING WITH PARTIAL CORRESPONDENCEYun GU, Shanghai Jiao Tong UniveristyHaoyang XUE, Shanghai Jiao Tong UniveristyJie YANG, Shanghai Jiao Tong UniveristyPengfei SHI, Shanghai Jiao Tong University
17:10 «ARS-O13.3 – ONLINE SUPERVISED HASHINGFatih CAKIR, Boston UniversityStan SCLAROFF, Boston University
17:30 ARS-O13.4 – A COMPACT SHOT REPRESENTATION FOR VIDEO SEMANTIC INDEXINGJinzhuo WANG, Peking University Shenzhen Graduate SchoolWenmin WANG, Peking University Shenzhen Graduate SchoolRonggang WANG, Peking University Shenzhen Graduate SchoolWen GAO, Peking University
17:50 ARS-O13.5 – RANK-AWARE GRAPH FUSION WITH CONTEXTUAL DISSIMILARITY MEASUREMENT FOR IMAGE RETRIEVALXu XIE, USTCWengang ZHOU, University of Science and Technology of ChinaHouqiang LI, USTCQi TIAN, University of Texas at San Antonio
18:10 ARS-O13.6 – HIERARCHICAL MULTI-VLAD FOR IMAGE RETRIEVALYitong WANG, The Institute of Digital Media, School of EE&CS, Peking UniversityLing-Yu DUAN, The Institute of Digital Media, School of EE&CS, Peking UniversityJie LIN, Institute for Infocomm ResearchZhe WANG, The Institute of Digital Media, School of EE&CS, Peking UniversityTiejun HUANG, The Institute of Digital Media, School of EE&CS, Peking University
ARS-O15: Object Tracking Monday, 16:30-18:30LECTURE Room: 204BSession Chair(s): Guillaume-Alexandre BILODEAU, École polytechnique de Montréal
16:30 ARS-O15.1 – MULTIPLE MODEL ADAPTIVE VISUAL TRACKING WITH CORRELATION FILTERSGokhan TANISIK, ASELSAN Inc.Erhan GUNDOGDU, ASELSAN Inc.
16:50 ARS-O15.2 – SEGMENT-WISE ONLINE LEARNING BASED ON GREEDY ALGORITHM FOR REAL-TIME MULTI-TARGET TRACKINGChanghoon LEE, KAISTChang D . YOO, KAIST
84 | ICIP 2015 – Technical Program
17:10 ARS-O15.3 – VISUAL TRACKING VIA MANIFOLD REGULARIZED LOCAL STRUCTURED SPARSE REPRESENTATION MODELLingfeng WANG, NLPR, Institute of Automation, Chinese Academy of SciencesChunhong PAN, NLPR, Institute of Automation, Chinese Academy of Sciences
17:30 ARS-O15.4 – ROBUST VISUAL TRACKING USING JOINT SCALE-SPATIAL CORRELATION FILTERSMengdan ZHANG, National Laboratory of Pattern Recognition, Institute of AutomationJunliang XING, National Laboratory of Pattern Recognition, Institute of AutomationJin GAO, National Laboratory of Pattern Recognition, Institute of AutomationWeiming HU, National Laboratory of Pattern Recognition, Institute of Automation
17:50 ARS-O15.5 – ROBUST MULTI-OBJECT TRACKING USING CONFIDENT DETECTIONS AND SAFE TRACKLETSAli TAALIMI, University of Tennessee-KnoxvilleHairong QI, University of Tennessee-Knoxville
18:10 ARS-O15.6 – MULTIPLE OBJECT TRACKING BASED ON SPARSE GENERATIVE APPEARANCEMODELINGDorra RIAHI, École Polytechnique de MontréalGuillaume-Alexandre BILODEAU, École Polytechnique de Montréal
ARS-O17: Saliency Analysis Monday, 16:30-18:30LECTURE Room: 204ASession Chair(s): Jie YANG, Shanghai Jiaotong University
16:30 ARS-O17.1 – GEODESIC WEIGHTED BAYESIAN MODEL FOR SALIENT OBJECT DETECTIONXiang WANG, Department of Electronic Engineering, Tsinghua UniversityHuimin MA, Department of Electronic Engineering, Tsinghua UniversityXiaozhi CHEN, Department of Electronic Engineering, Tsinghua University
16:50 ARS-O17.2 – RGB-D SALIENCY DETECTION VIA MUTUAL GUIDED MANIFOLD RANKINGHaoyang XUE, Shanghai Jiao Tong UniversityYun GU, Shanghai Jiao Tong UniversityYijun LI, Shanghai Jiao Tong UniversityJie YANG, Shanghai Jiao Tong University
17:10 ARS-O17.3 – CO-SALIENCY DETECTION VIA SIMILARITY-BASED SALIENCY PROPAGATIONChenjie GE, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityKeren FU, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityYijun LI, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityJie YANG, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityPengfei SHI, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityLi BAI, University of Nottingham
17:30 ARS-O17.4 – UNSUPERVISED COSEGMENTATION BASED ON GLOBAL CLUSTERING AND SALIENCYLucas LATTARI, Universidade Federal FluminenseAnselmo MONTENEGRO, Universidade Federal FluminenseCristina VASCONCELOS, Universidade Federal Fluminense
ICIP 2015 – Technical Program | 85
17:50 ARS-O17.5 – DICTIONARY LEARNING BASED SUPERPIXELS CLUSTERING FOR WEAKLY-SUPERVISED SEMANTIC SEGMENTATIONPeng YING, CASIAJing LIU, CASIAHanqing LU, The Institute of Automation of the Chinese Academy of Sciences (CASIA)
18:10 ARS-O17.6 – GROUP SALIENCY PROPAGATION FOR LARGE SCALE AND QUICK IMAGE CO-SEGMENTATIONKoteswar Rao JERRIPOTHULA, Nanyang Technological UniversityJianfei CAI, Nanyang Technological UniversityJunsong YUAN, Nanyang Technological University
ARS-O20: Visualization and Image Rendering Monday, 16:30-18:30LECTURE Room: 203Session Chair(s): Mujdat ÇETIN, Sabanci University
16:30 ARS-O20.1 – VOLUME VISUALIZATION FOR OUT-OF-CORE 3D IMAGES BASED ON SEMI-ADAPTIVE PARTITIONINGJian XUE, University of the Chinese Academy of SciencesKe LU, University of the Chinese Academy of Sciences
16:50 ARS-O20.2 – A FRAMEWORK FOR IMAGE-BASED ASSET GENERATION AND ANIMATIONJohannes FURCH, Fraunhofer HHIAnna HILSMANN, Fraunhofer HHI, Humboldt Universität zu BerlinPeter EISERT, Fraunhofer HHI, Humboldt Universität zu Berlin
17:10 ARS-O20.3 – ITERATIVE MASK GENERATION METHOD FOR HANDLING OCCLUSION IN OPTICAL FLOW ASSISTED VIEW INTERPOLATIONHoda REZAEE KAVIANI, McMaster UniversityShahram SHIRANI, McMaster University
17:30 ARS-O20.4 – FAST SPARSE EDGE-BASED INTRINSIC IMAGE DECOMPOSITION GUIDED BY CHROMATICITY GRADIENTSJinze YU, The University of TokyoYoichi SATO, The University of Tokyo
17:50 ARS-O20.5 – SPARSE EDIT PROPAGATION FOR HIGH RESOLUTION IMAGE USING SUPPORT VECTOR MACHINESChangjae OH, Yonsei UniversitySeungchul RYU, Yonsei UniversityYoungjung KIM, Yonsei UniversityJihyun KIM, LG ElectronicsTaewoong PARK, LG ElectronicsKwanghoon SOHN, Yonsei University
18:10 ARS-O20.6 – COLOR TO GRAYSCALE IMAGE CONVERSION USING MODULATION DOMAIN QUADRATIC PROGRAMMINGChuong NGUYEN, University of OklahomaJoseph HAVLICEK, University of Oklahoma
86 | ICIP 2015 – Technical Program
ARS-O10: Learning I Monday, 16:30-18:30LECTURE Room: 202Session Chair(s): Markus FLIERL, KTH Royal Institute of Technology
16:30 ARS-O10.1 – CATEGORIZATION OF CLOUD IMAGE PATCHES USING AN IMPROVED TEXTON-BASED APPROACHSoumyabrata DEV, Nanyang Technological University SingaporeYee Hui LEE, Nanyang Technological University SingaporeStefan WINKLER, Advanced Digital Sciences Center (ADSC), University of Illinois at Urbana-Champaign
16:50 ARS-O10.2 – LOCALITY SENSITIVE DISCRIMINATIVE DICTIONARY LEARNINGJun GUO, School of Information and Communication Engineering, Dalian University of TechnologyYanqing GUO, School of Information and Communication Engineering, Dalian University of TechnologyYi LI, School of Information and Communication Engineering, Dalian University of TechnologyBo WANG, School of Information and Communication Engineering, Dalian University of TechnologyMing LI, School of Information and Communication Engineering, Dalian University of Technology
17:10 ARS-O10.3 – MAX-MARGIN ANALYSIS BASED PATCH SAMPLING FOR DISCOVERY OF MID-LEVEL PARTSLingxiao YANG, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, ChinaXiaohua XIE, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China
17:30 « ARS-O10.4 – CLASSIFICATION BASED ON WEIGHTED SPARSE REPRESENTATION USINGSMOOTHED L0 NORM WITH NON-NEGATIVE COEFFICIENTSRahman KHORSANDI, University Of MiamiMohamed ABDEL-MOTTALEB, University Of Miami
17:50 ARS-O10.5 – MULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIERAqsa SHABBIR, Ghent UniversityGeert VERDOOLAEGE, Ghent University
18:10 « ARS-O10.6 – CLASS NOISE REMOVAL AND CORRECTION FOR IMAGE CLASSIFICATION USING ENSEMBLE MARGINWei FENG, Bordeaux INPSamia BOUKIR, Bordeaux INP
ARS-P18: Indexing and Retrieval Monday, 16:30-18:30POSTER Room: POSTER BSession Chair(s): Nicolas TSAPATSOULIS, Cyprus University of Technology
ICIP 2015 – Technical Program | 87
ARS-P18.1 – UNSUPERVISED SPORTS VIDEO PARTICLES ANNOTATION BASED ON SOCIAL LATENT SEMANTIC ANALYSISKlimis NTALIANIS, Athens University of Applied SciencesNicolas TSAPATSOULIS, Cyprus University of Technology
ARS-P18.2 – EXTRACTION OF HIERARCHICAL STRUCTURE OF WEB COMMUNITIES INCLUDING SALIENT KEYWORD ESTIMATION FOR WEB VIDEO RETRIEVALRyosuke HARAKAWA, Hokkaido UniversityTakahiro OGAWA, Hokkaido UniversityMiki HASEYAMA, Hokkaido University
ARS-P18.3 – SEARCH AND RETRIEVAL OF MULTI-MODAL DATA ASSOCIATED WITH IMAGE-PARTSNiloufar POURIAN, Department of Electrical and Computer Engineering, University of California at Santa BarbaraS . KARTHIKEYAN, Department of Electrical and Computer Engineering, University of California at Santa BarbaraB .S . MANJUNATH, Department of Electrical and Computer Engineering, University of California at Santa Barbara
ARS-P18.4 – ACCELERATING CDVS EXTRACTION ON MOBILE PLATFORM Shen ZHANG, Peking University Shenzhen Graduate SchoolRonggang WANG, Peking University Shenzhen Graduate SchoolQiusi WANG, Peking University Shenzhen Graduate SchoolWenmin WANG, Peking University Shenzhen Graduate School
ARS-P18.5 – ATTRIBUTE CONSTRAINED SUBSPACE LEARNINGMohammadreza BABAEE, Institute for Human-Machine Communication, Technische Universität MünchenMaryam BABAEE, Dept. of Artificial Intelligence, Faculty of Computer Engineering, University of IsfahanDaniel MERGET, Institute for Human-Machine Communication, Technische Universität MünchenPhilipp TIEFENBACHER, Institute for Human-Machine Communication, Technische Universität MünchenGerhard RIGOLL, Institute for Human-Machine Communication, Technische Universität München
ARS-P18.6 – MULTIMEDIA RETRIEVAL VIA DEEP LEARNING TO RANKXueyi ZHAO, Zhejiang UniversityXi LI, Zhejiang UniversityZhongfei ZHANG, Zhejiang University
ARS-P3: Biometric Applications Monday, 16:30-18:30POSTER Room: POSTER CSession Chair(s): Patrizio CAMPISI, Università degli Studi Roma TRE
ARS-P3.1 – COMMON SPARSE REPRESENTATION-BASED ROBUST MULTIMODAL BIOMETRICS RECOGNITIONHeng ZHANG, University Of Maryland, College ParkVishal PATEL, University of Maryland Institute for Advanced Computer StudiesRama CHELLAPPA, University Of Maryland, College Park
«
«
88 | ICIP 2015 – Technical Program
ARS-P3.2 – ORTHOGONAL SELF-GUIDED SIMILARITY PRESERVING PROJECTIONSXiaozhao FANG, Bio-Computing Research Center, Shenzhen Graduate School, Harbin Institute of TechnologyYong XU, Bio-Computing Research Center, Shenzhen Graduate School, Harbin Institute of TechnologyZheng ZHANG, Bio-Computing Research Center, Shenzhen Graduate School, Harbin Institute of TechnologyZhihui LAI, College of Computer Science and Software Engineering, Shenzhen UniversityLinlin SHEN, College of Computer Science and Software Engineering, Shenzhen University
ARS-P3.3 – SUBJECT IDENTIFICATION BASED ON EEG RESPONSES TO VIDEO STIMULIPhilip DAVIS, New Mexico State UniversityCharles CREUSERE, New Mexico State UniversityJim KROGER, New Mexico State University
ARS-P3.4 – SEMANTICS CONSTRAINED DICTIONARY LEARNING FOR SIGNER-INDEPENDENT SIGN LANGUAGE RECOGNITIONFang YIN, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute ofXiujuan CHAI, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute ofYu ZHOU, Institute of Information Engineering, Chinese Academy of SciencesXilin CHEN, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS)
ARS-P3.5 – VALIDATION AND RELIABILITY OF THE DISCRIMINATIVE POWER OF GEOMETRIC WOOD LOG END FEATURES Rudolf SCHRAML, University of SalzburgAlexander PETUTSCHNIGG, University of Applied Sciences SalzburgAndreas UHL, University of Salzburg
ARS-P3.6 – LANDMARK-BASED FISHER VECTOR REPRESENTATION FOR VIDEO-BASED FACE VERIFICATIONJun-Cheng CHEN, University of Maryland College ParkVishal M . PATEL, University of Maryland College ParkRama CHELLAPPA, University of Maryland College Park
ARS-P31: Optical Flow and Motion Estimation Monday, 16:30-18:30POSTER Room: POSTER DSession Chair(s): Gaurav SHARMA, University of Rochester
ARS-P31.1 – APPROXIMATION ORDER OF THE LAP OPTICAL FLOW ALGORITHMThierry BLU, The Chinese University of Hong KongPierre MOULIN, University of Illinois at Urbana ChampaignChristopher GILLIAM, The Chinese University of Hong Kong
ARS-P31.2 – IMPROVED SPECULAR REGIONS LOCALIZATION AND OPTICAL-FLOW BASEDMOTION ESTIMATION VIA JOINT PROCESSINGAhmed ELLIETHY, University of RochesterGaurav SHARMA, University of Rochester
ICIP 2015 – Technical Program | 89
ARS-P31.3 – RATE-DISTORTION OPTIMIZED OPTICAL FLOW ESTIMATIONSean YOUNG, UNSWDavid TAUBMAN, UNSW
ARS-P31.4 – SUPERPIXEL MATCHING-BASED DEPTH PROPAGATION FOR 2D-TO-3D CONVERSION WITH JOINT BILATERAL FILTERINGCheolkon JUNG, Xidian UniversityJiji CAI, Xidian University
ARS-P31.5 – A HYBRID MOTION ESTIMATION TECHNIQUE FOR FISHEYE VIDEO SEQUENCES BASED ON EQUISOLID RE-PROJECTIONAndrea EICHENSEER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Michel BÄTZ, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Jürgen SEILER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)André KAUP, Friedrich-Alexander University Erlangen-Nürnberg (FAU)
ARS-P31.6 – MOTION ESTIMATION VIA HIERARCHICAL BLOCK MATCHING AND GRAPH CUTAmin ZHENG, Hong Kong University of Science and TechnologyYuan YUAN, Hong Kong University of Science and TechnologySunil Prasad JAISWAL, Hong Kong University of Science and TechnologyOscar C . AU, Hong Kong University of Science and Technology
ARS-P7: Face and Gesture I Monday, 16:30-18:30POSTER Room: POSTER HSession Chair(s): Janusz KONRAD, Boston University
ARS-P7.1 – A ROBUST GESTURE RECOGNITION USING HAND LOCAL DATA AND SKELETON TRAJECTORY .Edwin ESCOBEDO CARDENAS, FEDERAL UNIVERSITY OF OURO PRETOGuillermo CAMARA CHAVEZ, FEDERAL UNIVERSITY OF OURO PRETO
ARS-P7.2 – MAXIMUM ENTROPY REGULARIZED GROUP COLLABORATIVE REPRESENTATION FOR FACE RECOGNITIONZhong ZHAO, Sun Yat-sen UniversityGuocan FENG, Sun Yat-sen UniversityLifang ZHANG, Sun Yat-sen UniversityJiehua ZHU, Georgia Southern University
ARS-P7.3 – PARETO-OPTIMAL DISCRIMINANT ANALYSISFelix JUEFEI-XU, Carnegie Mellon UniversityMarios SAVVIDES, Carnegie Mellon University
ARS-P7.4 – FACIAL LANDMARK DETECTION VIA CASCADE MULTI-CHANNEL CONVOLUTIONAL NEURAL NETWORKHou QIQI, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong UniversityWang JINJUN, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong UniversityCheng LELE, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong UniversityGong YIHONG, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
90 | ICIP 2015 – Technical Program
ARS-P7.5 – FACIAL POINT DETECTION USING CONVOLUTIONAL NEURAL NETWORKS TRANSFERRED FROM A HETEROGENEOUS TASKTakayoshi YAMAsh*tA, Chubu UniversityTaro WATASUE, Tome R&DYuji YAMAUCHI, Chubu UniversityHironobu FUJIYOSHI, Chubu University
ARS-P7.6 – FACIAL POINT DETECTION BASED ON A CONVOLUTIONAL NEURAL NETWORK WITH OPTIMAL MINI-BATCH PROCEDURETakayoshi YAMAsh*tA, Chubu UniversityMasatoshi KIMURA, Chubu UniversityYuji YAMAUCHI, Chubu UniversityHironobu FUJIYOSHI, Chubu University
ARS-P50: Face and Gesture II Monday, 16:30-18:30POSTER Room: POSTER GSession Chair(s): Janusz KONRAD, Boston University
ARS-P50.1 – WHOLE SPACE SUBCLASS DISCRIMINANT ANALYSIS FOR FACE RECOGNITIONBappaditya MANDAL, Institute for Infocomm Research, A*STARLiyuan LI, Institute for Infocomm Research, A*STARVijay CHANDRASEKHAR, Institute for Infocomm Research, A*STARJoo Hwee LIM, Institute for Infocomm Research, A*STAR
ARS-P50.2 – FAST AND EXACT BI-DIRECTIONAL FITTING OF ACTIVE APPEARANCE MODELSJean KOSSAIFI, Imperial College LondonGeorgios TZIMIROPOULOS, Imperial College LondonMaja PANTIC, Imperial College London
ARS-P50.3 – TWO-LEVEL MULTI-TASK METRIC LEARNING WITH APPLICATION TO MULTI-CLASSIFICATIONXuewu ZHANG, Shenzhen Graduate School, Peking UniversityHong LIU, Shenzhen Graduate School, Peking UniversityPingping WU, Shenzhen Graduate School, Peking University
ARS-P50.4 – HAND AND OBJECT SEGMENTATION FROM RGB-D IMAGES FOR INTERACTION WITH PLANAR SURFACESHenrique WEBER, Federal University of Rio Grande do SulClaudio Rosito JUNG, Federal University of Rio Grande do SulDan GELB, HP Palo Alto
ARS-P50.5 – LEVERAGING SHAPE AND DEPTH IN USER AUTHENTICATION FROM IN-AIR HAND GESTURESJonathan WU, Boston UniversityJames CHRISTIANSON, Boston UniversityJanusz KONRAD, Boston UniversityPrakash ISHWAR, Boston University
ARS-P50.6 – UTILIZING THE BEZIER DESCRIPTORS FOR HAND GESTURE RECOGNITIONOmer Rashid AHMAD, University of MagdeburgAyoub AL-HAMADI, University of Magdeburg
ICIP 2015 – Technical Program | 91
ARS-P6: Edge and Shape Detection Monday, 16:30-18:30POSTER Room: POSTER FSession Chair(s): A .N . RAJAGOPALAN, IIT Madras
ARS-P6.1 – CANNYLINES: A PARAMETER-FREE LINE SEGMENT DETECTORXiaohu LU, School of Remote Sensing and Information EngineeringJian YAO, School of Remote Sensing and Information Engineering, Wuhan UniversityKai LI, School of Remote Sensing and Information Engineering, Wuhan UniversityLi LI, School of Remote Sensing and Information Engineering, Wuhan University
ARS-P6.2 – ELLIPSE-SPECIFIC FITTING BY RELAXING THE 3L CONSTRAINTS WITH SEMIDEFINITE PROGRAMMINGJiangpeng RONG, Peking UniversitySen YANG, Peking UniversityXiang MEI, Peking UniversityXianghua YING, Peking UniversityShiyao HUANG, Peking UniversityHongbin ZHA, Peking University
ARS-P6.3 – TAPPING MOTION BLUR FOR ROBUST NORMAL ESTIMATION OF PLANAR SCENESSubeesh VASU, INDIAN INSTITUTE OF TECHNOLOGY MADRASA .N . RAJAGOPALAN, INDIAN INSTITUTE OF TECHNOLOGY MADRASGunasekaran SEETHARAMAN, AFRL/RIEA
ARS-P6.4 – EDGE DETECTION METHOD OF GAUSSIAN BLOCK DISTANCEJia DI, Liaoing Technical UniversityXiao CHENG-LONG, School of software, Liaoing Technical University, Liaoning, ChinaSun JIN-GUANG, School of Electronic and Information Engineering, Liaoing Technical University
ARS-P6.5 – ROBUST STATISTICAL SHAPE ANALYSIS BASED ON THE TANGENT SHAPE SPACEMichel ABBOUD, UEB, École Nationale d’Ingénieurs de Brest (ENIB)Abdesslam BENZINOU, UEB, École Nationale d’Ingénieurs de Brest (ENIB)Kamal NASREDDINE, UEB, École Nationale d’Ingénieurs de Brest (ENIB)Mustapha JAZAR, LaMA-Liban, Lebanese University
ARS-P6.6 – TEMPLATE-BASED STATISTICAL SHAPE MODELLING ON DEFORMATION SPACEGirum DEMISSE, University of LuxembourgDjamila AOUADA, University of LuxembourgBjorn OTTERSTEN, University of Luxembourg
ARS-P9: Face Processing Monday, 16:30-18:30POSTER Room: POSTER ESession Chair(s): Mohsen ARDABILIAN, École Centrale de Lyon
ARS-P9.1 – L1-GRASSMANN MANIFOLDS FOR ROBUST FACE RECOGNITIONMatthew JOHNSON, Rochester Institute of TechnologyAndreas SAVAKIS, Rochester Institute of Technology
92 | ICIP 2015 – Technical Program
ARS-P9.2 – REFLECTANCE SPECTRA BASED SKIN AND NON-SKIN CLASSIFICATIONWei CHEN, École Centrale de LyonMohsen ARDABILIAN, École Centrale de LyonAbdelmalek ZINE, École Centrale de Lyon
ARS-P9.3 – FACIAL AGE ESTIMATION VIA EXTENDED CURVATURE GABOR FILTERJiwhan KIM, Korea Advanced Institute of Science and TechnologyDongyoon HAN, Korea Advanced Institute of Science and TechnologySungryull SOHN, Electronics and Telecommunications Research InstituteJunmo KIM, Korea Advanced Institute of Science and Technology
ARS-P9.4 – CROSS-POSE COLOR FACIAL EXPRESSION RECOGNITION USING TRANSDUCTIVE TRANSFER LINEAR DISCRIMINAT ANALYSISWenming ZHENG, Southeast UniversityXiaoyan ZHOU, Nanjing University of Information Science and Technology
ARS-P9.5 – FACIAL LANDMARK DETECTION VIA POSE-INDUCED AUTO-ENCODER NETWORKSYu CHEN, Nanjing University of Science and TechnologyWei LUO, Nanjing University of Science and TechnologyJian YANG, Nanjing University of Science and Technology
ARS-P9.6 – FACE DETECTION AND LANDMARK LOCALIZATION USING BILAYER TREE STRUCTURED MODELGee-Sern HSU, National Taiwan University of Science and TechnologyKai-Hsiang CHANG, National Taiwan University of Science and TechnologyShih-Chieh HUANG, National Taiwan University of Science and TechnologyShang-Luen CHUNG, National Taiwan University of Science and Technology
COM-P7: Video Streaming Monday, 16:30-18:30POSTER Room: POSTER OSession Chair(s): Yago SANCHEZ, Fraunhofer HHI
COM-P7.1 – AN EXTENSION TO THE PRO-MPEG COP3 CODES FOR UNEQUAL ERROR PROTECTION OF REAL-TIME VIDEO TRANSMISSIONCésar DÍAZ, Grupo de Tratamiento de Imágenes - Universidad Politécnica de MadridJulián CABRERA, Grupo de Tratamiento de Imágenes - Universidad Politécnica de MadridFernando JAUREGUIZAR, Grupo de Tratamiento de Imágenes - Universidad Politécnica de MadridNarciso GARCÍA, Grupo de Tratamiento de Imágenes - Universidad Politécnica de Madrid
COM-P7.2 – COMPRESSED DOMAIN VIDEO PROCESSING FOR TILE BASED PANORAMIC STREAMING USING HEVCYago SANCHEZ DE LA FUENTE, Fraunhofer HHIRobert SKUPIN, Fraunhofer HHIThomas SCHIERL, Fraunhofer HHI
COM-P7.3 – PREDICTIVE PREFETCHING FOR MPEG DASH OVER LTE NETWORKSTianyi XU, InterDigital Communications, IncLiangping MA, InterDigital Communications, Inc
ICIP 2015 – Technical Program | 93
COM-P7.4 – UNEQUAL ERROR PROTECTION FOR REAL-TIME VIDEO STREAMING USING EXPANDING WINDOW REED-SOLOMON CODEYufeng GENG, Peking UniversityXinggong ZHANG, Peking UniversityChao ZHOU, HuaweiZongming GUO, Peking University
COM-P7.5 – IN-NETWORK VIEW RE-SAMPLING FOR INTERACTIVE FREE VIEWPOINT VIDEO STREAMINGLaura TONI, EPFLGene CHEUNG, National Insitute of InformaticsPascal FROSSARD, EPFL
COM-P7.6 – A FAIRNESS-AWARE SMOOTH RATE ADAPTATION APPROACH FOR DYNAMIC HTTP STREAMINGLi LIU, Peking UniversityChao ZHOU, HuaiWeiXinggong ZHANG, Peking UniversityZongming GUO, Peking University
ELI-P4: Detection and Classification Monday, 16:30-18:30POSTER Room: POSTER ASession Chair(s): Michael H .F . WILKINSON, University of Groningen
ELI-P4.1 – MULTI-LOOK PROCESSING OF HIGH-RESOLUTION SAS DATA FOR IMPROVED TARGET DETECTION PERFORMANCEDavid WILLIAMS, NATO STO Centre for Maritime Research and Experimentation (CMRE)Alan HUNTER, University of Bath
ELI-P4.2 – LEARNING OCCLUSION PATTERNS USING SEMANTIC PHRASES FOR OBJECT DETECTIONLiu JINDE, Institute of Automation, Chinese Academy of SciencesHuang KAIQI, Institute of Automation, Chinese Academy of SciencesTan TIENIU, Institute of Automation, Chinese Academy of Sciences
ELI-P4.3 – IMPROVING BACKGROUND ESTIMATION FOR FAINT ASTRONOMICAL OBJECT DETECTIONPaul TEENINGA, University of GroningenUgo MOSCHINI, University of GroningenScott TRAGER, University of GroningenMichael H .F . WILKINSON, University of Groningen
ELI-P4.4 – AUTOMATIC DETECTION OF MARTIAN DUST STORMS FROM HETEROGENEOUS DATA BASED ON DECISION LEVEL FUSIONKeisuke MAEDA, Hokkaido UniversityTakahiro OGAWA, Hokkaido UniversityMiki HASEYAMA, Hokkaido University
94 | ICIP 2015 – Technical Program
ELI-P4.5 – MULTI-INSTANCE LEARNING VIA INSTANCE-BASED AND BAG-BASED REPRESENTATION TRANSFORMATIONSLiming YUAN, School of Computer and Communication Engineering,Tianjin University of TechnologyLu ZHAO, School of Computer and Information Engineering,Tianjin Chengjian UniversityHaixia XU, School of Computer and Communication Engineering, Tianjin University of Technology
ELI-P4.6 – REGULARIZATION OF DEEP NEURAL NETWORKS USING A NOVEL COMPANION OBJECTIVE FUNCTIONWeichen SUN, Beijing University of Posts and TelecommunicationsFei SU, Beijing University of Posts and Telecommunications
IFS-O1: Forensic Video and Surveillance Monday, 16:30-18:30LECTURE Room: 205CSession Chair(s): Touradj EBRAHIMI, EPFL
16:30 IFS-O1.1 – ABNORMAL EVENT DETECTION VIA ADAPTIVE CASCADE DICTIONARY LEARNINGHui WEN, Beijing Key Laboratory of IOT, Institute of Information Engineering, CASShiming GE, Beijing Key Laboratory of IOT, Institute of Information Engineering, CASShuixian CHEN, Beijing Key Laboratory of IOT, Institute of Information Engineering, CASHongtao WANG, Beijing Key Laboratory of IOT, Institute of Information Engineering, CASLimin SUN, Beijing Key Laboratory of IOT, Institute of Information Engineering, CAS
16:50 IFS-O1.2 – CBRA: COLOR-BASED RANKING AGGREGATION FOR PERSON RE-IDENTIFICATIONRaphael PRATES, Universidade Federal de Minas GeraisWilliam Robson SCHWARTZ, Universidade Federal de Minas Gerais
17:10 « IFS-O1.3 – EXPLOITING MULTIPLE DETECTIONS TO LEARN ROBUST BRIGHTNESS TRANSFER FUNCTIONS IN RE-IDENTIFICATION SYSTEMSAmran BHUIYAN, Istituto Italiano di Tecnologia Alessandro PERINA, Istituto Italiano di Tecnologia Vittorio MURINO, Istituto Italiano di Tecnologia
17:30 IFS-O1.4 – IMPACT OF MINI-DRONE BASED VIDEO SURVEILLANCE ON INVASION OF PRIVACYPavel KORSHUNOV, EPFLMargherita BONETTO, University of TriesteTouradj EBRAHIMI, EPFLGiovanni RAMPONI, University of Trieste
17:50 IFS-O1.5 – PREDICTIVE MULTIPLE MOTION FIELDS FOR TRAJECTORY COMPLETION: APPLICATION TO SURVEILLANCE SYSTEMS .Manya AFONSO, Instituto Superior Tecnico, University of Lisbon, PortugalJacinto NASCIMENTO, Instituto Superior Tecnico, University of Lisbon
18:10 IFS-O1.6 – TEXTURE-BASED VESSEL CLASSIFIER FOR ELECTRO-OPTICAL SATELLITE IMAGERYVirginia FERNANDEZ ARGUEDAS, European Commission - Joint Research Centre
ICIP 2015 – Technical Program | 95
SNT-S3: Show & Tell III Monday, 16:30-18:30SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S3.1 – SHAPE PRIOR IMAGE SEGMENTATION AND DISOCCLUSIONFrederick PARK, Whittier CollegeIn this demonstration we will use a cliques based shape prior incorporated into a polygonal implementation of the Mumford-Shah (MS) functional for image segmentation and disocclusion . The demo consists of 2 parts where we will show curve evolution from the proposed method . Part 1 is a segmentation example while part 2 involves disocclusion .
SNT-S3.2 – IMAGE CIPHERING TO ENSURE PRIVACY ON OPEN IMAGE-SHARING PLATFORMSGaetan LE GUELVOUIT, B-Com, Digital Trust & Identity LabsKun HE, B-COMCyrielle FERON, B-COMChristophe BIDAN, B-COMWe present in this demonstration an application that gives user empowerment and photo privacy controls on image-sharing services . It features an image-ciphering algorithm with the ability to be robust to lossy compression (e .g . JPEG), and a key management server, which controls access .
SNT-S3.3 – A COMPARISON OF ITERATIVE COMPRESSIVE SENSING RECOVERY ALGORITHMSChris METZLER, Rice UniveristyWe compare various iterative compressive sensing recovery algorithms across multiple iterations . We demonstrate how our denoising-based approach serves to regularize intermediate solutions .
SNT-S3.4 – DEEP STRUCTURED LEARNING FOR MASS SEGMENTATION IN MAMMOGRAMSNeeraj DHUNGEL, University of Adelaide In this demonstration, we will present a novel method for segmentation of breast masses from mammograms using deep learning and structured prediction . We can see that combining deep learning with the structured predictions models using CRF and SSVM produces state of the art result in segmentation of mass in mammograms from publicly available datasets .
SS8-O1: Big Data Processing and Analysis for Film and Media Production Monday, 16:30-18:30LECTURE Room: 205BSession Chair(s): Anastasios TEFAS, Aristotle University of Thessaloniki
16:30 SS8-O1.5 – COMBINED 2D AND 3D WEB-BASED VISUALISATION OF ON-SET BIG MEDIA DATAAlun EVANS, Universitat Pompeu FabraJavi AGENJO, Universitat Pompeu FabraJosep BLAT, Universitat Pompeu Fabra
16:50 SS8-O1.2 – KERNEL MATRIX TRIMMING FOR IMPROVED KERNEL K-MEANS CLUSTERINGNikolaos TSAPANOS, Aristotle University of ThessalonikiAnastasios TEFAS, Aristotle University of ThessalonikiNikolaos NIKOLAIDIS, Aristotle University of ThessalonikiIoannis PITAS, Aristotle University of Thessaloniki
96 | ICIP 2015 – Technical Program
17:10 SS8-O1.4 – QUALITY ASSURANCE IN LARGE COLLECTIONS OF VIDEO SEQUENCESLukas POLOK, FIT, Brno University of TechnologyLukas KLICNAR, Brno University of Technology, Faculty of Information TechnologyVitezslav BERAN, Brno University of Technology, Faculty of Information Technology
17:30 SS8-O1.3 – COVERAGE EVALUATION OF CAMERA NETWORKS FOR FACILITATING BIG-DATA MANAGEMENT IN FILM PRODUCTIONEvren IMRE, University of SurreyAdrian HILTON, University of Surrey
17:50 « SS8-O1.1 – MULTI-MODAL BIG-DATA MANAGEMENT FOR FILM PRODUCTIONHansung KIM, University of SurreySimon PABST, Double Negative Ltd.Justin SNEDDON, Double Negative Ltd.Ted WAINE, Double Negative Ltd.Jeff CLIFFORD, Double Negative Ltd.Adrian HILTON, University of Surrey
TEC-P10: Image Recovery and Enhancement Monday, 16:30-18:30POSTER Room: POSTER NSession Chair(s): Ricardo DE QUEIROZ, Universidade de Brasilia
TEC-P10.1 – EXAMPLE-BASED ENHANCEMENT OF DEGRADED VIDEOEdson Mintsu HUNG, Universidade de BrasiliaDiogo GARCIA, Universidade de BrasiliaRicardo DE QUEIROZ, Universidade de Brasilia
TEC-P10.2 – AUTOMATIC CONTRAST ENHANCEMENT BY VARIATIONAL MINIMAX OPTIMIZATIONYongjian YU, Varian Medical SystemsJue WANG, Union College
TEC-P10.3 – DARK IMAGE ENHANCEMENT BASED ON PAIRWISE TARGET CONTRAST AND MULTI-SCALE DETAIL BOOSTINGYoungbae KIM, Korea UniversityYeong Jun KOH, Korea UniversityChulwoo LEE, Korea UniversitySehoon KIM, Samsung ElectronicsChang-Su KIM, Korea University
TEC-P10.4 – EFFICIENT REGRESSION PRIORS FOR REDUCING IMAGE COMPRESSION ARTIFACTSRasmus ROTHE, ETH ZurichRadu TIMOFTE, ETH ZurichLuc VAN GOOL, ETH Zurich
TEC-P10.5 – FAST SINGLE IMAGE DEHAZING WITH DOMAIN TRANSFORMATION-BASED EDGE-PRESERVING FILTER AND WEIGHED QUADTREE SUBDIVISIONBoyang QIN, Beijing University of Posts and TelecommunicationsZhitong HUANG, Beijing University of Posts and TelecommunicationsFanxiang ZENG, Beijing University of Posts and TelecommunicationsYuefeng JI, Beijing University of Posts and Telecommunications
«
«
ICIP 2015 – Technical Program | 97
TEC-P10.6 – GRADIENT-DOMAIN IMAGE DECOMPOSITION FOR IMAGE RECOVERYMakoto WATANABE, The University of KitakyushuSeisuke KYOCHI, The University of KitakyushuShunsuke ONO, Tokyo Institute of Technology
TEC-P13: Image Restoration and Denoising Monday, 16:30-18:30POSTER Room: POSTER MSession Chair(s): Frédéric SUR, Université de Lorraine
TEC-P13.1 – IMAGE DEBLOCKING USING GROUP-BASED SPARSE REPRESENTATION AND QUANTIZATION CONSTRAINT PRIORJian ZHANG, Peking UniversitySiwei MA, Peking UniversityYongbing ZHANG, Tsinghua UniversityWen GAO, Peking University
TEC-P13.2 – A BAYESIAN ADAPTIVE WEIGHTED TOTAL GENERALIZED VARIATION MODEL FOR IMAGE RESTORATIONZhenbo LU, University of Science and Technology of ChinaHouqiang LI, University of Science and Technology of ChinaWeiping LI, University of Science and Technology of China
TEC-P13.3 – SECOND ORDER MUMFORD-SHAH MODEL FOR IMAGE DENOISINGJinming DUAN, University of NottinghamYuchun DING, University of NottinghamJie YANG, Shanghai Jiaotong UniversityZhenkuan PAN, Qingdao UniversityLi BAI, University of Nottingham
TEC-P13.4 – PSF ACCURACY MEASURE FOR EVALUATION OF BLUR ESTIMATION ALGORITHMSJan KOTERA, UTIA AV CRBarbara ZITOVA, UTIA AV CRFilip SROUBEK, UTIA AV CR
TEC-P13.5 – AN A-CONTRARIO APPROACH TO QUASI-PERIODIC NOISE REMOVALFrédéric SUR, Université de Lorraine
TEC-P30: Image Denoising and Recovery Monday, 16:30-18:30POSTER Room: POSTER LSession Chair(s): Takamichi MIYATA, Chiba Institute of Technology
TEC-P30.1 – SUPER RESOLUTION RECONSTRUCTION USING GRAPH LAPLACIAN PENALIZATIONJun BAI, Institute of Automation, Chinese Academy of SciencesLimin SHI, Institute of Automation, Chinese Academy of SciencesBangyu LI, Institute of Automation, Chinese Academy of SciencesShiming XIANG, Institute of Automation, Chinese Academy of SciencesChunhong PAN, Institute of Automation, Chinese Academy of Sciences
«
98 | ICIP 2015 – Technical Program
TEC-P30.2 – LOW-RANK REGULARIZED COLLABORATIVE FILTERING FOR IMAGE DENOISINGMansour NEJATI, Isfahan University of TechnologyShadrokh SAMAVI, Isfahan University of TechnologyS .M .Reza SOROUSHMEHR, University of Michigan, Ann ArborKayvan NAJARIAN, University of Michigan, Ann Arbor
TEC-P30.3 – AUGMENTED LAGRANGIAN WITHOUT ALTERNATING DIRECTIONS:PRACTICAL ALGORITHMS FOR INVERSE PROBLEMS IN IMAGINGRahul MOURYA, University Jean Monnet, St EtienneLoic DENIS, University Jean Monnet, St-ÉtienneÉric THIÉBAUT, Centre de Recherche Astrophysique de Lyon CRAL / CNRS-UMR 5574, Observatoire de LyonJean-marie BECKER, University Jean Monnet, St Etienne
TEC-P30.4 – A MAXIMAL INTEREST-POINT STRATEGY APPLIED TO IMAGE ENHANCEMENT WITH EXTERNAL PRIORSOren KATZIR, Technion - Israel Institute of TechnologyGuy GILBOA, Technion - Israel Institute of Technology
TEC-P30.5 – INTER-CHANNEL RELATION BASED VECTORIAL TOTAL VARIATION FOR COLOR IMAGE RECOVERYTakamichi MIYATA, Chiba Institute of Technology
TEC-P8: Image and Video Restoration and Enhancement Monday, 16:30-18:30POSTER Room: POSTER JSession Chair(s): Sohail DIANAT, Rochester Institute of Technology
TEC-P8.1 – ANALYSIS ON SPECTRAL EFFECTS OF DARK-CHANNEL PRIOR FOR HAZE REMOVALYuxiang SHEN, McMaster UniversityXiaolin WU, McMaster UniversityXiaowei DENG, McMaster University
TEC-P8.2 – MOTION DRIVEN TONAL STABILIZATIONOriel FRIGO, Université Paris DescartesNeus SABATER, TechnicolorJulie DELON, Université Paris DescartesPierre HELLIER, Technicolor
TEC-P8.3 – SPECULAR REFLECTION REMOVAL USING LOCAL STRUCTURAL SIMILARITY AND CHROMATICITY CONSISTENCYYongqiang ZHAO, Northwestern Polytechnical UniversityQunnie PENG, Northwestern Polytechnical Universityji*ze XUE, Northwestern Polytechnical UniversitySeong G . KONG, Sejong University
TEC-P8.4 – RECOVERING INTRINSIC IMAGES FROM IMAGE SEQUENCES USING TOTAL VARIATION MODELSXiaohua XIE, Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesWenyong GONG, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, ChinaMinglun GONG, Department of Computer Science, Memorial University of NewfoundlandTieru WU, School of Mathematics, Jilin University, China
«
ICIP 2015 – Technical Program | 99
TEC-P8.5 – SUPERPIXEL BASED PATCH MATCH FOR DIFFERENTLY EXPOSED IMAGES WITHMOVING OBJECTS AND CAMERA MOVEMENTSJinghong ZHENG, Institute for Infocomm ResearchZhengguo LI, Institute for Infocomm Research
TEC-P8.6 – SINGLE UNDERWATER IMAGE ENHANCEMENT USING DEPTH ESTIMATION BASED ON BLURRINESSYan-Tsung PENG, University of California, San DiegoXiangyun ZHAO, University of California, San DiegoPamela COSMAN, University of California, San Diego
TEC-P9: Image Enhancement and Segmentation Monday, 16:30-18:30POSTER Room: POSTER KSession Chair(s): Mary COMER, Purdue University
TEC-P9.1 – A MOTION-TEXTURE AWARE DENOISING FOR ECONOMIC HARDWARE DESIGNZheng YUAN, Real Communications IncWujun CHEN, Realtek Semiconductor GroupJun XIN, Real Communications IncLingzhi LIU, Real Communications IncWeimin ZENG, Real Communications IncEric CHAI, Real Communications IncDapeng WU, University of Florida
TEC-P9.2 – HIGH DYNAMIC RANGE MAP ESTIMATION VIA FULLY CONNECTED RANDOM FIELDS WITH STOCHASTIC CLIQUESFrancis LI, University of WaterlooMohammad Javad SHAFIEE, University of WaterlooAudrey CHUNG, University of WaterlooBrendan CHWYL, University of WaterlooFarnoud KAZEMZADEH, University of WaterlooAlexander WONG, University of WaterlooJohn ZELEK, University of Waterloo
TEC-P9.3 – CONTRAST ENHANCEMENT OF BACK-LIGHT IMAGES VIA A REGIONAL RANK-1 CONSTRAINTJa-Won SEO, Samsung ElectronicsSeong Dae KIM, Korea Advanced Institute of Science and Technology (KAIST)
TEC-P9.4 – CHANNEL DETECTION IN MICROSCOPE IMAGES OF MATERIALS USING MARKEDPOINT PROCESS MODELINGDae Woo KIM, Purdue UniversityMary COMER, Purdue University
TEC-P9.5 – HALO CONTROL FOR LHE BASED LOCAL ADAPTIVE TONE MAPPINGYuta KIMURA, Hokkaido universityMasayuki IKEBE, Hokkaido university
TEC-P9.6 – DETECTING SPECULAR HIGHLIGHTS IN DERMATOLOGICAL IMAGESAli MADOOEI, Simon Fraser UniversityMark S . DREW, Simon Fraser University
«
100 | ICIP 2015 – Technical Program
CKTL-E: Banquet co*cktail Monday, 19:00-20:00SOCIAL EVENT Room: FOYER 2Session Chair(s): Paul FORTIER, Laval University
BQT-E: Banquet Monday, 20:00-23:00SOCIAL EVENT Room: 200ABSession Chair(s): André MORIN, Optelis Jean-Luc DUGELAY, Eurecom
ICIP 2015 – Technical Program | 101
TUESDAY SEPTEMBER 29
PLE-N2: Plenary – Advances in Computational Imaging Tuesday, 09:00-10:00PLENARY Room: 200ABSession Chair(s): Stéphane COULOMBE, École de technologie supérieure Kenneth ROSE, University of California
PresenterShree K . Nayar, T. C. Chang Professor of Computer Science, Columbia University
SummaryComputational imaging uses new optics to capture a coded image, and an appropriate algorithm to decode the captured image. This approach of manipulating images before there are recorded and processing recorded images before they are presented has three key benefits. First, it enables us to implement imaging functionalities that would be difficult, if not impossible, to achieve using traditional imaging. Second, it can be used to significantly reduce the hardware complexity of an imaging system. Lastly, under appropriate imaging conditions, it allows us to break the limits of traditional imaging. In this talk, I will show recent examples of cameras that demonstrate these benefits.
ARS-O2: Classification II Tuesday, 10:30-12:30LECTURE Room: 205BSession Chair(s): Jenny Benois-PINEAU, LaBRI
10:30 « ARS-O2.1 – SEMANTIC EMBEDDING SPACE FOR ZERO-SHOT ACTION RECOGNITIONXun XU, Queen Mary, University of LondonTimothy HOSPEDALES, Queen Mary, University of LondonShaogang GONG, Queen Mary, University of London
10:50 ARS-O2.2 – DEEP-PLANT: PLANT IDENTIFICATION WITH CONVOLUTIONAL NEURAL NETWORKSSue Han LEE, University of MalayaChee Seng CHAN, University of MalayaPaul WILKIN, Royal Botanic GardensPaolo REMAGNINO, Kingston University
11:10 ARS-O2.3 – BRUSHSTROKE BASED SPARSE HYBRID CONVOLUTIONAL NEURAL NETWORKS FOR AUTHOR CLASSIFICATION OF CHINESE INK-WASH PAINTINGSMeijun SUN, Tianjin UniversityDong ZHANG, Tianjin UniversityJinchang REN, University of StrathclydeZheng WANG, Tianjin UniversityJesse J JIN, Tianjin University
102 | ICIP 2015 – Technical Program
11:30 ARS-O2.4 – PRE-TRAINING CONVOLUTIONAL NEURAL NETWORKS: IS FINE-TUNE ALWAYS PREQUISITE?Yue HUANG, Xiamen UniversityRuiwen WU, Xiamen UniversityXinghao DING, Xiamen University
11:50 ARS-O2.5 – SEMI-SUPERVISED LEARNING BASED ON GROUP SPARSE FOR RELATIVE ATTRIBUTESHongxue YANG, Dalian University of TechnologyXiangwei KONG, Dalian University of TechnologyHaiyan FU, Dalian University of TechnologyMing LI, Dalian University of TechnologyGenping ZHAO, Harbin Engineering University
12:10 ARS-O2.6 – MULTI-CLASS WEATHER CLASSIFICATION ON SINGLE IMAGESZheng ZHANG, Beijing University of Posts and TelecommunicationsHuadong MA, Beijing University of Posts and Telecommunications
ARS-O5: Face Recognition I Tuesday, 10:30-12:30LECTURE Room: 205CSession Chair(s): Zheng-Hua TAN, Aalborg University
10:30 ARS-O5.1 – A ROBUST CONTOUR SAMPLING AND TENSOR-BASED APPROACH TO FACIAL BEARD AND MUSTACHE SHAPE SEGMENTATION AND MATCHINGKaranhaar SINGH, Carnegie Mellon UniversityKhoa LUU, Carnegie Mellon UniversityT . Hoang Ngan LE, Carnegie Mellon UniversityMarios SAVVIDES, Carnegie Mellon University
10:50 ARS-O5.2 – A FEATURE SUBTRACTION METHOD FOR IMAGE BASED KINSHIP VERIFICATION UNDER UNCONTROLLED ENVIRONMENTSXiaodong DUAN, Aalborg UniversityZheng-Hua TAN, Aalborg University
11:10 ARS-O5.3 – AN EFFICIENT FACE CLASSIFICATION METHOD BASED ON SHARED AND CLASS-SPECIFIC DICTIONARY LEARNINGJiuzhen LIANG, Jiangnan UniversityWenjing LI, Jiangnan UniversityQin WU, Jiangnan UniversityYuxuan ZHOU, Jiangnan UniversityXiuxiu XU, Jiangnan UniversityNianbing WANG, Jiangnan UniversityQi ZHOU, Jiangnan University
11:30 ARS-O5.4 – BOOSTING 3D LBP-BASED FACE RECOGNITION BY FUSING SHAPE AND TEXTURE DESCRIPTORS ON THE MESHClaudio TORTORICI, Khalifa University of Science Technology & ResearchNaoufel WERGHI, Khalifa University of Science Technology & ResearchStefano BERRETTI, University of Firenze
ICIP 2015 – Technical Program | 103
11:50 ARS-O5.5 – ENCODING AND DECODING LOCAL BINARY PATTERNS FOR HARSH FACE ILLUMINATION NORMALIZATIONFelix JUEFEI-XU, Carnegie Mellon UniversityMarios SAVVIDES, Carnegie Mellon University
12:10 ARS-O5.6 – FACE IMAGE ASSESSMENT LEARNED WITH OBJECTIVE AND RELATIVE FACE IMAGE QUALITIES FOR IMPROVED FACE RECOGNITIONHyung-Il KIM, Korea Advanced Institute of Science and Technology (KAIST)Seung Ho LEE, Korea Advanced Institute of Science and Technology (KAIST)Yong Man RO, Korea Advanced Institute of Science and Technology (KAIST)
ARS-P12: Foreground/Background Separation I Tuesday, 10:30-12:30POSTER Room: POSTER ASession Chair(s): Anthony VETRO, Mitsubishi Electric Research Labs (MERL)
ARS-P12.1 – REFLECTION REMOVAL USING DISPARITY AND GRADIENT-SPARSITY VIA SMOOTHING ALGORITHMTharatch SIRINUKULWATTANA, Korea Advanced Institute of Science and TechnologyGyeongmin CHOE, Korea Advanced Institute of Science and TechnologyIn So KWEON, Korea Advanced Institute of Science and Technology
ARS-P12.2 – MOVING CAMERA HUMAN ACTIVITY LOCALIZATION AND RECOGNITION WITH MOTIONPLANES AND MULTIPLE hom*oGRAPHIESKonstantinos AVGERINAKIS, Information and Technologies Institute - Centre for Research and Technology HellasKaterina ADAM, Information and Technologies Institute - Centre for Research and Technology HellasAlexia BRIASSOULI, Information and Technologies Institute - Centre for Research and Technology HellasIoannis KOMPATSIARIS, Information and Technologies Institute - Centre for Research and Technology Hellas
ARS-P12.3 – DEPTH-WEIGHTED GROUP-WISE PRINCIPAL COMPONENT ANALYSIS FOR VIDEO FOREGROUND/BACKGROUND SEPARATIONDong TIAN, Mitsubishi Electric Research Labs (MERL)Hassan MANSOUR, Mitsubishi Electric Research Labs (MERL)Anthony VETRO, Mitsubishi Electric Research Labs (MERL)
ARS-P12.4 – MULTIMODAL TOPIC MODELING BASED GEO-ANNOTATION FOR SOCIAL EVENT DETECTION IN LARGE PHOTO COLLECTIONSBin XU, Northeastern University, ChinaGuoliang FAN, Oklahoma State University
ARS-P12.5 – TOWARDS AUTOMATING VISUAL IN-FIELD MONITORING OF CROP HEALTHDavid GIBSON, University of BristolTilo BURGHARDT, University of BristolNeill CAMPBELL, University of BristolNishan CANAGARAJAH, University of Bristol
104 | ICIP 2015 – Technical Program
ARS-P12.6 – ROBUST AND FAST MOVING OBJECT DETECTION IN A NON-STATIONARY CAMERA VIA FOREGROUND PROBABILITY BASED SAMPLINGKimin YUN, Seoul National UniversityJin Young CHOI, Seoul National University
ARS-P13: Human Activity Recognition I Tuesday, 10:30-12:30POSTER Room: POSTER CSession Chair(s): Scott T . ACTON, University of Virginia
ARS-P13.1 – ACTIVITY RECOGNITION AND DETECTION WITH DISCRIMINATIVE PATCHES Ziyi LI, School of Computer and Control Engineering, University of Chinese Academy of SciencesLaiyun QING, School of Computer and Control Engineering, University of Chinese Academy of SciencesJun MIAO, Institute of Computing Technology, CAS
ARS-P13.2 – ENHANCED DEFORMABLE PART MODEL FOR PEDESTRIAN DETECTION VIA JOINT STATE INFERENCEXiao-Jiao MAO, Nanjing UniversityJiu-Yang ZHAO, Nanjing UniversityYu-Bin YANG, Nanjing UniversityNing LI, Nanjing University
ARS-P13.3 – CROWD MOTION MONITORING USING TRACKLET-BASED COMMOTION MEASUREHossein MOUSAVI, Istituto Italiano di TecnologiaMoin NABI, Istituto Italiano di TecnologiaHamed KIANI GALOOGAHI, Istituto Italiano di TecnologiaAlessandro PERINA, Istituto Italiano di TecnologiaVittorio MURINO, Istituto Italiano di Tecnologia
ARS-P13.4 – UGRASP: A UNIFIED FRAMEWORK FOR ACTIVITY RECOGNITION AND PERSON IDENTIFICATION USING GRAPH SIGNAL PROCESSINGTamal BATABYAL, University of VirginiaAndrea VACCARI, University of VirginiaScott T . ACTON, University of Virginia
ARS-P13.5 – TOWARDS PRIVACY-PRESERVING RECOGNITION OF HUMAN ACTIVITIESJi DAI, Boston UniversityBehrouz SAGHAFI, Boston UniversityJonathan WU, Boston UniversityJanusz KONRAD, Boston UniversityPrakash ISHWAR, Boston University
ARS-P13.6 – DETECTION OF PEDESTRIAN CROSSING ROADJoko HARIYONO, University of UlsanKang_Hyun JO, University of Ulsan
ARS-P48: Human Activity Recognition II Tuesday, 10:30-12:30POSTER Room: POSTER DSession Chair(s): Scott T . ACTON, University of Virginia
«
ICIP 2015 – Technical Program | 105
ARS-P48.1 – HUMAN ACTION RECOGNITION USING TIME-INVARIANT KEY-TRAJECTORIESDESCRIBING SPATIO-TEMPORAL SALIENT MOTIONJeong-Jik SEO, Korea Advanced Institute of Science and Technology (KAIST)Wissam J . BADDAR, Korea Advanced Institute of Science and Technology (KAIST)Dae Hoe KIM, Korea Advanced Institute of Science and Technology (KAIST)Yong Man RO, Korea Advanced Institute of Science and Technology (KAIST)
ARS-P48.2 – STRUCTURED FEATURE-GRAPH MODEL FOR HUMAN ACTIVITY RECOGNITIONWanru XU, Institute of Information Science, Beijing Jiaotong UniversityZhenjiang MIAO, Institute of Information Science, Beijing Jiaotong UniversityXiao-Ping ZHANG, Department of Electrical and Computer Engineering, Ryerson University
ARS-P48.3 – CROWD MODELING USING SOCIAL NETWORKSRima CHAKER, University of SharjahImran JUNEJO, University of SharjahZaher ALAGHBARI, University of Sharjah
ARS-P48.4 – TOWARDS DEFINING GROUPS AND CROWDS IN VIDEO USING THE ATOMIC GROUP ACTIONS DATASETRicky SETHI, Fitchburg State University
ARS-P48.5 – REAL-LIFE VIOLENT SOCIAL INTERACTION DETECTIONPaolo ROTA, University of TrentoNicola CONCI, University of TrentoNicu SEBE, University of TrentoJames M . REHG, Georgia Institute of Technology
ARS-P48.6 – CLASS-SPECIFIC SPARSE CODES FOR REPRESENTING ACTIVITIESSabanadesan UMAKANTHAN, Queensland University of TechnologySimon DENMAN, Queensland University of TechnologyClinton f*ckES, Queensland University of TechnologySridha SRIDHARAN, Queensland University of Technology
ARS-P49: Foreground/Background Separation II Tuesday, 10:30-12:30POSTER Room: POSTER BSession Chair(s): Anthony VETRO, Mitsubishi Electric Research Labs (MERL)
ARS-P49.1 – A NOVEL BACKGROUND SUBTRACTION APPROACH BASED ON MULTI LAYERED SELF-ORGANIZING MAPSGiorgio GEMIGNANI, Research Team, Hyera SoftwareAlessandro ROZZA, Research Team, Hyera Software
ARS-P49.2 – BACKGROUND MODELING IN VIDEOS REVISITED USING FINITE MIXTURES OF GENERALIZED GAUSSIANS AND SPATIAL INFORMATIONAissa BOULMERKA, École Nationale Supérieure en InformatiqueMohand Said ALLILI, Université du Québec en Outaouais
ARS-P49.3 – MULTIPLE FEATURES BASED SHARED MODELS FOR BACKGROUND SUBTRACTIONYingying CHEN, National Laboratory of Pattern Recognition, Institute of AutomationJinqiao WANG, National Laboratory of Pattern Recognition, Institute of AutomationHanqing LU, National Laboratory of Pattern Recognition, Institute of Automation
«
«
106 | ICIP 2015 – Technical Program
ARS-P49.4 – RECOVERING BACKGROUND REGIONS IN VIDEOS OF CLUTTERED URBAN SCENESIain RODGER, Heriot-Watt UniversityBarry CONNOR, ThalesNeil ROBERTSON, Heriot-Watt University
ARS-P49.5 – BACKGROUND SUBTRACTION FOR STATIC & MOVING CAMERAHasan SAJID, University of KentuckySen-Ching Samson CHEUNG, University of Kentucky
ARS-P49.6 – MULTI-TEMPORAL FOREGROUND DETECTION IN VIDEOSMariano TEPPER, Duke UniversityAlasdair NEWSON, Duke UniversityPablo SPRECHMANN, Courant Institute, New York UniversityGuillermo SAPIRO, Duke University
COI-O1: Tomographic Imaging Tuesday, 10:30-12:30LECTURE Room: 204ASession Chair(s): Yongyi YANG, Illinois Institute of Technology
10:30 COI-O1.1 – REGION BASED 4D TOMOGRAPHIC IMAGE RECONSTRUCTION: APPLICATION TO CARDIAC X-RAY CTGeert VAN EYNDHOVEN, Minds-Visionlab, University of AntwerpKees Joost BATENBURG, Centrum Wiskunde & Informatica, NL-1090 GB Amsterdam, The NetherlandsJan SIJBERS, iMinds-Visionlab, University of Antwerp
10:50 COI-O1.2 – DETERMINING FLUCTUATION IN BIO-NANOMACHINES FROM ELECTRONMICROSCOPY IMAGESYunye GONG, Cornell UniversityPeter DOERSCHUK, Cornell University
11:10 « COI-O1.3 – JOINT METAL ARTIFACT REDUCTION AND SEGMENTATION OF CT IMAGES USING DICTIONARY-BASED IMAGE PRIOR AND CONTINUOUS-RELAXED POTTS MODELPengchong JIN, Purdue UniversityDong Hye YE, Purdue UniversityCharles BOUMAN, Purdue University
11:30 COI-O1.4 – 4D NON-LOCAL MEANS POST-FILTERING FOR CARDIAC GATED SPECTChao SONG, Illinois Institute of TechnologyYongyi YANG, Illinois Institute of TechnologyWenyuan QI, Illinois Institute of TechnologyMiles WERNICK, Illinois Institute of TechnologyHendrik PRETORIUS, University of Massachusetts Medical SchoolMichael KING, University of Massachusetts Medical School
11:50 COI-O1.5 – PET IMAGE RECONSTRUCTION AND DENOISING ON HEXAGONAL LATTICESTabish SYED, IIIT HyderabadJayanthi SIVASWAMY, IIIT Hyderabad
12:10 COI-O1.6 – OPTICAL COHERENCE TOMOGRAPHY IMAGE SEGMENTATIONJinming DUAN, University of Nottingham
ICIP 2015 – Technical Program | 107
COM-P2: Image and Video Coding I Tuesday, 10:30-12:30POSTER Room: POSTER LSession Chair(s): Jana EHMANN, LG Electronics
COM-P2.1 – LOW-COMPLEXITY BLOCK SIZE DECISION FOR HEVC INTRA CODING USING BINARYIMAGE FEATURE DESCRIPTORSWalther GEUDER, Siemens Corporate TechnologyPeter AMON, Siemens Corporate TechnologyEckehard STEINBACH, Technische Universität München
COM-P2.2 – A REGULARIZATION APPROACH FOR BAYER RECONSTRUCTION IN LOSSY IMAGE CODING BY INVERSE DEMOSAICINGMasao YAMAGISHI, Tokyo Institute of TechnologySeisuke KYOCHI, The University of KitakyushuKeiichiro SHIRAI, Shinshu UniversityMasahiro OKUDA, The University of Kitakyushu
COM-P2.3 – HIGH-THROUGHPUT AND LOW-COMPLEXITY BINARY ARITHMETIC DECODER BASED ON LOGARITHMIC DOMAINQuanhe YU, Tsinghua UniversityXiaozhen ZHENG, Research Department, HiSilicon TechnologiesJianhua ZHENG, Research Department, HiSilicon TechnologiesYun HE, Tsinghua UniversityWei YU, Tsinghua UniversityDadong WANG, Tsinghua UniversityJunyou CHEN, Tsinghua UniversityYangyang XU, Tsinghua University
COM-P2.4 – ROTATE INTRA BLOCK COPY FOR STILL IMAGE CODINGZhengdong ZHANG, Massachusetts Institute of TechnologyVivienne SZE, Massachusetts Institute of Technology
COM-P2.5 – DEPENDENT RANDOM ACCESS POINT PICTURES IN HEVCMartin PETTERSSON, Ericsson ResearchRickard SJÖBERG, Ericsson ResearchJonatan SAMUELSSON, Ericsson Research
COM-P2.6 – RATE-DISTORTION EVALUATION FOR TWO-LAYER CODING SYSTEMSPhilippe HANHART, EPFLTouradj EBRAHIMI, EPFL
COM-P8: Image and Video Coding II Tuesday, 10:30-12:30POSTER Room: POSTER MSession Chair(s): Jana EHMANN, LG Electronics
COM-P8.1 – SHAPE ENCODING FOR EDGE MAP IMAGE COMPRESSIONDemetrios GEROGIANNIS, University of IoanninaChristophoros NIKOU, University of IoanninaLisimachos P . KONDI, University of Ioannina
108 | ICIP 2015 – Technical Program
COM-P8.2 – UNIVERSAL LOSSLESS CODING WITH RANDOM USER ACCESS: THE COST OF INTERACTIVITYAline ROUMY, INRIAThomas MAUGEY, INRIA
COM-P8.3 – RETINAL-INSPIRED FILTERING FOR DYNAMIC IMAGE CODINGEffrosyni DOUTSI, UNS, I3S laboratoire, CNRS, 4G-TechnologyLionel FILLATRE, UNS, I3S laboratoire, CNRSMarc ANTONINI, UNS, I3S laboratoire, CNRSJulien GAULMIN, 4G-Technology
COM-P8.4 – A DUAL BLOCK COORDINATE PROXIMAL ALGORITHM WITH APPLICATION TO DECONVOLUTION OF INTERLACED VIDEO SEQUENCESFeriel ABBOUD, Universite Paris-Est Marne-la-Vallee, LIGM UMR CNRS 8049Emilie CHOUZENOUX, Universite Paris-Est Marne-la-Vallee, LIGM UMR CNRS 8049Jean-Christophe PESQUET, Universite Paris-Est Marne-la-Vallee, LIGM UMR CNRS 8049Jean-Hugues CHENOT, Institut National de l’AudiovisuelLouis LABORELLI, Institut National de l’Audiovisuel
COM-P8.5 – LOSSLESS SCREEN CONTENT CODING IN HEVC BASED ON SAMPLE-WISE MEDIAN AND EDGE PREDICTIONVictor SANCHEZ, University of Warwick
COM-P3: Image and Video coding III Tuesday, 10:30-12:30POSTER Room: POSTER NSession Chair(s): Jana EHMANN, LG Electronics
COM-P3.1 – SPARSE LEAST-SQUARES PREDICTION FOR INTRA IMAGE CODINGLuis LUCAS, Instituto de TelecomunicaçõesNuno RODRIGUES, Instituto de TelecomunicaçõesCarla PAGLIARI, Instituto de TelecomunicaçõesEduardo A .B . DA SILVA, Instituto de TelecomunicaçõesSérgio FARIA, Instituto de Telecomunicações
COM-P3.2 – A MULTI-STANDARD INTERPOLATION HARDWARE SOLUTION FOR H .264 AND HEVCHenrique MAICH, Federal University of PelotasGuilherme PAIM, federal University of PelotasVladimir AFONSO, federal University of PelotasLuciano AGOSTINI, federal University of PelotasBruno ZATT, federal University of PelotasMarcelo PORTO, federal University of Pelotas
COM-P3.3 – CONTRIBUTIONS TO LOSSLESS CODING OF MEDICAL IMAGES USING MINIMUM RATE PREDICTORSJoão SANTOS, Instituto de TelecomunicaçõesAndré GUARDA, Instituto de TelecomunicaçõesNuno RODRIGUES, Instituto de TelecomunicaçõesSérgio FARIA, Instituto de Telecomunicações
«
«
ICIP 2015 – Technical Program | 109
COM-P3.4 – DATA RATE AND DYNAMIC RANGE COMPRESSION OF MEDICAL IMAGES: WHICH ONE GOES FIRST?Shahrukh ATHAR, University of WaterlooHojatollah YEGANEH, University of WaterlooZhou WANG, University of Waterloo
COM-P3.5 – FAST CU PARTITION DECISION USING MACHINE LEARNING FOR SCREEN CONTENT COMPRESSIONYao WANG, New York UniversityFanyi DUANMU, New York UniversityZhan MA, FutureWei Technologies Inc.
COM-P3.6 – OPTIMAL BIT ALLOCATION IN HEVC FOR REAL-TIME VIDEO COMMUNICATIONSMiaohui WANG, Chinese University of Hong KongKing Ngi NGAN, The Chinese University of Hong Kong
COM-P9: Image and Video coding IV Tuesday, 10:30-12:30POSTER Room: POSTER OSession Chair(s): Jana EHMANN, LG Electronics
COM-P9.1 – VLSI FRIENDLY FAST CU/PU MODE DECISION FOR HEVC INTRA ENCODING:LEVERAGING CONVOLUTION NEURAL NETWORKXianyu YU, Tsinghua UniversityZhenyu LIU, Tsinghua UniversityJunjie LIU, Tsinghua UniversityYuan GAO, Tsinghua UniversityDongsheng WANG, Tsinghua University
COM-P9.2 – ROI-BASED RATE CONTROL USING TILES FOR AN HEVC ENCODED VIDEO STREAMOVER A LOSSY NETWORKMarwa MEDDEB, Telecom ParisTechMarco CAGNAZZO, Telecom ParisTechBéatrice PESQUET-POPESCU, Telecom ParisTech
COM-P9.3 – 3 .975MW 18 .396GBPS 2R2W SRAM FOR SBAC CONTEXT MODEL OF HEVCLongshan DU, Tsinghua UniversityZhenyu LIU, Tsinghua University
COM-P9.4 – SHANNON-KOTELNIKOV MAPPINGS FOR SOFTCAST-BASED JOINT SOURCE-CHANNEL VIDEO CODINGMarco CAGNAZZO, Institut Mines-Telecom; Telecom-ParisTech; CNRS-LTCIMichel KIEFFER, L2S, CNRS-CentraleSupelec-Univ Paris-Sud
COM-P9.5 – PIXEL-GRAIN PREDICTION AND K-ORDER UEG-RICE ENTROPY CODING ORIENTED LOSSLESS FRAME MEMORY COMPRESSION FOR MOTION ESTIMATION IN HEVCXiaocong LIAN, School of Electronics and Information, Northwestern Polytechnical UniversityZhenyu LIU, Research Institute of Information Technology, Tsinghua UniversityWei ZHOU, School of Electronics and Information, Northwestern Polytechnical UniversityZhemin DUAN, School of Electronics and Information, Northwestern Polytechnical University
110 | ICIP 2015 – Technical Program
COM-P9.6 – SEAMLESS SWITCHING OF H .265/HEVC-CODED DASH REPRESENTATIONS WITH OPEN GOP PREDICTION STRUCTUREYe YAN, University of Science and Technology of ChinaMiska Matias HANNUKSELA, Nokia TechnologiesHouqiang LI, University of Science and Technology of China
ELI-O1: 3D Image Processing Tuesday, 10:30-12:30LECTURE Room: 203Session Chair(s): Philip A . CHOU, Microsoft
10:30 ELI-O1.1 – LARGE-AREA DEPTH RECOVERY FOR RGB-D CAMERAZengqiang YAN, Huazhong University of Science and TechnologyLi YU, Huazhong University of Science and TechnologyZixiang XIONG, Texas A&M University
10:50 ELI-O1.2 – REFRACTIVE STEREO RAY TRACING FOR RECONSTRUCTING UNDERWATER STRUCTURESScott SORENSEN, University of DelawareAbhishek KOLAGUNDA, University of DelawarePhilip SAPONARO, University of DelawareChandra KAMBHAMETTU, University of Delaware
11:10 ELI-O1.3 – SIPF: SCALE INVARIANT POINT FEATURE FOR 3D POINT CLOUDSBaowei LIN, Dalian Neusoft University of InformationFangda ZHAO, Hiroshima UniversityToru TAMAKI, Hiroshima UniversityFasheng WANG, Dalian Neusoft University of InformationLe XIAO, Dalian University of Technology
11:30 ELI-O1.4 – EFFICIENT IMAGE-SPACE EXTRACTION AND REPRESENTATION OF 3D SURFACE TOPOGRAPHYMatthias ZEPPELZAUER, St. Poelten University of Applied SciencesMarkus SEIDL, St. Poelten University of Applied Sciences
11:50 ELI-O1.5 – IMPROVING CALIBRATION OF THERMAL STEREO CAMERAS USING HEATED CALIBRATION BOARDPhilip SAPONARO, University of DelawareScott SORENSEN, University of DelawareStephen RHEIN, University of DelawareChandra KAMBHAMETTU, University of Delaware
12:10 ELI-O1.6 – COLOR-CODED PATTERN FOR NON METRIC CAMERA CALIBRATIONLorenzo SORGI, Technicolor Research & InnovationAndrey BUSHNEVSKIY, Technicolor Research & Innovation
«
ICIP 2015 – Technical Program | 111
ELI-P1: 3D Models and Applications Tuesday, 10:30-12:30POSTER Room: POSTER HSession Chair(s): Muhammad ASAD, City University London
ELI-P1.1 – ALBEDO ASSISTED HIGH-QUALITY SHAPE RECOVERY FROM 4D LIGHT FIELDSFei LIU, Institute of Automation, Chinese Academy of SciencesGuangqi HOU, Institute of Automation, Chinese Academy of SciencesZhenan SUN, Institute of Automation, Chinese Academy of SciencesTieniu TAN, Institute of Automation, Chinese Academy of Sciences
ELI-P1.2 – INTEL REALSENSE = REAL LOW COST GAZEMark DRAELOS, Duke UniversityQiang QIU, Duke UniversityAlex BRONSTEIN, Duke UniversityGuillermo SAPIRO, Duke University
ELI-P1.3 – 3D FACIAL MODEL SYNTHESIS USING COUPLED DICTIONARIESSwami SANKARANARAYANAN, University of MarylandVishal PATEL, University of MarylandRama CHELLAPPA, University of Maryland
ELI-P1.4 – GENERATING A 3D HAND MODEL FROM FRONTAL COLOR AND RANGE SCANSMuhammad ASAD, City University LondonEnguerrand GENTET, École Normale Supérieure de CachanRilwan Remilekun BASARU, City University LondonGreg SLABAUGH, City University London
ELI-P1.5 – LEARNING-BASED DEPTH ESTIMATION FROM 2D IMAGES USING GIST AND SALIENCYJosé Luis HERRERA CONEJERO, Universidad Politécnica de MadridJanusz KONRAD, Boston UniversityCarlos Roberto DEL BLANCO ADÁN, Universidad Politécnica de MadridNarciso GARCÍA SANTOS, Universidad Politécnica de Madrid
ELI-P1.6 – IMPROVED 3D SPARSE MAPS FOR HIGH-PERFORMANCE SFM WITH LOW-COST OMNIDIRECTIONAL ROBOTSPedro CAVESTANY, Cranfield UniversityAntonio L . RODRIGUEZ, Institute Transuranium Elements Joint Research CentreHumberto MARTÍNEZ-BARBERÁ, University of MurciaToby BRECKON, Durham University
ELI-P13: Image Processing Systems Tuesday, 10:30-12:30POSTER Room: POSTER GSession Chair(s): James FOWLER, Mississippi State University
ELI-P13.1 – FUSION OF MULTISPECTRAL AND PANCHROMATIC IMAGES BASED ON A NOVEL INTER-BAND STRUCTURE MODELShengwei ZHONG, Dept. of Information Engineering, Harbin Institute of TechnologyYe ZHANG, Dept. of Information Engineering, Harbin Institute of Technology
112 | ICIP 2015 – Technical Program
ELI-P13.2 – EFFECTIVE DOCUMENT IMAGE DEBLURRING VIA GRADIENT HISTOGRAM PRESERVATION Mingli ZHANG, École de technologie superieureChristian DESROSIERS, École de technologie superieureCaiming ZHANG, School of Computer Science and TechnologyMohamed CHERIET, École de technologie supérieure
ELI-P13.3 – ITERATIVE ALGORITHMS FOR SPECTRAL ESTIMATION WITH SPATIAL SMOOTHINGHenryk BLASINSKI, Stanford UniversityJoyce FARRELL, Stanford UniversityBrian WANDELL, Stanford University
ELI-P13.4 – A NOVEL BINARIZATION APPROACH FOR TEXT IN IMAGESPing HU, School of Computer and Control Engineering, University of Chinese Academy of SciencesKe LU, School of Computer and Control Engineering, University of Chinese Academy of SciencesWeiqiang WANG, School of Computer and Control Engineering, University of Chinese Academy of Sciences
ELI-P13.5 – HYPERSPECTRAL CLASSIFICATION USING A COMPOSITE KERNEL DRIVEN BY NEAREST-NEIGHBOR SPATIAL FEATURESVineetha MENON, Mississippi State UniversitySaurabh PRASAD, University of HoustonJames FOWLER, Mississippi State University
ELI-P13.6 – PERCEPTUAL BACKLIGHT SCALING FOR LOW POWER LIQUID CRYSTAL DISPLAYS BASED ON VISUAL SALIENCYCheolkon JUNG, Xidian UniversityZengtao XIA, Xidian University
GOYT-W: Industry Workshop: Imaging DSP at Google/YouTube Tuesday, 10:30-12:30WORKSHOP Room: 206ASession Chair(s): André MORIN, Optelis Jean-Luc DUGELAY, Eurecom
SummaryWhile well known for search, Google has now grown to generate significant impact in the media-processing space. Recruitment in media/imaging and vision has been growing for some time. This workshop features three Googlers, Peyman Milamfar, Anil Kokaram and Debargha Mukerjee, with 20-min snapshots of Imaging and Video DSP technology currently being explored by Google/YouTube. We highlight key developments and expose some of the underbelly of technology research and development in YouTube, Chrome, and Google Research itself.
PresentersDebargha Mukherjee, Open-source video-codec development at GoogleAnil Kokaram, Technical Lead in the Transcoding Group at YouTube/GooglePeyman Milanfar, Lead, Computational Imaging team in Google Research
«
ICIP 2015 – Technical Program | 113
NEW-P1: Stereoscopic, Multiview and 3-D Coding Tuesday, 10:30-12:30POSTER Room: POSTER JSession Chair(s): Pascal FROSSARD, EPFL
NEW-P1.1 – ON THE ACCURACY OF POINT LOCALISATION IN A CIRCULAR CAMERA-ARRAYAlireza GHASEMI, EPFLAdam SCHOLEFIELD, EPFLMartin VETTERLI, EPFL
NEW-P1.2 – LOW COMPLEXITY UNSUPERVISED MULTI-CAMERA COLOR CALIBRATION WITHAPPLICATION TO PANORAMIC VIDEO CAPTURINGKarim HELWANI, Huawei European Research CenterLukasz KONDRAD, Huawei European Research Center, MunichNicola PIOTTO, Huawei European Research Center, Munich
NEW-P1.3 – SUPER-RESOLUTION IMAGE SYNTHESIS USING THE PHYSICAL PIXEL ARRANGEMENT OF A LIGHT FIELD CAMERAKazuki OHASHI, Nagoya UniveresityKeita TAKAHASHI, Nagoya UniveresityMehrdad PANAHPOUR TEHERANI, Nagoya UniveresityToshiaki FUJII, Nagoya Univeresity
NEW-P1.4 – RANK ANALYSIS OF A LIGHT FIELD FOR DUAL-LAYER 3D DISPLAYSKeita TAKAHASHI, Nagoya UniversityToyohiro SAITO, Nagoya UniversityMehrdad PANAHPOUR TEHRANI, Nagoya UniversityToshiaki FUJII, Nagoya University
NEW-P1.5 – CDF 9/7 WAVELETS AS SPARSIFYING OPERATOR IN COMPRESSIVE HOLOGRAPHY Hao YAN, Vrije Universiteit Brussel, Dept. of Electronics and Informatics (ETRO)David BLINDER, Vrije Universiteit Brussel, Dept. of Electronics and Informatics (ETRO), Belgium;Stijn BETTENS, Vrije Universiteit Brussel, Dept. of Electronics and Informatics (ETRO)Heidi OTTEVAERE, Vrije Universiteit Brussel, Brussels Photonics Team (B-PHOT)Adrian MUNTEANU, Vrije Universiteit Brussel, Dept. of Electronics and Informatics (ETRO)Peter SCHELKENS, Vrije Universiteit Brussel, Dept. of Electronics and Informatics (ETRO)
NEW-P2: Multidimensional Processing Tuesday, 10:30-12:30POSTER Room: POSTER KSession Chair(s): Michael HOEDLMOSER, Siemens AG
NEW-P2.1 – ANGLE CONSTRAINED PATH FOR CLUSTERING OF MULTIPLE MANIFOLDSAmir BABAEIAN, UC San DiegoAlireza BAYESTEHTASHK, Oregon Health & Science UniversityMohammadreza BABAEE, Technische Universitat MunchenMojtaba BANDARABADI, University of CoimbraAntonio DOURADO, University of CoimbraAmin GHADESI, University of Mazandaran
«
114 | ICIP 2015 – Technical Program
NEW-P2.2 – SYNTHESIS OF LIGHT-FIELD RAW DATA FROM RGB-D IMAGESChao SUN, University of Electronic Science and Technology of ChinaYiqun WU, Hongkong University of Science and TechnologyBing ZENG, University of Electronic Science and Technology of China
NEW-P2.3 – COMPLEX MODULATION COMPUTER-GENERATED HOLOGRAM BY A FAST HYBRID POINT-SOURCE/WAVE-FIELD APPROACHAntonin GILLES, Institut de Recherche Technologique b<>comPatrick GIOIA, Institut de Recherche Technologique b<>comRémi COZOT, Institut de Recherche Technologique b<>comLuce MORIN, Institut de Recherche Technologique b<>com
NEW-P2.4 – A FRAMEWORK FOR VIEW-DEPENDENT HOLOGRAM REPRESENTATION AND ADAPTIVE RECONSTRUCTIONKartik VISWANATHAN, Orange LabsPatrick GIOIA, Orange LabsLuce MORIN, INSA/IETR
NEW-P2.5 – 3D WINDOW LOCALIZATION ON BUILDING FACADES FROM AERIAL IMAGESMichael HOEDLMOSER, Siemens AG Austria
NEW-P2.6 – BUILDING CHANGE DETECTION BASED ON 3D RECONSTRUCTIONBaohua CHEN, Department of Automation, Tsinghua UniversityYueqi DUAN, Department of Automation, Tsinghua UniversitySiyuan HUANG, Department of Automation, Tsinghua UniversityJie ZHOU, Department of Automation, Tsinghua UniversityLei DENG, Department of Automation, Tsinghua University
SMR-O2: Image Segmentation and Classification Tuesday, 10:30-12:30LECTURE Room: 205ASession Chair(s): Mireille BOUTIN, Purdue University
10:30 SMR-O2.1 – MULTI-KERNEL COLLABORATIVE REPRESENTATION FOR IMAGE CLASSIFICATIONWeiyang LIU, School of Electronic and Computer Engineering, Peking UniversityZhiding YU, Department of Electrical & Computer Engineering, Carnegie Mellon UniversityYandong WEN, School of Electronic & Information Engineering, South China University of TechnologyMeng YANG, College of Computer Science & Software Engineering, Shenzhen UniversityYuexian ZOU, School of Electronic & Computer Engineering, Peking University
10:50 SMR-O2.2 – THE HIDDEN STRUCTURE OF IMAGE DATASETSSangchun HAN, Purdue UniversityMireille BOUTIN, Purdue University
11:10 SMR-O2.3 – WITHIN-CLASS PENALTY BASED MULTI-CLASS SUPPORT VECTOR MACHINEXiaoshuang SHI, Graduate School at Shenzhen, Tsinghua UniversityZhenhua GUO, Graduate School at Shenzhen, Tsinghua UniversityYujiu YANG, Graduate School at Shenzhen, Tsinghua UniversityLin YANG, Department of Biomedical Engineering, University of Florida
ICIP 2015 – Technical Program | 115
11:30 « SMR-O2.4 – PARTIALLY TAGGED IMAGE CLUSTERINGQiyue YIN, Institute of Automation, Chinese Academy of SciencesShu WU, Institute of Automation, Chinese Academy of SciencesLiang WANG, Institute of Automation, Chinese Academy of Sciences
11:50 SMR-O2.5 – TOWARDS REDUCTION OF THE TRAINING AND SEARCH RUNNING TIME COMPLEXITIES FOR NON-RIGID OBJECT SEGMENTATIONJacinto NASCIMENTO, ISR-IST, PortugalGustavo CARNEIRO, ISR-IST, Portugal
12:10 SMR-O2.6 – A SPLITTING-AND-GROUPING BASED MULTI-MODEL FITTING FOR COMPUTER VISIONYun ZHANG, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote SensingBin LUO, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing
SNT-S4: Show & Tell IV Tuesday, 10:30-12:30SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S4.1 – PRACTICAL OPTIMIZATION ALGORITHMS FOR IMAGE PROCESSINGRahul MOURYA, Université Jean MonnetWe propose to demonstrate the usability and efficiency of novel optimization algorithms,ror selected problems in image processing such as Poissonian Image Deblurring, Shift-Variant Image Deblurring, and Image Segmentation with Mumford-Shah Model . Through a MTALB GUI, users can see in real-time how the different algorithms behave for the different problems and see the evolving solution of the optimization problems, and final solution in less than half a minute .
SNT-S4.2 – APPLYING IMAGE ANALYSIS TO ASSESS FOOD AESTHETICS AND UNIQUENESS Ying LI, IBM T. J. Watson Research CenterThis demo is about assessing the aesthetics of a cooked dish by analyzing its color composition . Especially, it detects major colors in the food image, explores their compliance to certain color schemes, measures how they spread across the color wheel, estimate their intensity and brightness, and finally assess how visually appealing the image is .
SNT-S4.3 – EFFICIENT REGRESSION PRIORS FOR REDUCING IMAGE COMPRESSION ARTIFACTSRasmus ROTHE, Computer Vision Lab, D-ITET, ETH ZurichRadu TIMOFTE, Computer Vision Lab, D-ITET, ETH ZurichLuc VAN GOOL, Computer Vision Lab, D-ITET, ETH ZurichWe propose an efficient novel compression artifact reduction algorithm based on the adjusted anchored neighborhood regression, a method from image super-resolution literature . We double the relative gains in PSNR when compared with the state-of-the-art methods such as SLGP, while being order(s) of magnitude faster .
116 | ICIP 2015 – Technical Program
SNT-S4.4 – UTILIZING IMAGE-BASED FEATURES IN BIOMEDICAL DOCUMENT CLASSIFICATIONKaidi MA, University of DelawareHogyeong JEONG, University of DelawareGowri SOMANATH, University of DelawareRyan TARPINE, GoogleKyle SCHUTTER, Brown UniversityDorothea BLOSTEIN, Queen’s UniveristySorin ISTRAIL, Univeristy of DelawareChandra KAMBHAMETTU, University of DelawareHagit SHATKAY, University of Delaware and Queen’s UniversityIn the demonstration we will show how our system utilizes both OCR-based image features and text-based features to successfully identify articles that pertain to cis-regulatory modules in the context of gene-networks . We will start by showing how we represent biomedical articles . Namely, we use two types of representation: image-based and text-based
SS7-O1: Computational Imaging Tuesday, 10:30-12:30LECTURE Room: 202Session Chair(s): Clem KARL, Boston University Charles BOUMAN, Purdue University Thrasyvoulos N . PAPPAS, Northwestern University
10:30 SS7-O1.1 – COMPUTATIONAL LIGHTING DESIGNSylvain PARIS, Adobe Research
10:50 «SS7-O1.2 – MODEL-BASED IMAGE RECONSTRUCTION OF CHEMILUMINESCENCEUSING A PLENOPTIC 2 .0 CAMERAHung NIEN, University of MichiganJeffrey FESSLER, University of MichiganVolker SICK, University of Michigan
11:10 « SS7-O1.3 – 3-D IMAGE RECONSTRUCTION FOR BIO NANOMACHINES WITH HELICAL SYMMETRY: IMAGE FORMATION THEORYQiu WANG, Cornell UniversityPeter DOERSCHUK, Cornell University
11:30 SS7-O1.4 – SAMPLING OPTIMIZATION FOR ON-CHIP COMPRESSIVE VIDEOLeonidas SPINOULAS, Northwestern UniversityOliver COSSAIRT, Northwestern UniversityAggelos K . KATSAGGELOS, Northwestern University
11:50 SS7-O1.5 – MODEL-BASED ITERATIVE RECONSTRUCTION FOR MAGNETIC RESONANCE FINGERPRINTINGBo ZHAO, University of Illinois at Urbana-Champaign
12:10 « SS7-O1.6 – AN AUGMENTED LAGRANGIAN METHOD FOR IMAGE RECONSTRUCTION WITH MULTIPLE FEATURESH . Emre GUVEN, ASELSAN INC, Ankara, TURKEYAlper GUNGOR, ASELSAN Inc.Mujdat ÇETIN, SABANCI UNIVERSITY ISTANBUL
ICIP 2015 – Technical Program | 117
TEC-O3: Image Enhancement, Deblurring and Denoising Tuesday, 10:30-12:30LECTURE Room: 204BSession Chair(s): Alin ACHIM, University of Bristol
10:30 TEC-O3.1 – IMAGE DEBLURRING USING ROBUST SPARSITY PRIORSXinxin ZHANG, Peking University Shenzhen Graduate SchoolRonggang WANG, Peking University Shenzhen Graduate SchoolYonghong TIAN, Peking UniversityWenmin WANG, Peking University Shenzhen Graduate SchoolWen GAO, Peking University
10:50 TEC-O3.2 – REFERENCE IMAGE BASED METHOD OF REGION OF INTEREST ENHANCEMENT FOR HAZE IMAGEWuzhen SHI, Harbin Institute of TechnologyXinwei GAO, Harbin Institute of TechnologyBoqi CHEN, Harbin Institute of TechnologyFeng JIANG, Harbin Institute of TechnologyDebin ZHAO, Harbin Institute of Technology
11:10 TEC-O3.3 – BLIND IMAGE DECONVOLUTION USING THE SYLVESTER MATRIXNora ALKHALDI, The university of SheffieldJoab WINKLER, The university of Sheffield
11:30 TEC-O3.4 – GROUP-BASED HYPERSPECTRAL IMAGE DENOISING USING LOW RANK REPRESENTATIONMengdi WANG, Tsinghua UniversityJing YU, Beijing University of TechnologyWeidong SUN, Tsinghua University
11:50 TEC-O3.5 – IMAGE DENOISING VIA CODED APERTURE PHOTOGRAPHYMinhaeng LEE, KAISTYu-Wing TAI, KAIST
12:10 TEC-O3.6 – A LOW-LIGHT IMAGE ENHANCEMENT METHOD FOR BOTH DENOISING AND CONTRAST ENLARGINGLin LI, Peking University Shenzhen Graduate SchoolRonggang WANG, Peking University Shenzhen Graduate SchoolWenmin WANG, Peking University Shenzhen Graduate SchoolWen GAO, Peking University Shenzhen Graduate School
118 | ICIP 2015 – Technical Program
TEC-P1: Automated Detection and Tracking in Biomedical Images I Tuesday, 10:30-12:30POSTER Room: POSTER FSession Chair(s): A . Enis ÇETIN, Bilkent University Oguzhan OGUZ, Bilkent University
TEC-P1.1 – QUANTIFICATION OF THE 3D COLLAGEN NETWORK GEOMETRY IN CONFOCAL REFLECTION MICROSCOPYMartin MASKA, Masaryk UniversityCristina EDERRA, Center for Applied Medical Research, University of NavarraJavier FERNÁNDEZ-MARQUÉS, Center for Applied Medical Research, University of NavarraArrate MUÑOZ-BARRUTIA, Center for Applied Medical Research, University of NavarraMichal KOZUBEK, Masaryk UniversityCarlos ORTIZ-DE-SOLÓRZANO, Center for Applied Medical Research, University of Navarra
TEC-P1.2 – MULTI-RESOLUTION SUPER-PIXELS AND THEIR APPLICATIONS ON FLUORESCENTMESENCHYMAL STEM CELLS IMAGESOnur YORULMAZ, Bilkent Univesity,Department of Electrical and Electronics Engineering Oguzhan OGUZ, Bilkent Univesity,Department of Electrical and Electronics Engineering Ece AKHAN, Bilkent Univesity,Department of Molecular Biology and Genetics Dönüs TUNCEL, Bilkent Univesity,Department of Chemistry Rengül Ç . ATALAY, Cancer Systems Biology Laboratory, Graduate School of Informatics, Middle East Technical UniversityA . Enis ÇETIN, Bilkent Univesity,Department of Electrical and Electronics Engineering
TEC-P1.3 – A SENSITIVE AND EFFICIENT METHOD FOR MEASURING CHANGE IN CORTICALTHICKNESS USING FUZZY CORRESPONDENCE IN ALZHEIMER’S DISEASESaurabh GARG, University of British ColumbiaLisa TANG, University of British ColumbiaAnthony TRABOULSEE, University of British ColumbiaRoger TAM, University of British Columbia
TEC-P1.4 – SIMULTANEOUS MOTION CORRECTION AND T1 ESTIMATION IN QUANTITATIVE T1 MAPPING: AN ML RESTORATION APPROACHGabriel RAMOS-LLORDÉN, iMinds-Vision Lab, University of AntwerpArnold Jan DEN DEKKER, iMinds-Vision Lab, University of AntwerpGwendolyn VAN STEENKISTE, iMinds-Vision Lab, University of AntwerpJohan VAN AUDEKERKE, Bio-imaging Lab, University of AntwerpMarleen VERHOYE, Bio-imaging Lab, University of AntwerpJan SIJBERS, iMinds-Vision Lab, University of Antwerp
TEC-P1.5 – AN AUTOMATIC MUSCLE FIBER ORIENTATION TRACKING ALGORITHM USING BAYESIAN KALMAN FILTER FOR ULTRASOUND IMAGESShuai ZHANG, The University of Hong KongZhiguo ZHANG, The University of Hong KongShingchow CHAN, The University of Hong KongHuiying WEN, School of Medicine, Shenzhen Key Laboratory of Biomedical Engineering, Shenzhen UniversityXin CHEN, School of Medicine, Shenzhen Key Laboratory of Biomedical Engineering, Shenzhen University
ICIP 2015 – Technical Program | 119
TEC-P1.6 – AUTOMATIC DETECTION OF BONE MARROW INFILTRATION BY MULTIPLE MYELOMA DETECTION IN LOW-DOSE CTFrancisco MARTÍNEZ-MARTÍNEZ, Czech Technical University in PragueJan KYBIC, Czech Technical University in PragueLukás LAMBERT, Charles University in Prague, First Faculty of Medicine, Department of Radiology
TEC-P31: Automated Detection and tracking in Biomedical Images II Tuesday, 10:30-12:30POSTER Room: POSTER ESession Chair(s): A . Enis ÇETIN, Bilkent University Oguzhan OGUZ, Bilkent University
TEC-P31.1 – USING STEERABLE WAVELETS AND MINIMAL PATHS TO RECONSTRUCT AUTOMATICALLY FILAMENTS IN FLUORESCENCE IMAGINGThibault LAGACHE, Institut PasteurQuentin MARCOU, Institut PasteurAntoine BARDONNET, Institut PasteurBrice ROTUREAU, Institut PasteurPhilippe BASTIN, Institut PasteurJean-Christophe OLIVO-MARIN, Institut Pasteur
TEC-P31.2 – HIERARCHICAL TUCKER TENSOR REGRESSION: APPLICATION TO BRAIN IMAGING DATA ANALYSISMing HOU, Laval universityBrahim CHAIB-DRAA, Laval university
TEC-P31.3 – DIAGNOSTIC COLOR ESTIMATION OF TISSUE COMPONENTS IN PATHOLOGY IMAGESVIA VON MISES MIXTURE MODELXingyu LI, University of TorontoKonstantinos N . PLATANIOTIS, University of Toronto
TEC-P31.4 – DENSE FEMUR RECONSTRUCTION FROM TWO X-RAY IMAGES USING GENERIC 3D MODEL WITH TWIST CORRECTIONKi-Jung KIM, Kyung Hee UniversitySeungkyu LEE, Kyung Hee UniversityYoon Hyuk KIM, Kyung Hee University
TEC-P31.5 – A MULTI-FRAME OPTICAL FLOW SPOT TRACKERji*zhou LI, The Chinese University of Hong KongChristopher GILLIAM, The Chinese University of Hong KongThierry BLU, The Chinese University of Hong Kong
TEC-P31.6 – RECOVERING SIZE AND SHAPE OF POLYP FROM ENDOSCOPE IMAGE BY RBF-NN MODIFICATIONYuji IWAHORI, Chubu UniversitySeiya TSUDA, Chubu UniversityYuki HANAI, Chubu UniversityRobert J . WOODHAM, University of British ColumbiaM . K . BHUYAN, Indian Inst. of Tech. GuwahatiKunio KASUGAI, Aichi Medical University
«
120 | ICIP 2015 – Technical Program
SGT-L: Get-Together Students-Employers Luncheon Tuesday, 12:30-14:00LUNCH Room: 206BSession Chair(s): Sylvie DANIEL, Laval University Guoliang FAN, Oklahoma State University Patrizio CAMPISI, Università Degli Studi Roma Tre
ARS-O21: Learning II Tuesday, 14:00-16:00LECTURE Room: 205CSession Chair(s): Markus FLIERL, KTH Royal Institute of Technology
14:00 ARS-O21.1 – SEMI-SUPERVISED LEARNING FOR FINE-GRAINED OBJECT RECOGNITIONSimone PALAZZO, University of CataniaConcetto SPAMPINATO, University of CataniaDaniela GIORDANO, University of Catania
14:20 ARS-O21.2 – MAY THE TORCHER LIGHT OUR WAY: A NEGATIVE-ACCELERATED ACTIVE LEARNING FRAMEWORK FOR IMAGE CLASSIFICATIONZhipeng YE, Harbin Institute of TechnologyPeng LIU, Harbin Institute of TechnologyXianglong TANG, Harbin Institute of TechnologyWei ZHAO, Harbin Institute of Technology
14:40 ARS-O21.3 – GEOMETRY-BASED RANKING FOR MOBILE 3D VISUAL SEARCH USING HIERARCHICALLY STRUCTURED MULTI-VIEW FEATURESDavid MARS, kth-Royal Institute of TechnologyHanwei WU, kth-Royal Institute of TechnologyHaopeng LI, kth-Royal Institute of TechnologyMarkus FLIERL, kth-Royal Institute of Technology
15:00 ARS-O21.4 – MULTI-LABEL ACTIVE LEARNING WITH LABEL CORRELATION FOR IMAGE CLASSIFICATIONChen YE, Soochow UniversityJian WU, Soochow UniversityVictor S . SHENG, University of Central ArkansasPengpeng ZHAO, Soochow UniversityZhiming CUI, Soochow University
15:20 ARS-O21.5 – CENTER-BASED WEIGHTED KERNEL LINEAR REGRESSION FOR IMAGE CLASSIFICATIONQingxiang FENG, Tsinghua UniversityChun YUAN, Tsinghua UniversityJiawen HUANG, Tsinghua UniversityWeifeng LI, Tsinghua University
15:40 ARS-O21.6 – THE USE OF DEEP LEARNING FEATURES IN A HIERARCHICAL CLASSIFIER LEARNED WITH THE MINIMIZATION OF A NON-GREEDY LOSS FUNCTIONZhibin LIAO, Australian Centre for Visual Technologies, The University of AdelaideGustavo CARNEIRO, Australian Centre for Visual Technologies, The University of Adelaide
ICIP 2015 – Technical Program | 121
ARS-O6: Face Recognition II Tuesday, 14:00-16:00LECTURE Room: 205ASession Chair(s): Zheng-Hua TAN, Aalborg University
14:00 ARS-O6.1 – ROBUST POSE NORMALIZATION FOR FACE RECOGNITION UNDER VARYING VIEWSBiao WANG, Samsung R&D Institute, ChinaXuetao FENG, Samsung R&D Institute, ChinaLujin GONG, Samsung R&D Institute, ChinaHao FENG, Samsung R&D Institute, ChinaWonjun HWANG, Samsung Advanced Institute of TechnologyJae-joon HAN, Samsung Advanced Institute of Technology
14:20 ARS-O6.2 – GRAPH REGULARIZED DISCRIMINANT ANALYSIS AND ITS APPLICATION TO FACE RECOGNITIONTianfei ZHOU, Beijing Institute of TechnologyYao LU, Beijing Institute of TechnologyYanan ZHANG, Beijing Institute of Technology
14:40 ARS-O6.3 – LOCAL FEATURE LEARNING FOR FACE RECOGNITION UNDER VARYING POSESXiaodong DUAN, Aalborg UniversityZheng-Hua TAN, Aalborg University
15:00 ARS-O6.4 – A GEOMETRICAL-MODEL-BASED FACE RECOGNITIONYea-Shuan HUANG, Chung-Hua UniversitySuen-Yu CHEN, Chung-Hua University
15:20 ARS-O6.5 – A 3D FACE RECOGNITION METHOD USING REGION-BASED EXTENDED LOCAL BINARY PATTERNShiwen LV, School of Automation, Southeast University, Nanjing 210096, ChinaFeipeng DA, School of Automation, Southeast University, Nanjing 210096, ChinaXing DENG, School of Automation, Southeast University
15:40 ARS-O6.6 – WEIGHTED SPARSE REPRESENTATION USING A LEARNED DISTANCE METRIC FOR FACE RECOGNITIONXiaochao QU, Korea UniversitySuah KIM, Korea UniversityDessalegn ATNAFU, Korea UniversityHyoung Joong KIM, Korea University
ARS-O7: Image Retrieval Tuesday, 14:00-16:00LECTURE Room: 204ASession Chair(s): Kiyo AIZAWA, University of Tokyo
14:00 ARS-O7.1 – LOAD-BALANCED LOCALITY-SENSITIVE HASHING: A NEW METHOD FOR EFFICIENT NEAR DUPLICATE IMAGE DETECTIONYabo FAN, National Laboratory of Pattern Recognition, Institute of AutomationJunliang XING, National Laboratory of Pattern Recognition, Institute of AutomationWeiming HU, National Laboratory of Pattern Recognition, Institute of Automation
122 | ICIP 2015 – Technical Program
14:20 ARS-O7.2 – RETRIEVING IMAGES COMBINING SALIENCY DETECTION WITH IRMShao HUANG, University of Chinese Academy of SciencesWeiqiang WANG, University of Chinese Academy of Sciences
14:40 ARS-O7.3 – ARTRIEVAL: PAINTING RETRIEVAL WITHOUT EXPERT KNOWLEDGENamil KIM, KAISTYukyung CHOI, KAISTSoonmin HWANG, KAISTIn So KWEON, KAIST
15:00 ARS-O7.4 – PRODUCT TREE QUANTIZATION FOR APPROXIMATE NEAREST NEIGHBOR SEARCHJiangbo YUAN, Florida State UniversityXiuwen LIU, Florida State University
15:20 ARS-O7.5 – SEARCHING FOR NEAREST NEIGHBORS WITH A DENSE SPACE PARTITIONINGTuan NGUYEN, The University of TokyoYusuke MATSUI, The University of TokyoToshihiko YAMASAKI, The University of TokyoKiyoharu AIZAWA, The University of Tokyo
15:40 ARS-O7.6 – RST-INVARIANT SKETCH RETRIEVAL BASED ON CIRCULAR DESCRIPTIONHanguang ZHAO, Dalian University of TechnologyXiangwei KONG, Dalian University of TechnologyHaiyan FU, Dalian University of TechnologyYujia ZHANG, Fordham University
ARS-P14: Human Body Analysis and Tracking Tuesday, 14:00-16:00POSTER Room: POSTER ASession Chair(s): Stefan WINKLER, Advanced Digital Sciences Center, University of Illinois at Urbana-Champaign
ARS-P14.1 – HUMAN POSE ESTIMATION WITH GLOBAL MOTION CUESQingxuan SHI, Beijing Institute of TechnologyHuijun DI, Beijing Institute of TechnologyYao LU, Beijing Institute of TechnologyFeng LV, Beijing Institute of Technology
ARS-P14.2 – CONTEXT AWARE MODEL FOR ARTICULATED HUMAN POSE ESTIMATIONLianrui FU, Institute of Automation, Chinese Academy of SciencesJunge ZHANG, Institute of Automation, Chinese Academy of SciencesKaiqi HUANG, Institute of Automation, Chinese Academy of Sciences
ARS-P14.3 – COMPUTATIONALLY EFFICIENT HUMAN POSE ESTIMATION WITH MULTI SOFTMAX DEEP CONVOLUTIONAL NEURAL NETWORKYunhun JANG, Korea Advanced Institute of Science and Technology (KAIST)Dae-Shik KIM, Korea Advanced Institute of Science and Technology (KAIST)
ARS-P14.4 – IMPROVING BOOSTED PEDESTRIAN DETECTOR IN A SURVEILLANCE VIDEOPuhao MA, Tsinghua UniversityHaizhou AI, Tsinghua UniversityShun SAKAI, OMRON Corporation
ICIP 2015 – Technical Program | 123
ARS-P14.5 – HAND GESTURE RECOGNITION AND SPOTTING IN UNCONTROLLED ENVIRONMENTS BASED ON CLASSIFIER WEIGHTINGYi YAO, University of WarwickChang-Tsun LI, University of Warwick
ARS-P14.6 – REAL-TIME HUMAN BODY PARTS LOCALIZATION FROM DYNAMIC VISION SENSORWentao MAO, Samsung Advanced Institute of Technology (China Lab)Qiang WANG, Samsung Advanced Institute of Technology (China Lab)Xiaotao WANG, Samsung Advanced Institute of Technology (China Lab)
ARS-P17: Image Segmentation I Tuesday, 14:00-16:00POSTER Room: POSTER DSession Chair(s): Lionel LACASSAGNE, University Paris-Sud
ARS-P17.1 – INTERACTIVE OBJECT SEGMENTATION USING SINGLE TOUCHViswanath GOPALAKRISHNAN, Samsung R&D Institute - India, BangaloreAnirudh PURWAR, Samsung R&D Institute - India, BangaloreSatish LOKKOJU, Samsung R&D Institute - India, BangaloreRaushan KUMAR, Samsung R&D Institute - India, BangaloreKiran NANJUNDA IYER, Samsung R&D Institute - India, Bangalore
ARS-P17.2 – MATERIAL CLASSIFICATION AND SEMANTIC SEGMENTATION OF RAILWAY TRACK IMAGES WITH DEEP CONVOLUTIONAL NEURAL NETWORKSXavier GIBERT, University of MarylandVishal PATEL, University of MarylandRama CHELLAPPA, University of Maryland
ARS-P17.3 – PARALLEL LIGHT SPEED LABELING: AN EFFICIENT CONNECTED COMPONENT LABELING ALGORITHM FOR MULTI-CORE PROCESSORSLaurent CABARET, Laboratoire de Recherche en Informatique / INRIA - Univ. Paris Sud Lionel LACASSAGNE, Laboratoire de Recherche en Informatique / INRIA - Univ. Paris Sud Daniel ETIEMBLE, Laboratoire de Recherche en Informatique / INRIA - Univ. Paris Sud
ARS-P17.4 – ROAD EXTRACTION VIA ADAPTIVE GRAPH CUTS WITH MULTIPLE FEATURESGuangliang CHENG, National laboratory of pattern recognition, Institute of Automation Chinese Academy of SciencesYing WANG, National laboratory of pattern recognition, Institute of Automation Chinese Academy of SciencesFeiyun ZHU, National laboratory of pattern recognition, Institute of Automation Chinese Academy of SciencesChunhong PAN, National laboratory of pattern recognition, Institute of Automation Chinese Academy of Sciences
ARS-P17.5 – FINE-STRUCTURED OBJECT SEGMENTATION VIA LOCAL AND NONLOCAL NEIGHBORHOOD PROPAGATIONYongchao GONG, Institute of Automation, Chinese Academy of SciencesShiming XIANG, Institute of Automation, Chinese Academy of SciencesLingfeng WANG, Institute of Automation, Chinese Academy of SciencesChunhong PAN, Institute of Automation, Chinese Academy of Sciences
«
«
124 | ICIP 2015 – Technical Program
ARS-P19: Local Features Tuesday, 14:00-16:00POSTER Room: POSTER BSession Chair(s): Frédéric DUFAUX, Télécom ParisTech
ARS-P19.1 – PLANT IDENTIFICATION USING TRIANGULAR REPRESENTATION BASED ON SALIENT POINTS AND MARGIN POINTSZhong-Qiu ZHAO, Hefei University of TechnologyYan HONG, Hefei University of TechnologyPeng ZHENG, Hefei University of Technology
ARS-P19.2 – HISTOGRAMS OF LOCALLY AGGREGATED ORIENTED GRADIENTSXiusheng LU, Harbin Institute of TechnologyShengping ZHANG, Harbin Institute of TechnologyHongxun YAO, Harbin Institute of TechnologyXin SUN, Harbin Institute of TechnologyYanhao ZHANG, Harbin Institute of Technology
ARS-P19.3 – TIGER: A TEXTURE-ILLUMINATION GUIDED ENERGY RESPONSE MODEL FOR ILLUMINATION ROBUST LOCAL SALIENCYBrendan CHWYL, University of WaterlooAudrey CHUNG, University of WaterlooFrancis LI, University of WaterlooAlexander WONG, University of WaterlooDavid CLAUSI, University of Waterloo
ARS-P19.4 – IMPROVING DISTINCTIVENESS OF BRISK FEATURES USING DEPTH MAPSMaxim KARPUSHIN, Télécom ParisTechGiuseppe VALENZISE, Télécom ParisTechFrédéric DUFAUX, Télécom ParisTech
ARS-P19.5 – FAST-MATCH: FAST AND ROBUST FEATURE MATCHING ON LARGE IMAGESJonas ARNFRED, University of Illinois at Urbana-ChampaignStefan WINKLER, University of Illinois at Urbana-Champaign
ARS-P19.6 – PER-PATCH METRIC LEARNING FOR ROBUST IMAGE MATCHINGSezer KARAOGLU, University of AmsterdamIvo EVERTS, University of AmsterdamJan VAN GEMERT, University of AmsterdamTheo GEVERS, University of Amsterdam
ARS-P21: Multimedia Content Analysis Tuesday, 14:00-16:00POSTER Room: POSTER CSession Chair(s): Jean-Luc DUGELAY, Eurecom
ARS-P21.1 – SCALABLE ACTION LOCALIZATION WITH KERNEL-SPACE HASHINGAndrei STOIAN, CNAMMarin FERECATU, CNAMJenny BENOIS-PINEAU, LABRIMichel CRUCIANU, CNAM
ICIP 2015 – Technical Program | 125
ARS-P21.2 – ANALYZING USER PREFERENCE FOR SOCIAL IMAGE RECOMMENDATIONXianming LIU, University of Illinois, Urbana-ChampaignMin-Hsuan TSAI, GoogleThomas HUANG, University of Illinois, Urbana-Champaign
ARS-P21.3 – VISUAL VOICE ACTIVITY DETECTION BASED ON SPATIOTEMPORAL INFORMATION AND BAG OF WORDSFoteini PATRONA, Aristotle University of ThessalonikiAlexandros IOSIFIDIS, Aristotle University of ThessalonikiAnastasios TEFAS, Aristotle University of ThessalonikiNikolaos NIKOLAIDIS, Aristotle University of ThessalonikiIoannis PITAS, Aristotle University of Thessaloniki
ARS-P21.4 – EVENT RETRIEVAL USING MOTION BARCODESGil BEN-ARTZI, The Hebrew University of JerusalemMichael WERMAN, The Hebrew University of JerusalemShmuel PELEG, The Hebrew University of Jerusalem
ARS-P21.5 – LEARNING UNIFIED SPARSE REPRESENTATIONS FOR MULTI-MODAL DATAKaiye WANG, NLPR, CASIAWei WANG, NLPR, CASIALiang WANG, NLPR, CASIA
ARS-P45: Image Segmentation II Tuesday, 14:00-16:00POSTER Room: POSTER ESession Chair(s): Lionel LACASSAGNE, University Paris-Sud
ARS-P45.1 – SEEDED LAPLACIAN: AN INTERACTIVE IMAGE SEGMENTATION APPROACH USING EIGENFUNCTIONSAhmed TAHA, Faculty of Engineering - Alexandria UniversityMarwan TORKI, Faculty of Engineering - Alexandria University
ARS-P45.2 – LEARNING DISCRIMINATIVE OCCLUSION FEATURE FOR DEPTH ORDERING INFERENCE ON MONOCULAR IMAGEAnlong MING, Beijing University of Posts and TelecommunicationsBaofeng XUN, Beijing University of Posts and TelecommunicationsJia NI, Beijing University of Posts and TelecommunicationsMingfei GAO, Beijing University of Posts and TelecommunicationsYu ZHOU, Beijing University of Posts and Telecommunications
ARS-P45.3 – COUPLED ENSEMBLE GRAPH CUTS AND OBJECT VERIFICATION FOR ANIMAL SEGMENTATION FROM HIGHLY CLUTTERED VIDEOSZhi ZHANG, UNIVERSITY OF MISSOURITony X . HAN, UNIVERSITY OF MISSOURIZhihai HE, UNIVERSITY OF MISSOURI
ARS-P45.4 – SELF-SUPERVISED ROAD DETECTION FROM A SINGLE IMAGEXiqun LU, Zhejiang University
«
126 | ICIP 2015 – Technical Program
ARS-P45.5 – SCREEN CONTENT IMAGE SEGMENTATION USING LEAST ABSOLUTE DEVIATION FITTINGShervin MINAEE, New York UniversityYao WANG, New York University
ARS-P45.6 – TRANSDUCTIVE VIDEO CO-SEGMENTATION ON THE TEMPORAL TREESZhihui FU, Shanghai Jiao Tong UniversityBotao WANG, Shanghai Jiao Tong UniversityHongkai XIONG, Shanghai Jiao Tong University
COM-O2: Video Coding I Tuesday, 14:00-16:00LECTURE Room: 202Session Chair(s): Stéphane COULOMBE, École de technologie supérieure
14:00 « COM-O2.1 – FAST H .264 TO HEVC TRANSCODER BASED ON POST-ORDER TRAVERSAL OFQUADTREE STRUCTUREJean-françois FRANCHE, École de technologie supérieure (ÉTS)Stéphane COULOMBE, École de technologie supérieure (ÉTS)
14:20 COM-O2.2 – MODE-DEPENDENT TRANSFORM COMPETITION FOR HEVCAdrià ARRUFAT, OrangePierrick PHILIPPE, OrangeOlivier DÉFORGES, IETR/INSA
14:40 COM-O2.3 – HIGH PERFORMANCE LOOP FILTER FOR HEVCWai-kuen CHAM, The Chinese University of HongKongQinglong HAN, The Chinese University of HongKong
15:00 COM-O2.4 – IMAGE CODING WITH INCOMPLETE TRANSFORM COMPETITION FOR HEVCAdrià ARRUFAT, OrangeAnne-flore PERRIN, OrangePierrick PHILIPPE, B-COM
15:20 COM-O2.5 – FAST MOTION BLUR COMPENSATION IN HEVC USING FIXED-LENGTH FILTERYiqun LIU, Leibniz Universität HannoverJörn OSTERMANN, Leibniz Universität Hannover
15:40 COM-O2.6 – STATISTICAL APPROACH FOR MOTION ESTIMATION SKIPPING (SAMEK)Li YU, Xi’an Jiaotong-Liverpool UniversityJimin XIAO, Xian Jiaotong-Liverpool UniversityTammam TILLO, Xian Jiaotong-Liverpool UniversityCe ZHU, University of Electronic Science and Technology of China
ELI-O5: Multiview / 3D Video Coding Tuesday, 14:00-16:00LECTURE Room: 203Session Chair(s): Aljoša SMOLIC, Disney Research Zürich
ICIP 2015 – Technical Program | 127
14:00 ELI-O5.1 – EFFICIENT DEPTH INTRA MODE DECISION BY REFERENCE PIXELS CLASSIFICATIONIN 3D-HEVCHong-Bin ZHANG, Nanjing University of Science and TechnologyChang-Hong FU, Nanjing University of Science and TechnologyYui-Lam CHAN, The Hong Kong Polytechnnic UniversitySik-Ho TSANG, The Hong Kong Polytechnic UniversityWan-Chi SIU, The Hong Kong Polytechnic University
14:20 ELI-O5.2 – UPSAMPLED-VIEW DISTORTION OPTIMIZATION FOR MIXED RESOLUTION 3D VIDEO CODINGMichal JOACHIMIAK, Tampere University of TechnologyMiska Matias HANNUKSELA, Nokia Research CenterPayman AFLAKI, Nokia Research CenterMoncef GABBOUJ, Tampere University of Technology
14:40 ELI-O5.3 – EFFICIENT CALIBRATION FOR MULTI-PLANE hom*oGRAPHY USING A LASER LEVELYen-chou TAI, Dept. of Computer Science, National Chiao Tung UniversityChin-Wei LIU, Dept. of Computer Science, National Chiao Tung UniversityYong-Sheng CHEN, Dept. of Computer Science, National Chiao Tung UniversityJen-hui CHUANG, Dept. of Computer Science, National Chiao Tung University
15:00 ELI-O5.4 – OVERVIEW OF THE MULTIVIEW HIGH EFFICIENCY VIDEO CODING (MV-HEVC) STANDARDMiska Matias HANNUKSELA, Nokia TechnologiesYe YAN, University of Science and Technology of ChinaXuehui HUANG, University of Science and Technology of ChinaHouqiang LI, University of Science and Technology of China
15:20 ELI-O5.5 – FAST ENCODING OF 3D COLOR-PLUS-DEPTH VIDEO BASED ON 3D-HEVCWen-nung LIE, National Chung Cheng UniversityYan-heng LU, National Chung Cheng University
15:40 ELI-O5.6 – BLOCK DEPENDANT DICTIONARY BASED DISPARITY COMPENSATION FOR STEREO IMAGE CODINGGabriel DAUPHIN, L2TI, Institut Galilée, Université Paris 13 Sorbonne Paris CitéMounir KAANICHE, L2TI, Institut Galilée, Université Paris 13 Sorbonne Paris CitéAnissa MOKRAOUI, L2TI, Institut Galilée, Université Paris 13 Sorbonne Paris Cité
ELI-P10: Text and Characters in Images Tuesday, 14:00-16:00POSTER Room: POSTER MSession Chair(s): Hideaki GOTO, Tohoku University
ELI-P10.1 – CHARACTER RECOGNITION FOR THE MACHINE READER ZONE OF ELECTRONIC IDENTITY CARDSHyeogjin LEE, Seoul National UniversityNojun KWAK, Seoul National University
ELI-P10.2 – SCENE TEXT DETECTION BASED ON COMPONENT-LEVEL FUSION AND REGION-LEVEL VERIFICATIONGuanghan NING, University of Missouri-ColumbiaTony X . HAN, University of Missouri-ColumbiaZhihai HE, University of Missouri-Columbia
128 | ICIP 2015 – Technical Program
ELI-P10.3 – FAST AND ACCURATE CANDIDATE REDUCTION USING THE MULTICLASS LDA FOR JAPANESE/CHINESE CHARACTER RECOGNITIONRyosuke ODATE, Tohoku UniversityHideaki GOTO, Tohoku University
ELI-P10.4 – FEATURE EXTRACTION OF HANDWRITTEN KANNADA CHARACTERS USING CURVELETS AND PRINCIPAL COMPONENT ANALYSISPadma M .C, P.E.S. College of EngineeringSaleem PASHA, P.E.S. College of Engineering, Mandya, Karnataka, India
ELI-P10.5 – A PATTERN RECOGNITION APPROACH TO MAKE ACCESSIBLE THE GEOGRAPHIC IMAGES FOR BLIND AND VISUALLY IMPAIREDZehira HADDAD, Université Paris 8Yong CHEN, Université Paris 8Jaime LOPEZ KRAHE, Université Paris 8
ELI-P10.6 – IN-AIR HANDWRITTEN CHINESE CHARACTER RECOGNITION USING MULTI-STAGE CLASSIFIER BASED ON ADAPTIVE DISCRIMINATIVE LOCALITY ALIGNMENTXiwen QU, University of Chinese Academy of SciencesWeiqiang WANG, University of Chinese Academy of SciencesKe LU, University of Chinese Academy of SciencesNing XU, University of Chinese Academy of Sciences
ELI-P2: 3D Object and Scene Reconstruction I Tuesday, 14:00-16:00POSTER Room: POSTER OSession Chair(s): Peter DOERSCHUK, Cornell University
ELI-P2.1 – VARIATIONAL MULTI-IMAGE STEREO MATCHINGSimon DONNÉ, iMinds-IPI-UGentBart GOOSSENS, iMinds-IPI-UGentWilfried PHILIPS, iMinds-IPI-UGentJan AELTERMAN, iMinds-IPI-UGent
ELI-P2.2 – FLUCTUATIONS OF DISPARITY SPACE IMAGE FOR STEREO MATCHING IN UNTEXTURED REGIONSHongmei ZHU, Beihang UniversityJihao YIN, Beihang University
ELI-P2.3 – LEARNING DEPTH FROM A SINGLE IMAGE USING VISUAL-DEPTH WORDSSunok KIM, Yonsei UniversitySunghwan CHOI, Yonsei UniversityKwanghoon SOHN, Yonsei University
ELI-P2.4 – DEPTH EDGE BASED TRILATERAL FILTER METHOD FOR STEREO MATCHINGDongming CHEN, École Centrale de LyonMohsen ARDABILIAN, École Centrale de LyonLiming CHEN, École Centrale de Lyon
ELI-P2.5 – DEPTH FROM ACCIDENTAL MOTION USING GEOMETRY PRIORSung-hoon IM, KAISTGyeongmin CHOE, KAISTHae-Gon JEON, KAISTIn So KWEON, KAIST
«
ICIP 2015 – Technical Program | 129
ELI-P2.6 – USING LINE CONSISTENCY TO ESTIMATE 3D INDOOR MANHATTAN SCENE LAYOUT FROM A SINGLE IMAGEHsing-Chun CHANG, National Tsing Hua UniversitySzu-Hao HUANG, National Tsing Hua UniversityShang-Hong LAI, National Tsing Hua University
ELI-P11: 3D Object and Scene Reconstruction II Tuesday, 14:00-16:00POSTER Room: POSTER NSession Chair(s): Peter DOERSCHUK, Cornell University
ELI-P11.1 – MESH SEGMENTATION WITH CONNECTING PARTS FOR 3D OBJECT PROTOTYPINGKarl APAZA-AGÜERO, Universidade Federal do ParanáLuciano SILVA, Universidade Federal do ParanáOlga BELLON, Universidade Federal do Paraná
ELI-P11.2 – WHAT DOES A SINGLE LIGHT-RAY REVEAL ABOUT A TRANSPARENT OBJECT?Chia-Yin TSAI, Carnegie Mellon UniversityAshok VEERARAGHAVAN, Rice UniversityAswin C . SANKARANARAYANAN, Carnegie Mellon University
ELI-P11.3 – HIGH-ACCURACY 3D IMAGE STITCHING FOR ROBOT-BASED INSPECTION SYSTEMSMarco ULRICH, Technische Universität MünchenAndreas FORSTNER, Technische Universität MünchenGunther REINHART, Technische Universität München
ELI-P11.4 – RECONSTRUCTION FOR STOCHASTIC 3-D SIGNALS WITH SYMMETRIC STATISTICS IN NOISE: ELECTRON MICROSCOPY OF VIRUS PARTICLESNan XU, Cornell UniversityPeter DOERSCHUK, Cornell University
ELI-P11.5 – POINT SET REGISTRATION BASED ON IMPLICIT SURFACE FITTING WITH EQUIVALENT DISTANCETong LIU, Harbin Institute of TechnologyWang LIU, Harbin Institute of TechnologyLiyan QIAO, Harbin Institute of TechnologyTiannan LUO, Harbin Institute of TechonologyXiyuan PENG, Harbin Institute of Technology
ELI-P11.6 – STRUCTURED REPRESENTATION-BASED ROBUST AGILE-BEAM LADAR IMAGINGVishal M PATEL, University of MarylandMichael A . POWERS, General Dynamics
IFS-P1: Content and Privacy Protection Tuesday, 14:00-16:00POSTER Room: POSTER KSession Chair(s): Stefano TUBARO, Politecnico di Milano
IFS-P1.1 – AFFECT-PRESERVING PRIVACY PROTECTION OF VIDEOWanxin XU, University of KentuckySen-Ching Samson CHEUNG, University of KentuckyNeelkamal SOARES, Geisinger Health System
«
130 | ICIP 2015 – Technical Program
IFS-P1.2 – PHYLOGENY RECONSTRUCTION FOR MISALIGNED AND COMPRESSED VIDEO SEQUENCESFilipe COSTA, University of CampinasSilvia LAMERI, Politecnico di MilanoPaolo BESTAGINI, Politecnico di MilanoZanoni DIAS, University of CampinasAnderson ROCHA, University of CampinasMarco TAGLIASACCHI, Politecnico di MilanoStefano TUBARO, Politecnico di Milano
IFS-P1.3 – INVARIANT CHARACTERIZATION OF DOVID SECURITY FEATURES USING A PHOTOMETRIC DESCRIPTORSvorad STOLC, Austrian Institute of Technology (AIT)Daniel SOUKUP, Austrian Institute of Technology (AIT)Reinhold HUBER-MOERK, Austrian Institute of Technology (AIT)
IFS-P1.4 – FACE DE-IDENTIFICATION WITH EXPRESSIONS PRESERVATIONGeoffrey LETOURNEL, LaBRIAurelie BUGEAU, LaBRIVinh-Thong TA, LaBRIJean Philippe DOMENGER, LaBRI
IFS-P1.5 – GRAPH REGULARIZED LOW-RANK MATRIX RECOVERY FOR ROBUST PERSON RE-IDENTIFICATIONMing-Chia TSAI, Academia SinicaChia-Po WEI, Academia SinicaYu-Chiang Frank WANG, Academia Sinica
IFS-P1.6 – NEAR-DUPLICATE DETECTION AND ALIGNMENT FOR MULTI-VIEW VIDEOSAmbra MELLONI, Politecnico di MilanoSilvia LAMERI, Politecnico di MilanoPaolo BESTAGINI, Politecnico di MilanoMarco TAGLIASACCHI, Politecnico di MilanoStefano TUBARO, Politecnico di Milano
IFS-P3: Robust Hashing and Counter-forensics Tuesday, 14:00-16:00POSTER Room: POSTER LSession Chair(s): Stefano TUBARO, Politecnico di Milano
IFS-P3.1 – A STUDY ON PUF CHARACTERISTICS FOR COUNTERFEIT DETECTIONChau-Wai WONG, University of Maryland, College ParkMin WU, University of Maryland, College Park
IFS-P3.2 – REMOVING CAMERA FINGERPRINT TO DISGUISE PHOTOGRAPH SOURCEHui ZENG, Sun Yat-sen UniversityJiansheng CHEN, Sun Yat-sen UniversityXiangui KANG, Sun Yat-sen UniversityWenjun ZENG, University of Missouri-Columbia
IFS-P3.3 – MULTI-FEATURE HASHING BASED ON SNR MAXIMIZATIONHonghai YU, University of Illinois at Urbana-ChampaignPierre MOULIN, University of Illinois at Urbana-Champaign
ICIP 2015 – Technical Program | 131
IFS-P3.4 – COUNTERING ANTI-FORENSICS OF IMAGE RESAMPLINGAnjie PENG, School of Information Science and Technology, Sun Yat-Sen University Hui ZENG, School of Information Science and Technology, Sun Yat-Sen University Xiaodan LIN, School of Information Science and Technology, Sun Yat-Sen University Xiangui KANG, School of Information Science and Technology, Sun Yat-Sen University
SMR-O3: Texture Representation Tuesday, 14:00-16:00LECTURE Room: 204BSession Chair(s): David NEUHOFF, University of Michigan
14:00 SMR-O3.1 – A MULTI-SCALE LOCAL BINARY PATTERN BASED ON PATH INTEGRAL FOR TEXTURE CLASSIFICATIONQiuyan LIN, Institute of Computer Science and Technology, Peking UniversityWenfa QI, Institute of Computer Science and Technology, Peking University
14:20 SMR-O3.2 – DISTRIBUTIONS OF LOCAL RADIUS INDICES ON PERIODIC TESSELLATIONSYuanhao ZHAI, University of MichiganDavid NEUHOFF, University of Michigan
14:40 SMR-O3.3 – MEDIAN ROBUST EXTENDED LOCAL BINARY PATTERN FOR TEXTURE CLASSIFICATIONLi LIU, National University of Defense TechnologyPaul FIEGUTH, University of WaterlooMatti PIETIKAINEN, University of OuluSongyang LAO, National University of Defense Technology
15:00 SMR-O3.4 – DATA-DRIVEN PROGRESSIVE COMPRESSION OF COLORED 3D MESHCaroline MENDES, Universidade Federal do ParanaKarl APAZA-AGÜERO, Universidade Federal do ParanaLuciano SILVA, Universidade Federal do ParanaOlga BELLON, Universidade Federal do Parana
15:20 SMR-O3.5 – TEXTURE CHARACTERIZATION VIA IMPROVED DETERMINISTIC WALKS ON IMAGE-GENERATED COMPLEX NETWORKLeandro COUTO, Federal University of UberlandiaThiago RIBEIRO, Federal University of UberlandiaAndre BACKES, Federal University of UberlandiaCelia BARCELOS, Federal University of Uberlandia
15:40 SMR-O3.6 – HISTOGRAM OF GRADIENT MAGNITUDES - A ROTATION INVARIANT TEXTURE-DESCRIPTORMonika SHARMA, TCS Innovation LabsHiranmay GHOSH, TCS Innovation Labs
SMR-P5: Image Representation Tuesday, 14:00-16:00POSTER Room: POSTER JSession Chair(s): Roberto A . LOTUFO, Universidade Estadual de Campinas
132 | ICIP 2015 – Technical Program
SMR-P5.1 – MULTI-SCALE BISECTOR INTEGRALS: AN INVARIANT DESCRIPTOR FOR ACCURATE SHAPE RETRIEVALBin WANG, School of Information and Engineering, Nanjing University of Finance and EconomicsYongsheng GAO, Griffith Univeristy
SMR-P5.2 – SHORT LOCAL DESCRIPTORS FROM 2D CONNECTED PATTERN SPECTRAPetra BOSILJ, Université de Bretagne Sud - IRISAEwa KIJAK, Université de Rennes 1 - IRISAMichael H .F . WILKINSON, University of GroningenSébastien LEFÈVRE, Université de Bretagne Sud - IRISA
SMR-P5.3 – PERFORMANCE ANALYSIS OF RETARGETING PYRAMID AND ITS APPLICATIONSRyosuke MORITA, Tokyo University of Agriculture and TechnologyKeiichiro SHIRAI, Shinshu UniversityYuichi TANAKA, Tokyo University of Agriculture and Technology
SMR-P5.4 – SCENE TEXT RECOGNITION WITH DEEPER CONVOLUTIONAL NEURAL NETWORKSYuqi ZHANG, Institute of Automation, Chinese Academy of SciencesWei WANG, Institute of Automation, Chinese Academy of SciencesLiang WANG, Institute of Automation, Chinese Academy of Sciences
SMR-P5.5 – ANISOTROPIC DATA-SPECIFIC WAVELETS FOR STRUCTURE-AWARE IMAGE PROCESSINGQingzheng WANG, State Key Laboratory of Virtual Technology and Systems, Beihang UniversityShuai LI, State Key Laboratory of Virtual Technology and Systems, Beihang UniversityHong QIN, Stony Brook UniversityAimin HAO, State Key Laboratory of Virtual Technology and Systems, Beihang University
SMR-P5.6 – AN ARRAY-BASED NODE-ORIENTED MAX-TREE REPRESENTATIONRoberto SOUZA, UNICAMPLetícia RITTNER, UNICAMPRubens MACHADO, CTI Renato ArcherRoberto LOTUFO, UNICAMP
SMR-P7: Object-based Representation Tuesday, 14:00-16:00POSTER Room: POSTER HSession Chair(s): Xiantong ZHEN, University of Western Ontario
SMR-P7.1 – DISTINCTIVE ACTION SKETCHYing ZHENG, Harbin Institute of TechnologyHongxun YAO, Harbin Institute of TechnologyXiaoshuai SUN, Harbin Institute of TechnologySicheng ZHAO, Harbin Institute of Technology
SMR-P7.2 – A NEW UNSUPERVISED MODEL OF ACTION RECOGNITIONLi XIAOQIANG, School of Computer Engineer and Science,Shanghai UniversityWang DAN, School of Computer Engineer and Science,Shanghai University
ICIP 2015 – Technical Program | 133
SMR-P7.3 – DIMENSIONALITY REDUCTION BY SUPERVISED LOCALITY ANALYSISXiantong ZHEN, University of Western OntarioPeipei PENG, Harbin Engineering UniversityXuezhi XIANG, Harbin Engineering UniversityLei ZHANG, Harbin Engineering University
SMR-P7.4 – ROBUST LOCAL AND GLOBAL SHAPE CONTEXT FOR TATTOO IMAGE MATCHINGJoonsoo KIM, Purdue UniversityAlbert PARRA, Purdue UniversityJiaju YUE, Purdue UniversityHe LI, Purdue UniversityEdward J . DELP, Purdue University
SMR-P7.5 – TERRORISM VIDEO RECOGNITION WITH SEMANTIC CONCEPTS DETECTING AND RE-RANKINGYifan SONG, School of Information and Communication Engineering, BUPTZhicheng ZHAO, Beijing Key Laboratory of Network System and Network Culture, BUPTFei SU, Beijing Key Laboratory of Network System and Network Culture, BUPT
SMR-P7.6 – SALIENCE BASED HIERARCHICAL FUZZY REPRESENTATION FOR OBJECTRECOGNITIONLifeng YANG, Tianjin UniversityHu QINGHUA, Tianjin UniversityLei ZHAO, Tianjin UniversityYin LI, Tianjin University
SNT-S5: Show & Tell V Tuesday, 14:00-16:00SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S5.1 – CALIBRATION TOOL FOR POST-PRODUCTIONLorenzo SORGI, TechnicolorAndrey BUSHNEVSKIY, TechnicolorRalf OSTERMANN, TechnicolorThis demonstration presents an innovative camera calibration tool that focuses on producing high-quality results with minimum manual interaction . The technology is particularly suited for easy calibration of wide-angle and super-wide-angle lenses .
SNT-S5.2 – POINT LOCALISATION FROM MULTI-CAMERA SYSTEMS: PERFORMANCE BOUNDS AND ALGORITHMSAlireza GHASEMI, EPFLAdam SCHOLEFIELD, EPFLMartin VETTERLI, EPFLIn this Show & Tell demonstration, we will visualise the localisation performance of different multi-camera systems and triangulation algorithms . For clarity, we will work in 2-D, so points will be localised within polygons . We will provide interactive tools that allow the user to investigate and gain insight into the impact of camera setups and localisation algorithms
134 | ICIP 2015 – Technical Program
SNT-S5.3 – GOAL-ORIENTED TOP-DOWN PROBABILISTIC VISUAL ATTENTION MODEL FOR RECOGNITION OF MANIPULATED OBJECTS IN EGOCENTRIC VIDEOSJenny BENOIS-PINEAU, Laboratoire Bordelais de Recherches en Informatique (LaBRI)In this demo we present several videos showing how top-down saliency maps can be built from the knowledge of hands and arms poses . We show how they can adapt to the shape of manipulated objects on different challenging datasets of egocentric vision .
SNT-S5.4 – JOINT OPTIMIZATION APPROACH TO METAL ARTIFACT REDUCTION AND SEGMENTATION FOR CT IMAGESPengchong JIN, Purdue UniversityDong Hye YE, Purdue UniversityCharles BOUMAN, Purdue UniversityIn this demonstration, we show that it is possible to substantially improve segmentation accuracy be formulating these two problems of CT image segmentation and artifact reduction as a single joint optimization problem . The demonstration will graphically and dynamically illustrate this alternating approach in detail . Specially, we will show the evolution of restored image and the segmentation after each iteration in an animated video .
SS6-O1: Compact Descriptor for Visual Search Tuesday, 14:00-16:00LECTURE Room: 205BSession Chair(s): Rongrong JI, Xiamen University
14:00 SS6-O1.1 – COLOR NAMES LEARNING USING CONVOLUTIONAL NEURAL NETWORKSYuhang WANG, The National Laboratory of Pattern Recognition, Institute of Automation, CASJing LIU, The National Laboratory of Pattern Recognition, Institute of Automation, CASJinqiao WANG, The National Laboratory of Pattern Recognition, Institute of Automation, CASYong LI, The National Laboratory of Pattern Recognition, Institute of Automation, CASHanqing LU, The National Laboratory of Pattern Recognition, Institute of Automation, CAS
14:20 SS6-O1.2 – AN EFFECTIVE EYE STATES DETECTION METHOD BASED ON THE PROJECTION OF THE GRAY INTERVAL DISTRIBUTIONXianming LIN, Cognitive Science Department of Xiamen University Ling CAI, School of Information Science and Engineering, Xiamen University, ChinaShao-Zi LI, School of Information Science and Engineering, Xiamen UniversityRongrong JI, School of Information Science and Engineering, Xiamen University
14:40 SS6-O1.3 – LEARNING DEEP COMPACT DESCRIPTOR WITH BAGGING AUTO-ENCODERS FOR OBJECT RETRIEVALHaiyun GUO, CASIAJinqiao WANG, CASIAHanqing LU, CASIA
15:00 SS6-O1.4 – AN EFFICIENT CODING FRAMEWORK FOR COMPACT DESCRIPTORS EXTRACTED FROM VIDEO SEQUENCEZhangshuai HUANG, Institute of Digital Media, School of EE & CS, Peking UniversityLing-Yu DUAN, Institute of Digital Media, School of EE & CS, Peking UniversityJie LIN, Institute for Infocomm Research
ICIP 2015 – Technical Program | 135
Shiqi WANG, Dept. of Electrical and Computer Engineering, University of WaterlooSiwei MA, Institute of Digital Media, School of EE & CS, Peking UniversityTiejun HUANG, Institute of Digital Media, School of EE & CS, Peking University
15:20 SS6-O1.5 – SENTIMENT ANALYSIS OF CHINESE MICRO-BLOG BASED ON MULTI-MODAL CORRELATION MODELLingxiao LI, Cognitive Science Department, Xiamen UniversityShao-Zi LI, Cognitive Science Department, Xiamen UniversityDonglin CAO, Cognitive Science Department, Xiamen UniversityDazhen LIN, Cognitive Science Department, Xiamen UniversityRongrong JI, Cognitive Science Department, Xiamen University
TEC-P18: Multi-image and Video Super-Resolution and Restoration Tuesday, 14:00-16:00POSTER Room: POSTER FSession Chair(s): Aggelos K . KATSAGGELOS, Northwestern University
TEC-P18.1 – HYBRID SUPER-RESOLUTION COMBINING EXAMPLE-BASED SINGLE-IMAGE AND INTERPOLATION-BASED MULTI-IMAGE RECONSTRUCTION APPROACHESMichel BÄTZ, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Andrea EICHENSEER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Jürgen SEILER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Markus JONSCHER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)André KAUP, Friedrich-Alexander University Erlangen-Nürnberg (FAU)
TEC-P18.2 – DICTIONARY-BASED MULTIPLE FRAME VIDEO SUPER-RESOLUTIONQiqin DAI, Northwestern UniversitySeunghwan YOO, Northwestern UniversityArmin KAPPELER, Northwestern UniversityAggelos K . KATSAGGELOS, Northwestern University
TEC-P18.3 – FLUOROSOCOPIC SEQUENCE DENOISING USING A MOTION COMPENSATED MULTI-SCALE TEMPORAL FILTERINGCarole AMIOT, ThalesCatherine GIRARD, ThalesJérémie PESCATORE, ThalesJocelyn CHANUSSOT, Gipsa-Lab - Université Grenoble-AlpesMichel DESVIGNES, Gipsa-Lab - Université Grenoble-Alpes
TEC-P18.4 – FACIAL VIDEO SUPER RESOLUTION USING SEMANTIC EXEMPLAR COMPONENTSXu CHEN, Sharp Labs of AmericaAnustup CHOUDHURY, Sharp Labs of AmericaPeter VAN BEEK, Sharp Labs of AmericaAndrew SEGALL, Sharp Labs of America
TEC-P18.5 – SUPER-RESOLUTION FOR INCONSISTENT SCALABLE VIDEO STREAMINGAbo-Talib MAHFOODH, Michigan State UniversityDebargha MUKHERJEE, Michigan State UniversityHayder RADHA, Michigan State University
«
«
136 | ICIP 2015 – Technical Program
TEC-P18.6 – MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTSYanghao LI, Peking UniversityJiaying LIU, Peking UniversityWenhan YANG, Peking UniversityZongming GUO, Peking University
TEC-P32: Medical Image Analysis Tuesday, 14:00-16:00POSTER Room: POSTER GSession Chair(s): Jean-Philippe THIRAN, EPFL
TEC-P32.1 – ACCELERATED MICROSTRUCTURE IMAGING VIA CONVEX OPTIMISATION FOR REGIONS WITH MULTIPLE FIBRES (AMICO_X)Anna AURÍA, EPFLDavid ROMASCANO, EPFLErick CANALES-RODRÍGUEZ, FIDMAG Germanes HospitalariesYves WIAUX, ISSS, Heriot-Watt UniversityTim DYRBY, Danish Research Centre for Magnetic Resonance, Copenhagen University HospitalDaniel ALEXANDER, CMIC, University College London, London, United KingdomJean-philippe THIRAN, EPFLAlessandro DADUCCI, EPFL
TEC-P32.2 – DETECTING DIFFERENT SUB-TYPES OF ACUTE MYELOGENOUS LEUKEMIA USING DICTIONARY LEARNING AND SPARSE REPRESENTATIONOmid SARRAFZADEH, Isfahan University of Medical SciencesHossein RABBANI, Isfahan University of Medical SciencesAlireza MEHRI DEHNAVI, Isfahan University of Medical SciencesArdeshir TALEBI, Isfahan University of Medical Sciences
TEC-P32.3 – AN ALGORITHM BASED ON LBPV AND MIL FOR LEFT ATRIAL THROMBI DETECTION USING TRANSESOPHAGEAL ECHOCARDIOGRAPHYJianrui DING, Harbin Institute of TechnologyMin XIAN, UTAH STATE UNIVERSITYHengda CHENG, Utah State UniversityYingtao ZHANG, Harbin Institute of TechnologyFei XU, Utah State University
TEC-P32.4 – BEATING CILIA IDENTIFICATION IN FLUORESCENCE MICROSCOPE IMAGES FOR ACCURATE CBF MEASUREMENTFan ZHANG, University of SydneyWeidong CAI, University of SydneyYang SONG, University of SydneyPaul YOUNG, Woolco*ck Institute of Medical Research & University of SydneyDaniela TRAINI, Woolco*ck Institute of Medical Research & University of SydneyLucy MORGAN, Concord Repatriation General Hospital & University of SydneyHui-Xin HONG, Woolco*ck Institute of Medical Research & University of SydneyLachlan BUDDLE, Concord Repatriation General HospitalDagan FENG, University of Sydney
ICIP 2015 – Technical Program | 137
TEC-P32.5 – OPTIMAL TRANSPORT USING HELMHOLTZ-HODGE DECOMPOSITION AND FIRST-ORDER PRIMAL-DUAL ALGORITHMSMorgane HENRY, Laboratoire Jean KuntzmannEmmanuel MAITRE, Laboratoire Jean KuntzmannValerie PERRIER, Laboratoire Jean Kuntzmann
TEC-P32.6 – CLASS-SPECIFIC HIERARCHICAL CLASSIFICATION FOR HEP-2 SPECIMEN IMAGESKrati GUPTA, Indian Institute of Technology MandiVibha GUPTA, Indian Institute of Technology MandiArnav BHAVSAR, Indian Institute of Technology MandiAnil SAO, Indian Institute of Technology Mandi
ARS-O19: Visual Biometrics Tuesday, 16:30-18:30LECTURE Room: 205BSession Chair(s): Sen-Ching Samson CHEUNG, University of Kentucky
16:30 ARS-O19.1 – FACE LIVENESS DETECTION AND RECOGNITION USING SHEARLET BASED FEATURE DESCRIPTORSYuming LI, City University of Hong KongLai-man PO, City University of Hong KongXuyuan XU, City University of Hong KongLitong FENG, City University of Hong KongFang YUAN, City University of Hong Kong
16:50 « ARS-O19.2 – FACE ANTI-SPOOFING BASED ON COLOR TEXTURE ANALYSISZinelabidine BOULKENAFET, Center for Machine Vision Research, University of OuluJukka KOMULAINEN, Center for Machine Vision Research, University of OuluAbdenour HADID, Center for Machine Vision Research, University of Oulu
17:10 ARS-O19.3 – RETINA VERIFICATION USING A COMBINED POINTS AND EDGES APPROACHEe Ping ONG, Institute for Infocomm ResearchYanwu XU, Institute for Infocomm ResearchDamon Wing Kee WONG, Institute for Infocomm ResearchJiang LIU, Institute for Infocomm Research
17:30 ARS-O19.4 – IRIS SUPER-RESOLUTION VIA NONPARAMETRIC OVER-COMPLETE DICTIONARY LEARNINGRaied ALJADAANY, Carnegie Mellon UniversityKhoa LUU, Carnegie Mellon UniversityShreyas VENUGOPALAN, Carnegie Mellon UniversityMarios SAVVIDES, Carnegie Mellon University
17:50 ARS-O19.5 – HIGH-ORDER INFORMATION FOR ROBUST IRIS RECOGNITION UNDER LESS CONTROLLED CONDITIONSGuanglei YANG, Dalian University of TechnologyHui ZENG, Dalian University of TechnologyPeihua LI, Dalian University of TechnologyLei ZHANG, The Hong Kong Polytechnic University
138 | ICIP 2015 – Technical Program
18:10 ARS-O19.6 – EVALUATING THE EFFECTS OF IMAGE COMPRESSION IN MOIRÉ-PATTERN-BASED FACE-SPOOFING DETECTIONDiogo GARCIA, Universidade de BrasíliaRicardo DE QUEIROZ, Universidade de Brasília
ARS-O3: Discriminative Local Features Tuesday, 16:30-18:30LECTURE Room: 203Session Chair(s): Keigo HIRAKAWA, University of Dayton
16:30 ARS-O3.1 – HYBRID CODING OF VISUAL CONTENT AND LOCAL IMAGE FEATURESLuca BAROFFIO, Politecnico di MilanoMatteo CESANA, Politecnico di MilanoAlessandro REDONDI, Politecnico di MilanoMarco TAGLIASACCHI, Politecnico di MilanoStefano TUBARO, Politecnico di Milano
16:50 « ARS-O3.2 – COMPARING FEATURE DETECTORS: A BIAS IN THE REPEATABILITY CRITERIA .Ives REY-OTERO, CMLA, ENS-CachanMauricio DELBRACIO, ECE, Duke UniversityJean-michel MOREL, CMLA, ENS-Cachan
17:10 ARS-O3.3 – IMPROVING SURF INTEREST POINT DETECTION FOR DEFOCUS BLUR ROBUSTNESSElhusain SAAD, University of DaytonKeigo HIRAKAWA, University of Dayton
17:30 ARS-O3.4 – ASPLÜND’S METRIC DEFINED IN THE LOGARITHMIC IMAGE PROCESSING (LIP) FRAMEWORK FOR COLOUR AND MULTIVARIATE IMAGESGuillaume NOYEL, International Prevention Research InstituteMichel JOURLIN, Laboratoire Hubert Curien
17:50 ARS-O3.5 – ROBUST TEXTURE FEATURES BASED ON UNDECIMATED DUAL-TREE COMPLEX WAVELETS AND LOCAL MAGNITUDE BINARY PATTERNSNantheera ANANTRASIRICHAI, University of BristolJeremy BURN, University of BristolDavid BULL, University of Bristol
18:10 ARS-O3.6 – SPATIAL MATCHING OF SKETCHES WITHOUT POINT CORRESPONDENCEFang WANG, National ICT AustraliaYi LI, National ICT Australia
ARS-P22: Object Detection & Classification Tuesday, 16:30-18:30POSTER Room: POSTER BSession Chair(s): Maria CORNACCHIA, Syracuse University
ARS-P22.1 – A STATE SPACE APPROACH TO VISUAL OBJECT TRACKINGJinwei YUAN, University of Texas at DallasFarokh BASTANI, University of Texas at Dallas
ICIP 2015 – Technical Program | 139
ARS-P22.2 – FILTERING SVM FRAME-BY-FRAME BINARY CLASSIFICATION IN A DETECTION FRAMEWORKAlejandro BETANCOURT, Eindhoven University of TechnologyPietro MORERIO, University of GenoaLucio MARCENARO, University of GenoaMatthias RAUTERBERG, Eindhoven University of TechnologyCarlo REGAZZONI, University of Genoa
ARS-P22.3 – MOVING OBJECT DETECTION FROM MOVING PLATFORMS USING LAGRANGE MULTIPLIERAgwad ELTANTAWY, Memorial University of NewfoundlandMohamed SHEHATA, Memorial University of Newfoundland
ARS-P22.4 – SCALE ESTIMATION WITH DIFFERENCE OF ORDERED RESIDUALSMaria CORNACCHIA, Syracuse UniversitySenem VELIPASALAR, Syracuse University
ARS-P22.5 – OBJECTNESS ESTIMATION USING EDGESHongzhen WANG, Institute of Automation, Chinese Academy of SciencesZikun LIU, Institute of Automation, Chinese Academy of SciencesLingfeng WANG, Institute of Automation, Chinese Academy of SciencesLubin WENG, Institute of Automation, Chinese Academy of SciencesChunhong PAN, Institute of Automation, Chinese Academy of Sciences
ARS-P22.6 – EFFICIENT 2×2 BLOCK-BASED CONNECTED COMPONENTS LABELING ALGORITHMSDiêgo SANTIAGO, Federal University of PernambucoIng Ren TSANG, Federal University of PernambucoGeorge CAVALCANTI, Federal University of PernambucoIng Jyh TSANG, Alcatel-Lucent
ARS-P23: Object Detection and Tracking II Tuesday, 16:30-18:30POSTER Room: POSTER ASession Chair(s): David NEUHOFF, University of Michigan
ARS-P23.1 – FITTING 3D MORPHABLE MODELS USING LOCAL FEATURESPatrik HUBER, University of SurreyZhen-Hua FENG, Jiangnan UnversityWilliam CHRISTMAS, University of SurreyJosef KITTLER, University of SurreyMatthias RÄTSCH, Reutlingen University
ARS-P23.2 – IMPROVING DEEP CONVOLUTIONAL NEURAL NETWORKS WITH UNSUPERVISED FEATURE LEARNINGKien NGUYEN, Queensland University of TechnologyClinton f*ckES, Queensland University of TechnologySridha SRIDHARAN, Queensland University of Technology
«
«
140 | ICIP 2015 – Technical Program
ARS-P23.3 – ADAPTIVE SEARCH OF BACKGROUND MODELS FOR OBJECT DETECTION IN IMAGES TAKEN BY MOVING CAMERASTsubasa MINEMATSU, Kyushu UniversityHideaki UCHIYAMA, Kyushu UniversityAtsushi SHIMADA, Kyushu UniversityHajime NAGAHARA, Kyushu UniversityRin-ichiro TANIGUCHI, Kyushu University
ARS-P23.4 – MULTIPLE KERNEL BOOSTING BASED TRACKING USING POOLING FEATURESTing GE, Beijing Institute of TechnologyYao LU, Beijing Institute of Technology
ARS-P23.5 – QUALITY CONTROL IN CROWDSOURCED OBJECT SEGMENTATIONFerran CABEZAS, Universite de ToulouseAxel CARLIER, Universite de ToulouseAmaia SALVADOR, Universitat Politecnica de Catalunya (UPC)Xavier GIRO-I-NIETO, Universitat Politecnica de Catalunya (UPC)Vincent CHARVILLAT, Universite de Toulouse
ARS-P23.6 – EFFECT OF CAMERA-IMU DISPLACEMENT CALIBRATION ERROR ON TRACKING PERFORMANCENekruzjon MAXUDOV, Ozyegin UniversityAli Özer ERCAN, Ozyegin UniversityA . Tanju ERDEM, Ozyegin University
ARS-P28: Scene Analysis I Tuesday, 16:30-18:30POSTER Room: POSTER DSession Chair(s): Simone MILANI, University of Padova
ARS-P28.1 – LIVE VIDEO SYNOPSIS FOR MULTIPLE CAMERASYedid HOSHEN, Hebrew University of JerusalemShmuel PELEG, Hebrew University of Jerusalem
ARS-P28.2 – NOISE CORRECTION OF IMAGE LABELING IN CROWDSOURCINGBryce NICHOLSON, University of Central ArkansasVictor S . SHENG, University of Central ArkansasJing ZHANG, Hefei University of Technology
ARS-P28.3 – THREE-DIMENSIONAL RECONSTRUCTION FROM HETEROGENEOUS VIDEO DEVICES WITH CAMERA-IN-VIEW INFORMATIONSimone MILANI, University of Padova
ARS-P28.4 – CROWD FLOW SEGMENTATION IN COMPRESSED DOMAIN USING CRFSrinivas S S KRUTHIVENTI, Indian Institute of ScienceVenkatesh Babu RADHAKRISHNAN, Indian Institute of Science
ARS-P28.5 – IMPROVED RAINDROP DETECTION USING COMBINED SHAPE AND SALIENCY DESCRIPTORS WITH SCENE CONTEXT ISOLATIONDereck WEBSTER, Cranfield UniversityToby BRECKON, Durham University
«
ICIP 2015 – Technical Program | 141
ARS-P28.6 – ACTIVITY RECOGNITION WITH VOLUME MOTION TEMPLATES AND HISTOGRAMS OF 3D GRADIENTSEmre DOGAN, INSA-LyonGönen EREN, Galatasaray UniversityChristian WOLF, INSA-LyonAtilla BASKURT, INSA-Lyon
ARS-P35: Visual Learning with Domain Adaptation Tuesday, 16:30-18:30POSTER Room: POSTER CSession Chair(s): Yannick BERTHOUMIEU, Bordeaux Polytechnic Institute
ARS-P35.1 – BLURRED IMAGE RECOGNITION USING DOMAIN ADAPTATIONXiaokang XIE, Huazhong University of Science and TechnologyZhiguo CAO, Huazhong University of Science and TechnologyYang XIAO, Huazhong University of Science and TechnologyMengyu ZHU, Huazhong University of Science and TechnologyHao LU, Huazhong University of Science and Technology
ARS-P35.2 – ADAPTIVE MULTI-TASK LEARNING FOR FINE-GRAINED CATEGORIZATIONGang SUN, Institute of Software, Chinese Academy of SciencesYanyun CHEN, Institute of Software, Chinese Academy of SciencesXuehui LIU, Institute of Software, Chinese Academy of SciencesEnhua WU, Institute of Software, Chinese Academy of Sciences
ARS-P35.3 – UNSUPERVISED DOMAIN ADAPTION DICTIONARY LEARNING FOR VISUAL RECOGNITIONZhun ZHONG, China University of PetroleumZongmin LI, China University of PetroleumRunlin LI, China University of PetroleumXiaoxia SUN, China University of Petroleum
ARS-P35.4 – KERNEL SUBSPACE ALIGNMENT FOR UNSUPERVISED DOMAIN ADAPTATIONMingwei XU, School of Automation, Nanjing University of Posts and TelecommunicationsSongsong WU, School of Automation, Nanjing University of Posts and TelecommunicationsXiaoyuan JING, School of Automation, Nanjing University of Posts and TelecommunicationsJingyu YANG, School of Computer Science and Technology, Nanjing University of Science and Technology
ARS-P35.5 – CROSS-DOMAIN RECOGNITION BY IDENTIFYING COMPACT JOINT SUBSPACESYuewei LIN, University of South CarolinaJing CHEN, University of MacauYu CAO, IBM ResearchYoujie ZHOU, University of South CarolinaLingfeng ZHANG, University of HoustonSong WANG, University of South Carolina
«
142 | ICIP 2015 – Technical Program
ARS-P35.6 – CONNECTING THE DOTS WITHOUT CLUES: UNSUPERVISED DOMAIN ADAPTATION FOR CROSS-DOMAIN VISUAL CLASSIFICATIONWei-Yu CHEN, National Taiwan UniversityTsu-Ming Harry HSU, National Taiwan UniversityCheng-an HOU, Academia SinicaYi-Ren YEH, Chinese Culture UniversityYu-Chiang Frank WANG, Academia Sinica
ARS-P44: Scene Analysis II Tuesday, 16:30-18:30POSTER Room: POSTER ESession Chair(s): Simone MILANI, University of Padova
ARS-P44.1 – OUTDOOR SCENE LABELLING WITH LEARNED FEATURES AND REGION CONSISTENCY ACTIVATIONYandong LI, University of Electronic Science and Technology of ChinaFerdous SOHEL, The University of Western AustraliaMohammed BENNAMOUN, The University of Western AustraliaHang LEI, University of Electronic Science and Technology of China
ARS-P44.2 – IMPROVING EGOCENTRIC VISION OF DAILY ACTIVITIESGonzalo VACA-CASTANO, University of Central FloridaSamarjit DAS, Bosch Research and Technology CenterJoao P SOUSA, Bosch Research and Technology Center
ARS-P44.3 – AN ITERATIVE CONVERGENCE ALGORITHM FOR SINGLE/MULTI GROUND PLANE DETECTION AND ANGLE ESTIMATION WITH RGB-D CAMERAYankun LANG, Wakayama UniversityHaiyuan WU, Wakayama UniversityToshiyuki AMANO, Wakayama UniversityQian CHEN, Wakayama University
ARS-P44.4 – DEPTH ESTIMATION BY ANALYZING INTENSITY DISTRIBUTION FOR LIGHT-FIELD CAMERASYatong XU, Shenzhen Key Lab of Broadband Network and Multimedia, Graduate School at Shenzhen, Tsinghua UnivXin JIN, Shenzhen Key Lab of Broadband Network and Multimedia, Graduate School at Shenzhen, Tsinghua UnivQionghai DAI, Automation Department, Tsinghua University
ARS-P44.5 – COMBINING NONUNIFORM SAMPLING, HYBRID SUPER VECTOR AND RANDOM FOREST WITH DISCRIMINATIVE DECISION TREES FOR ACTION RECOGNITIONKuanhong XU, Samsung R&D Institute, ChinaYa LU, Samsung R&D Institute, ChinaHongwei ZHANG, Samsung R&D Institute, ChinaXuetao FENG, Samsung R&D Institute, ChinaWonjun KIM, Samsung Advanced Institute of TechnologyJae-joon HAN, Samsung Advanced Institute of Technology
ARS-P44.6 – A SPATIAL CLASS LDA MODEL FOR CLASSIFICATION OF SPORTS SCENE IMAGESJin JEON, KAISTMunchurl KIM, KAIST
ICIP 2015 – Technical Program | 143
ELI-O8: Document Analysis Tuesday, 16:30-18:30LECTURE Room: 205ASession Chair(s): Xiao-Ping ZHANG, Ryerson University
16:30 ELI-O8.1 – CAPTURED OPEN BOOK IMAGE DE-WARPING USING DEPTH INFORMATIONChyuan-Tyng WU, Purdue UniversityKurt BENGTSON, Hewlett Packard CompanyJan ALLEBACH, Purdue University
16:50 ELI-O8.2 – SKEW CORRECTION AND LINE EXTRACTION IN BINARIZED PRINTED TEXT IMAGESWei LI, Institute of Imaging and Computer Vision, RWTH Aachen UniversityMatthias BREIER, Institute of Imaging and Computer Vision, RWTH Aachen UniversityDorit MERHOF, Institute of Imaging and Computer Vision, RWTH Aachen University
17:10 ELI-O8.3 – GAMMA CORRECTION ACCELERATION FOR REAL-TIME TEXT EXTRACTION FROM COMPLEX COLORED IMAGESRostom KACHOURI, Université Paris-Est, Laboratoire d�informatique Gaspard-Monge, A3SI, ESIEE Paris, CNRSChristian MEDINA ARMAS, Université Paris-Est, Laboratoire dinformatique Gaspard-Monge, A3SI, ESIEE Paris, CNRS, FranceMohamed AKIL, Université Paris-Est, Laboratoire dinformatique Gaspard-Monge, A3SI, ESIEE Paris, CNRS
17:30 ELI-O8.4 – SCENE TEXT DETECTION USING SEQUENTIAL NONTEXT FILTERINGYue LU, East China Normal UniversityQingqing WANG, East China Normal UniversityYing WEN, East China Normal University
17:50 ELI-O8.5 – FONT FINDER: VISUAL RECOGNITION OF TYPEFACE IN PRINTED DOCUMENTSTu BUI, University of SurreyJohn COLLOMOSSE, University of Surrey
18:10 ELI-O8.6 – A LAYERED METHOD FOR DETERMINING MANGA TEXT BUBBLE READING ORDERSamu KOVANEN, Aalto UniversityKiyoharu AIZAWA, The University of Tokyo
SMR-P2: Image and Video Quality Assessment I Tuesday, 16:30-18:30POSTER Room: POSTER LSession Chair(s): Maria Aishy AMER, Concordia University
SMR-P2.1 – STUDYING HUMAN BEHAVIOURAL RESPONSES TO TIME-VARYING DISTORTIONS FOR VIDEO QUALITY ASSESSMENTJuan V . TALENS-NOGUERA, University of HullWei ZHANG, University of HullHantao LIU, University of Hull
144 | ICIP 2015 – Technical Program
SMR-P2.2 – THE QUEST FOR THE INTEGRATION OF VISUAL SALIENCY MODELS IN OBJECTIVE IMAGE QUALITY ASSESSMENT: A DISTRACTION POWER COMPENSATED COMBINATION STRATEGYWei ZHANG, University of HullJuan V . TALENS-NOGUERA, University of HullHantao LIU, University of Hull
SMR-P2.3 – NO-REFERENCE QUALITY ASSESSMENT OF CONTRAST-DISTORTED IMAGES BASED ON NATURAL SCENE STATISTICSYuming FANG, Jiangxi University of Finance and EconomicsKede MA, University of Waterloo
SMR-P2.4 – SIMULTANEOUS ESTIMATION OF IMAGE QUALITY AND DISTORTION VIA MULTI-TASK CONVOLUTIONAL NEURAL NETWORKSLe KANG, University of Maryland, College ParkPeng YE, SONY US Research CenterYi LI, NICTADavid DOERMANN, University of Maryland, College Park
SMR-P2.5 – COMPARISON OF SUBJECTIVE VIEWING TEST METHODS FOR IMAGE QUALITY ASSESSMENTTsung-Jung LIU, National Chung Hsing UniversityKuan-Hsien LIU, Academia SinicaHsin-Hua LIU, National Taiwan UniversitySoo-Chang PEI, National Taiwan University
SMR-P3: Image and Video Quality Assessment II Tuesday, 16:30-18:30POSTER Room: POSTER MSession Chair(s): Maria Aishy AMER, Concordia University
SMR-P3.1 – ON THE IMPROVEMENT OF NO-REFERENCE MEAN OPINION SCORE ESTIMATION ACCURACY BY FOLLOWING A FRAME-LEVEL REGRESSION APPROACHKaterina PANDREMMENOU, University of IoanninaMuhammad SHAHID, Blekinge Institute of TechnologyLisimachos P . KONDI, University of IoanninaBenny LOVSTROM, Blekinge Institute of Technology
SMR-P3.2 – NO-REFERENCE IMAGE QUALITY ASSESSMENT FOR REMOVAL OF PROCESSED ANDUNPROCESSED NOISEMeisam RAKHSHANFAR, Concordia UniversityMaria Aishy AMER, Concordia University
«
ICIP 2015 – Technical Program | 145
SMR-P3.3 – DIFFERENCE OF GAUSSIAN STATISTICAL FEATURES BASED BLIND IMAGE QUALITY ASSESSMENT: A DEEP LEARNING APPROACHYaqi LV, Ningbo UniversityGangyi JIANG, Ningbo UniversityMei YU, Ningbo UniversityHaiyong XU, Ningbo UniversityFeng SHAO, Ningbo UniversityShanshan LIU, Ningbo University
SMR-P3.4 – ASSESSING THE VISUAL EFFECT OF NON-PERIODIC TEMPORAL VARIATION OF QUANTIZATION STEPSIZE IN COMPRESSED VIDEOZhili GUO, Polytechnic School of Engineering, New York UniversityYao WANG, Polytechnic School of Engineering, New York University
SMR-P3.5 – A STUDY OF SUBJECTIVE VIDEO QUALITY AT VARIOUS FRAME RATESAlex MACKIN, University of BristolFan ZHANG, University of BristolDavid BULL, University of Bristol
SMR-P3.6 – IMAGE QUALITY ASSESSMENT BASED ON DCT SUBBAND SIMILARITYAmnon BALANOV, Technion - Israel Institute of TechnologyArik SCHWARTZ, Technion - Israel Institute of TechnologyYair MOSHE, Technion - Israel Institute of TechnologyNimrod PELEG, Technion - Israel Institute of Technology
SMR-P11: Image and Video Quality Assessment III Tuesday, 16:30-18:30POSTER Room: POSTER NSession Chair(s): Maria Aishy AMER, Concordia University
SMR-P11.1 – SUBJECTIVE AND OBJECTIVE EVALUATION OF IMAGE INPAINTING QUALITYPhilipp TIEFENBACHER, Technische Universität MünchenViktor BOGISCHEF, Technische Universität MünchenDaniel MERGET, Technische Universität MünchenGerhard RIGOLL, Technische Universität München
SMR-P11.2 – IMAGE QUALITY EVALUATION USING IMAGE QUALITY RULER AND GRAPHICAL MODELWeibao WANG, Purdue UniversityYandong GUO, Microsoft ResearchJan ALLEBACH, Purdue University
SMR-P11.3 – 3D PERCEPTION BASED QUALITY POOLING ON STEREOSCOPIC IMAGEHaksub KIM, Yonsei UniversityJunghwan KIM, Yonsei UniversitySanghoon LEE, Yonsei University
SMR-P11.4 – REDUCED-REFERENCE QUALITY ASSESSMENT BASED ON THE ENTROPY OF DNTCOEFFICIENTS OF LOCALLY WEIGHTED GRADIENTSS . Alireza GOLESTANEH, Arizona State UniversityLina J . KARAM, Arizona State University
146 | ICIP 2015 – Technical Program
SMR-P11.5 – SALIENCY WEIGHTED QUALITY ASSESSMENT OF TONE-MAPPED IMAGESHamid NASRINPOUR, University of ManitobaNeil BRUCE, University of Manitoba
SMR-P11.6 – FULL-REFERENCE VISUAL QUALITY ASSESSMENT FOR SYNTHETIC IMAGES: A SUBJECTIVE STUDYDebarati KUNDU, University of Texas at AustinBrian EVANS, University of Texas at Austin
SMR-P4: Image Quality Assessment Tuesday, 16:30-18:30POSTER Room: POSTER OSession Chair(s): Ghassan ALREGIB, Georgia Institute of Technology
SMR-P4.1 – QUALITY PREDICTION OF ASYMMETRICALLY COMPRESSED STEREOSCOPIC VIDEOSJiheng WANG, University of WaterlooShiqi WANG, University of WaterlooZhou WANG, University of Waterloo
SMR-P4.2 – REDUCED-REFERENCE PERCEPTUAL QUALITY ASSESSMENT FOR VIDEO STREAMINGMohammed AABED, Georgia Institute of TechnologyGhassan ALREGIB, Georgia Institute of Technology
SMR-P4.3 – A HIGHLY EFFICIENT METHOD FOR BLIND IMAGE QUALITY ASSESSMENTQingbo WU, University of Electronic Science and Technology of ChinaZhou WANG, University of WaterlooHongliang LI, University of Electronic Science and Technology of China
SMR-P4.4 – PERSIM: MULTI-RESOLUTION IMAGE QUALITY ASSESSMENT IN THE PERCEPTUALLYUNIFORM COLOR DOMAINDogancan TEMEL, Georgia Institute of TechnologyGhassan ALREGIB, Georgia Institute of Technology
SMR-P4.5 – LIMITATIONS OF THE SSIM QUALITY METRIC IN THE CONTEXT OF DIAGNOSTIC IMAGINGJean-francois PAMBRUN, École de technologie supérieureRita NOUMEIR, École de technologie supérieure
SMR-P4.6 – PERCEPTUAL QUALITY ASSESSMENT OF DENOISED IMAGESKai ZENG, University of WaterlooZhou WANG, University of Waterloo
SNT-S6: Show & Tell VI Tuesday, 16:30-18:30SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S6.1 – DEFORMABLE MODELS FOR THE CONSTRUCTION OF 3D USER-INTERACTIVE SEGMENTATION ALGORITHMSDaniel SCHMITTER, Biomedical Imaging Group, EPFLChristophe GAUDET-BLAVIGNAC, Biomedical Imaging Group, EPFLDavide PICCINI, Advanced Clinical Imaging Technology Group, Siemens Healthcare SectorMichael UNSER, Biomedical Imaging Group, EPFL
«
«
ICIP 2015 – Technical Program | 147
In this demo, we will show our work in facial expression recognition . The demo will be accepting an image with possibly multiple persons, it will detect the several faces and will output for each face confidence values for a set of pre-trained facial expressions, namely: surprise, fear, disgust, happiness, sadness and anger .
SNT-S6.2 – FACIAL VIDEO SUPER RESOLUTION USING SEMANTIC EXEMPLAR COMPONENTSXu CHEN, Sharp Labs of AmericaIn this demo, we are going to present a side by side comparison of video super resolution results using our method and the state-of-the-art approach . The upscaling factor is selected to be 4 . The video is captured from YouTube and TV broadcast streaming .
SNT-S6.3 – ROBUST ANOMALY DETECTION FOR VISION-BASED INSPECTION OF RAILWAY COMPONENTSXavier GIBERT, University of MarylandWe will demonstrate our developed library of tools and algorithms that will be used to inspect railway tracks with machine vision technology . This technology has been integrated into a distributed computing framework and a user-friendly review package with a client-server interface .
SNT-S6.4 – STATISTICAL IMAGE RECONSTRUCTION FOR SYMMETRIC VIRUS PARTICLESNan XU, Cornell UniversityPeter DOERSCHUK, Cornell UniversityCryo electron microscopy leads to 3-D image reconstruction problems . This demonstration describes methods for incorporating the symmetry into expectation-maximization algorithms for the maximum likelihood solution of the reconstruction problem . The demonstration will use sophisticated 3-D computer graphics to allow participants to understand the goals and achievements of the 3-D reconstruction algorithms described in the paper
SS2-O1: Image/Video Indexing and Retrieval for Healthcare Tuesday, 16:30-18:30LECTURE Room: 202Session Chair(s): Alexia BRIASSOULI, Centre for Research and Technology Hellas Jenny BENOIS-PINEAU, LaBRI
16:30 SS2-O1.1 – COMPUTATIONALLY EFFICIENT RECOGNITION OF ACTIVITIES OF DAILY LIVINGStergios POULARAKIS, Information and Technologies Institute - Centre for Research and Technology HellasKonstantinos AVGERINAKIS, Information and Technologies Institute - Centre for Research and Technology HellasAlexia BRIASSOULI, Information and Technologies Institute - Centre for Research and Technology HellasIoannis KOMPATSIARIS, Information and Technologies Institute - Centre for Research and Technology Hellas
16:50 SS2-O1.2 – FEATURE SALIENCY ANALYSIS FOR PERCEPTUAL SIMILARITY OF CLUSTERED MICROCALCIFICATIONSJuan WANG, Illinois Institute of TechnologyYongyi YANG, Illinois Institute of Technology
148 | ICIP 2015 – Technical Program
17:10 «SS2-O1.3 – BARCODE ANNOTATIONS FOR MEDICAL IMAGE RETRIEVAL: A PRELIMINARY INVESTIGATIONHamid R . TIZHOOSH, University of Waterloo
17:30 « SS2-O1.4 – OBJECT RECOGNITION WITH TOP-DOWN VISUAL ATTENTION MODELING FOR BEHAVIORAL STUDIESVincent BUSO, Laboratoire Bordelais de Recherches en InformatiqueJenny BENOIS-PINEAU, Laboratoire Bordelais de Recherches en InformatiqueIvan GONZALEZ -DIAZ, Universidad Carlos III de Madrid
17:50 SS2-O1.5 – IDENTIFYING EPILEPTIC SEIZURES BASED ON A TEMPLATE-BASED EYEBALL DETECTION TECHNIQUESupriya SATHYANARAYANA, Nanyang Technological UniversityRavi Kumar SATZODA, TUM CREATESuchitra SATHYANARAYANA, Nanyang Technological UniversitySrikanthan THAMBIPILLAI, Nanyang Technological University
TEC-O1: Compressed Sensing Tuesday, 16:30-18:30LECTURE Room: 204BSession Chair(s): Jie LIANG, Simon Fraser University
16:30 TEC-O1.1 – RECONSTRUCTION OF COMPRESSIVELY SAMPLED LIGHT FIELDS USING A WEIGHTED 4D-DCT BASISYusuke MIYAGI, Graduate School of Engineering, Nagoya UniversityKeita TAKAHASHI, Graduate School of Engineering, Nagoya UniversityMehrdad PANAHPOUR TEHRANI, Graduate School of Engineering, Nagoya UniversityToshiaki FUJII, Graduate School of Engineering, Nagoya University
16:50 TEC-O1.2 – NONCONVEX RECONSTRUCTION FOR LOW-DIMENSIONAL FLUORESCENCE MOLECULAR TOMOGRAPHIC POISSON OBSERVATIONSLasith ADHIKARI, University of California, MercedDianwen ZHU, University of California, MercedChangqing LI, University of California, MercedRoummel MARCIA, University of California, Merced
17:10 « TEC-O1.3 – BM3D-AMP: A NEW IMAGE RECOVERY ALGORITHM BASED ON BM3D DENOISINGChristopher METZLER, Rice UniversityArian MALEKI, Columbia UniversityRichard BARANIUK, Rice University
17:30 TEC-O1.4 – IMAGE SUPER-RESOLUTION FROM COMPRESSED SENSING OBSERVATIONSWael SAAFIN, University of GranadaMiguel VEGA, University of GranadaRafael MOLINA, University of GranadaAggelos K . KATSAGGELOS, Northwestern University
ICIP 2015 – Technical Program | 149
17:50 TEC-O1.5 – LOCAL SENSING WITH GLOBAL RECOVERYDung TRAN, Johns Hopkins UniversityDuyet TRAN, Hanoi University of Science and TechnologySang CHIN, Boston UniversityTrac TRAN, Johns Hopkins University
18:10 TEC-O1.6 – MULTI-RESOLUTION COMPRESSED SENSING RECONSTRUCTION VIA APPROXIMATEMESSAGE PASSINGXing WANG, Simon Fraser UniversityJie LIANG, Simon Fraser University
TEC-O2: Image Denoising Tuesday, 16:30-18:30LECTURE Room: 204ASession Chair(s): Masayuki TANAKA, Tokyo Institute of Technology
16:30 TEC-O2.1 – IMAGE DENOISING USING OPTIMALLY WEIGHTED BILATERAL FILTERS: A SURE AND FAST APPROACHKunal CHAUDHURY, Indian Institute of ScienceKollipara RITHWIK, Indian Institute of Technology, Hyberadbad
16:50 TEC-O2.2 – DA3D: FAST AND DATA ADAPTIVE DUAL DOMAIN DENOISINGNicola PIERAZZO, ENS CachanMartin RAIS, ENS CachanJean-michel MOREL, ENS CachanGabriele FACCIOLO, ENS Cachan
17:10 TEC-O2.3 – IMAGE DENOISING IN MULTIPLICATIVE NOISEChandra Sekhar SEELAMANTULA, Indian Institute of ScienceThierry BLU, The Chinese University of Hong Kong
17:30 TEC-O2.4 – ROTATION INVARIANT SIMILARITY MEASURE FOR NON-LOCAL SELF-SIMILARITY BASED IMAGE DENOISINGChenglin ZUO, Ghent University & National University of Defense TechnologyLjubomir JOVANOV, Ghent UniversityHiep LUONG, Ghent UniversityBart GOOSSENS, Ghent UniversityWilfried PHILIPS, Ghent UniversityYu LIU, National University of Defense TechnologyMaojun ZHANG, National University of Defense Technology
17:50 TEC-O2.5 – ROBUST CONTRAST ENHANCEMENT OF NOISY LOW-LIGHT IMAGES: DENOISING-ENHANCEMENT-COMPLETIONJaemoon LIM, Korea UniversityJin-Hwan KIM, Korea UniversityJae-Young SIM, Ulsan National Institute of Science and TechnologyChang-Su KIM, Korea University
18:10 TEC-O2.6 – PSEUDO FOUR-CHANNEL IMAGE DENOISING FOR NOISY CFA RAW DATAHiroki AKIYAMA, Tokyo Institute of TechnologyMasayuki TANAKA, Tokyo Institute of TechnologyMasatoshi OKUTOMI, Tokyo Institute of Technology
150 | ICIP 2015 – Technical Program
TEC-P20: Neurological Feature Extraction and Classification Tuesday, 16:30-18:30POSTER Room: POSTER HSession Chair(s): Guy COURBEBAISSE, University of Lyon, CREATIS
TEC-P20.1 – ASYMMETRY EVALUATION OF FUNDUS IMAGES IN RIGHT AND LEFT EYES USING RADON TRANSFORM AND FRACTAL ANALYSISTahereh MAHMUDI, Isfahan Univ. of Med. SciencesRahele KAFIEH, Isfahan Univ. of Med. SciencesHossein RABBANI, Isfahan Univ. of Med. SciencesAlireza MEHRI, Isfahan Univ. of Med. SciencesMohammadreza AKHLAG, Isfahan Univ. of Med. Sciences
TEC-P20.2 – SENSORY LOAD HIERARCHY-BASED CLASSIFICATION OF SCHIZOPHRENIA PATIENTSMustafa S . ÇETIN, University of New MexicoJulia M . STEPHEN, The Mind Research NetworkVince D . CALHOUN, University of New Mexico
TEC-P20.3 – REGION-BASED BRAIN SELECTION AND CLASSIFICATION ON PET IMAGES FOR ALZHEIMERS DISEASE COMPUTER AIDED DIAGNOSISImène GARALI, Institut FRESNEL UMR-CNRS 7249, Campus Universitaire de Saint JérômeMouloud ADEL, Institut FRESNEL UMR-CNRS 7249, Campus Universitaire de Saint JérômeSalah BOURENNANE, Institut FRESNEL UMR-CNRS 7249, Campus Universitaire de Saint JérômeEric GUEDJ, Centre Européen de Recherche en Imagerie Médicale, Faculté de Médecine, Marseille Aix-Marseille
TEC-P20.4 – SUBJECT-CENTERED MULTI-VIEW FEATURE FUSION FOR NEUROIMAGING RETRIEVAL AND CLASSIFICATIONSidong LIU, Harvard Medical SchoolWeidong CAI, Harvard Medical SchoolSiqi LIU, The University of SydneySonia PUJOL, Harvard Medical SchoolRon KIKINIS, Harvard Medical SchoolDagan FENG, The University of Sydney
TEC-P20.5 – CLASSIFICATION OF EEG SIGNALS FOR DETECTION OF EPILEPTIC SEIZURE ACTIVITIES BASED ON LBP DESCRIPTOR OF TIME-FREQUENCY IMAGESLarbi BOUBCHIR, University of Paris 8Somaya AL-MAADEED, Qatar UniversityAhmed BOURIDANE, Northumbria UniversityArab ALI CHERIF, University of Paris 8, France
TEC-P20.6 – ULTRASOUND MEDIAN NERVE LOCALIZATION BY CLASSIFICATION BASED ON DESPECKLE FILTERING AND FEATURE SELECTIONOussama HADJERCI, INSA Centre Val de Loire, Université d’Orléans, Laboratoire PRISME EA 4229Adel HAFIANE, INSA Centre Val de Loire, Laboratoire PRISME EA 4229Donatello CONTE, Université de Francois Rabelais, Laboratoire LI EA 6300Pascal MAKRIS, Université de Francois Rabelais, Laboratoire LI EA 6300Pierre VIEYRES, Université d’Orléans, Laboratoire PRISME EA 4229Alain DELBOS, Clinique Medipole Garonne CS 13624
ICIP 2015 – Technical Program | 151
TEC-P23: Single-image Superresolution Tuesday, 16:30-18:30POSTER Room: POSTER FSession Chair(s): Pier Luigi DRAGOTTI, Imperial College
TEC-P23.1 – FAST IMAGE SUPER-RESOLUTION VIA SELECTIVE MANIFOLD LEARNING OFHIGH-RESOLUTION PATCHESChinh DANG, Michigan State UniversityHayder RADHA, Michigan State University
TEC-P23.2 – INCORPORATING IMAGE DEGENERATION MODELING WITH MULTITASK LEARNING FOR IMAGE SUPER-RESOLUTIONYudong LIANG, Xi’an Jiaotong UniversityJinjun WANG, Xi’an Jiaotong UniversityShizhou ZHANG, Xi’an Jiaotong UniversityYihong GONG, Xi’an Jiaotong University
TEC-P23.3 – ADAPTIVE AUTOREGRESSIVE MODEL WITH WINDOW EXTENSION VIA EXPLICIT GEOMETRY FOR IMAGE INTERPOLATIONQingyun WANG, Institute of Computer Science and Technology,Peking UniversityJiaying LIU, Institute of Computer Science and Technology,Peking UniversityWenhan YANG, Institute of Computer Science and Technology,Peking UniversityZongming GUO, Institute of Computer Science and Technology,Peking University
TEC-P23.4 – ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENTYang XIAN, The Graduate Center, The City University of New YorkYingli TIAN, The City College and The Graduate Center, The City University of New York
TEC-P23.5 – FAST SINGLE-IMAGE UPSAMPLING WITH RELATIVE EDGE GROWTH RATE PRIORSChang SU, Samsung Research AmericaLi TAO, Samsung Research America
TEC-P23.6 – SAMPLING PIECEWISE SMOOTH SIGNALS AND ITS APPLICATION TO IMAGE UP-SAMPLINGXiaoyao WEI, Imperial College LondonPier Luigi DRAGOTTI, Imperial College London
TEC-P27: Visual Signal Analysis Tuesday, 16:30-18:30POSTER Room: POSTER JSession Chair(s): Stanley CHAN, Purdue University
TEC-P27.1 – FAST SPATIALLY VARYING OBJECT MOTION BLUR ESTIMATIONYi ZHANG, University of DaytonKeigo HIRAKAWA, University of Dayton
TEC-P27.2 – VESSEL REGION DETECTION IN CORONARY X-RAY ANGIOGRAMSHamidreza FAZLALI, Isfahan University of TechnologyNader KARIMI, Isfahan University of TechnologyS .M .Reza SOROUSHMEHR, University of Michigan, Ann ArborShashank SINHA, University of Michigan, Ann ArborShadrokh SAMAVI, Isfahan University of TechnologyBrahmajee NALLAMOTHU, University of Michigan, Ann ArborKayvan NAJARIAN, University of Michigan, Ann Arbor
«
152 | ICIP 2015 – Technical Program
TEC-P27.3 – UNDERSTANDING SYMMETRIC SMOOTHING FILTERS VIA GAUSSIAN MIXTURESStanley CHAN, Purdue UniversityTodd ZICKLER, Harvard UniversityYue LU, Harvard University
TEC-P27.4 – A FUZZY APPROACH TO REAL-TIME DIGITAL COLOR REPRODUCTION OF CLOTHING WITH 3D CAMERAFinn WONG, Intel CorporationDonghai DAI, Intel Corporation
TEC-P27.5 – MULTI-OBJECTIVE OPTIMIZATION BASED ON PARAMETER TUNING OF CLAHE TO ACHIEVE DIFFERENT CONTRAST LEVELS IN MEDICAL IMAGESLuis G . MORÉ, Facultad Politécnica - Universidad Nacional de AsunciónJosé Luis VÁZQUEZ NOGUERA, Facultad Politécnica - Universidad Nacional de AsunciónDiego PINTO-ROA, Facultad Politécnica - Universidad Nacional de AsunciónMarcos BRIZUELA, Facultad Politécnica - Universidad Nacional de AsunciónHoracio LEGAL AYALA, Facultad Politécnica - Universidad Nacional de Asunción
TEC-P27.6 – SDM-BSM: A FUSING DEPTH SCHEME FOR HUMAN ACTION RECOGNITIONHong LIU, Shenzhen Graduate School, Peking UniversityLu TIAN, Shenzhen Graduate School, Peking UniversityMengyuan LIU, Shenzhen Graduate School, Peking UniversityHao TANG, Shenzhen Graduate School, Peking University
TEC-P3: Computer-assisted Screening and Diagnosis Tuesday, 16:30-18:30POSTER Room: POSTER KSession Chair(s): Seong Tae KIM, KAIST
TEC-P3.1 – REGION MATCHING BASED ON LOCAL STRUCTURE INFORMATION IN IPSILATERAL DIGITAL BREAST TOMOSYNTHESIS VIEWSSeong Tae KIM, KAISTDae Hoe KIM, KAISTDong Jin JI, KAISTYong Man RO, KAIST
TEC-P3.2 – PREDICTION OF FACIAL SOFT TISSUE DEFORMATIONS WITH IMPROVED RUBIN-BODNER MODEL AFTER CRANIOMAXILLOFACIAL (CMF) SURGERYGuangming ZHANG, Wake Forest University School of MedicineJames J XIA, The Methodist Hospital Research InstituteXiaoyan ZHANG, The Methodist Hospital Research InstituteXiaobo ZHOU, Wake Forest University School of Medicine
TEC-P3.3 – FEATURES-BASED APPROACH FOR ALZHEIMER’S DISEASE DIAGNOSIS USING VISUAL PATTERN OF WATER DIFFUSION IN TENSOR DIFFUSION IMAGINGOlfa BEN AHMED, University Of BordeauxJenny BENOIS-PINEAU, Laboratoire Bordelais de Recherches en Informatique (LaBRI)Chokri BEN AMAR, University of SfaxMichelle ALLARD, University of BordeauxGwenaelle CATHELINE, University of Bordeaux
ICIP 2015 – Technical Program | 153
TEC-P3.4 – MODEL-BASED (PASSIVE) HEART RATE ESTIMATION USING REMOTE VIDEO RECORDING OF MOVING HUMAN SUBJECTS ILLUMINATED BY AMBIENT LIGHTJacob GUNTHER, Utah State UniversityNathan RUBEN, Utah State UniversityTodd MOON, Utah State University
TEC-P3.5 – COMPUTER AIDED ENDOSCOPE DIAGNOSIS VIA WEAKLY LABELED DATA MININGShuai WANG, State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of SciencesYang CONG, State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of SciencesHuijie FAN, State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of SciencesYunsheng YANG, Chinese PLA General HospitalYandong TANG, State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of SciencesHuaici ZHAO, State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences
TEC-P5: Energy- and Graph-based Approaches Tuesday, 16:30-18:30POSTER Room: POSTER GSession Chair(s): Kenneth ROSE, University of California, Santa Barbara
TEC-P5.1 – SEGMENTATION OF CELLS IN ELECTRON MICROSCOPY IMAGES THROUGH MULTIMODAL LABEL TRANSFERRenuka SHENOY, University of California, Santa BarbaraMin-chi SHIH, University of California, Santa BarbaraKenneth ROSE, University of California, Santa Barbara
TEC-P5.2 – DYNAMIC BI-MODAL FUSION OF IMAGES FOR THE SEGMENTATION OF POLLEN TUBES IN VIDEOAsongu TAMBO, University of California RiversideBir BHANU, University of California Riverside
TEC-P5.3 – COST AGGREGATION TABLE: A THEORETIC DERIVATION ON THE MARKOV RANDOM FIELD AND ITS RELATION TO MESSAGE PASSINGJeongmok HA, Pohang University of Science and Technology (POSTECH)Byeongchan JEON, Pohang University of Science and Technology (POSTECH)Sung Yong JO, Pohang University of Science and Technology (POSTECH)Jeayoung JEON, Pohang University of Science and Technology (POSTECH)Hong JEONG, Pohang University of Science and Technology (POSTECH)
TEC-P5.4 – AUTOMATIC SEGMENTATION OF NATURAL IMAGES WITH ANISOTROPIC FAST MARCHING ALGORITHM AND GEODESIC VOTINGVijaya Kumar GHORPADE, Institut Pascal, CEREMADELaurent COHEN, University Paris Dauphine, CEREMADE
«
«
154 | ICIP 2015 – Technical Program
TEC-P5.5 – SEGMENTATION OF LIVER TUMOR VIA NONLOCAL ACTIVE CONTOURSBin CHEN, Southeast UniversityYang CHEN, Southeast UniversityGuanyu YANG, Southeast UniversityJingyu MENG, Southeast UniversityRui ZENG, Southeast UniversityLimin LUO, Southeast University
TEC-P5.6 – SEGMENTATION OF INFANT BRAIN MR IMAGES BASED ON ADAPTIVE SHAPE PRIOR AND HIGHER-ORDER MGRFMarwa ISMAIL, University of LouisvilleMahmoud MOSTAPHA, University of LouisvilleAhmed SOLIMAN, University of LouisvilleMatt NITZKEN, University of LouisvilleFahmi KHALIFA, University of LouisvilleAhmed ELNAKIB, University of LouisvilleGeorgy GIMEL’FARB, University of AucklandManuel CASANOVA, University of LouisvilleAyman EL-BAZ, University of Louisville
YPE-E: SPS Young Professionals and Practicing Engineers Networking Event
Tuesday, 17:00-19:00
SOCIAL EVENT Room: NATIONAL ASSEMBLY LIBRARY
Session Chair(s): Mahsa POURAZAD, TELUS Paul FORTIER, Laval University
ICIP 2015 – Technical Program | 155
WEDNESDAY SEPTEMBER 30
PLE-N3: Plenary – Challenges and Opportunities in Biological Imaging Wednesday, 09:00-10:00PLENARY Room: 200ABSession Chair(s): Stéphane COULOMBE, École de technologie supérieure Kenneth ROSE, University of California
PresenterMichael Unser, Professor, EPFL Biomedical Imaging Group
Summary While the major achievements in medical imaging can be traced back to the end the 20th century, there are strong indicators that we have recently entered the golden age of cellular/biological imaging. The enabling modality is fluorescence microscopy which results from the combination of highly specific fluorescent probes (Nobel Prize 2008) and sophisticated optical instrumentation (Nobel Prize 2014). Modern microscopy centers are providing biologists with unprecedented amounts of data in 3D + time. To address the computational aspects, two nascent fields have emerged in which image processing is expected to play a significant role. The first is “digital optics” where the idea is to combine optics with advanced signal processing in order to increase spatial resolution while reducing acquisition time. The second area is “bioimage informatics” which is concerned with the development of image analysis software to make microscopy more quantitative. The key issue here is reliable image segmentation as well as the ability to track structures of interest over time. We shall discuss specific examples and describe state-of-the-art solutions for bioimage reconstruction and analysis. This will help us build a list of challenges and opportunities to guide further research in bioimaging.
ARS-O8: Image Segmentation III Wednesday, 10:30-12:30LECTURE Room: 205ASession Chair(s): Christian DESROSIERS, École de technologie supérieure
10:30 ARS-O8-4 – USER INTERACTIVE SEGMENTATION WITH PARTIALLY GROWING RANDOM FORESTJongwon CHOI, Seoul National University, ASRIJin Young CHOI, Seoul National University, ASRI
10:50 « ARS-O8.2 – A NEW MUMFORD-SHAH TYPE MODEL INVOLVING A SMOOTHING OPERATOR FOR MULTIPHASE IMAGE SEGMENTATIONYing GU, Institute for Infocomm ResearchWei XIONG, Institute for Infocomm ResearchLi-lian WANG, Nanyang Technological UniversityJierong CHENG, Institute for Infocomm ResearchJia DU, Institute for Infocomm ResearchWenyu CHEN, Institute for Infocomm ResearchYue WANG, Institute for Infocomm ResearchShue Ching CHIA, Institute for Infocomm Research
156 | ICIP 2015 – Technical Program
11:10 ARS-O8.3 – FIXATION POINT-BASED IMAGE SEGMENTATION USING RANDOM WALK MODELCheolkon JUNG, Xidian UniversityXiao TIAN, Xidian University
11:30 ARS-O8-1 – NANO-SCALE CONTEXT-SENSITIVE SEMANTIC SEGMENTATIONNan ZHAO, Florida State UniversityXiuwen LIU, Florida State University
11:50 ARS-O8.5 – A SPARSE CODING METHOD FOR SEMI-SUPERVISED SEGMENTATION WITH MULTI-CLASS HISTOGRAM CONSTRAINTSStefan KARNYACZKI, École de technologie supérieureChristian DESROSIERS, École de technologie supérieure
12:10 ARS-O8.6 – UNSUPERVISED HIERARCHICAL IMAGE SEGMENTATION BASED ON BAYESIAN SEQUENTIAL PARTITIONINGHao-Wei YEH, Department of Electronics Engineering, National Chiao Tung University, TaiwanChen-Yu TSENG, Department of Electronics Engineering, National Chiao Tung University, TaiwanTung-Yu WU, Institute for Computational and Mathematical Engineering, Stanford UniversitySheng-Jyh WANG, Department of Electronics Engineering, National Chiao Tung University
ARS-P1: Action Detection and Recognition I Wednesday, 10:30-12:30POSTER Room: POSTER ASession Chair(s): Anastasios TEFAS, Aristotle University of Thessaloniki
ARS-P1.1 – ACTION RECOGNITION WITH APPROXIMATE SPARSE CODINGYu WANG, Nagoya UniversityJien KATO, Nagoya University
ARS-P1.2 – MULTI-VIEW DESCRIPTOR MINING VIA CODEWORD NET FOR ACTION RECOGNITIONJingyu LIU, National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of SciencesYongzhen HUANG, National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of SciencesXiaojiang PENG, Hengyang Normal UniversityLiang WANG, National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences
ARS-P1.3 – TRAFFIC ACCIDENT DETECTION THROUGH A HYDRODYNAMIC LENSHabib ULLAH, University of TrentoMohib ULLAH, University of TrentoHina AFRIDI, University of TrentoNicola CONCI, University of TrentoFrancesco G .B . DE NATALE, University of Trento
ARS-P1.4 – JOINT CLASSIFICATION OF ACTIONS WITH MATRIX COMPLETIONSushma BOMMA, Heriot-Watt UniversityNeil ROBERTSON, Heriot-Watt University
«
ICIP 2015 – Technical Program | 157
ARS-P1.5 – MULTI-LEVEL ACTION DETECTION VIA LEARNING LATENT STRUCTUREBehzad BOZORGTABAR, University of CanberraRoland GOECKE, University of Canberra
ARS-P1.6 – 3-D SKELETON JOINTS-BASED ACTION RECOGNITION USING COVARIANCEDESCRIPTORS ON DISCRETE SPHERICAL HARMONICS TRANSFORMAdnan AL ALWANI, GREYC CNRS (UMR 6072), University of Caen Basse-NormandieYoussef CHAHIR, GREYC CNRS (UMR 6072), University of Caen Basse-Normandie
ARS-P47: Action Detection and Recognition II Wednesday, 10:30-12:30POSTER Room: POSTER BSession Chair(s): Anastasios TEFAS, Aristotle University of Thessaloniki
ARS-P47.1 – ACTIVE IMAGE PAIR SELECTION FOR CONTINUOUS PERSON RE-IDENTIFICATIONAbir DAS, University of California, RiversideRameswar PANDA, University of California, RiversideAmit ROY-CHOWDHURY, University of California, Riverside
ARS-P47.2 – MERGING LINEAR DISCRIMINANT ANALYSIS WITH BAG OF WORDS MODEL FOR HUMAN ACTION RECOGNITIONAlexandros IOSIFIDIS, Aristotle University of ThessalonikiAnastasios TEFAS, Aristotle University of ThessalonikiIoannis PITAS, Aristotle University of Thessaloniki
ARS-P47.3 – DEEP CCA BASED SUPER VECTOR FOR ACTION RECOGNITIONDongqi CAI, Beijing University of Posts and TelecommunicationsFei SU, Beijing University of Posts and Telecommunications
ARS-P47.4 – SPATIO-TEMPORAL PYRAMID CUBOID MATCHING FOR ACTION RECOGNITION USING DEPTH MAPSBin LIANG, Charles Sturt UniversityLihong ZHENG, Charles Sturt University
ARS-P47.5 – LOCAL MEAN SPATIO-TEMPORAL FEATURE FOR DEPTH IMAGE-BASED SPEED-UP ACTION RECOGNITIONXiaopeng JI, Shenzhen Institutes of Advanced Technology, CASJun CHENG, Shenzhen Institutes of Advanced Technology, CASDapeng TAO, Shenzhen Institutes of Advanced Technology, CAS
ARS-P47.6 – ACTION RECOGNITION USING JOINT COORDINATES OF 3D SKELETON DATATamal BATABYAL, University of VirginiaTanushyam CHATTOPADHYAY, TCSDipti Prasad MUKHERJEE, Indian Statistical Institute
ARS-P52: Activity and Face Recognition Wednesday, 10:30-12:30POSTER Room: POSTER CSession Chair(s): Rolf Hugh BAXTER, Heriot-Watt University
ARS-P52.1 – ADAPTIVE APPEARANCE LEARNING FOR HUMAN POSE ESTIMATIONLei WANG, Shanghai Jiao Tong UniversityXu ZHAO, Shanghai Jiao Tong UniversityYuncai LIU, Shanghai Jiao Tong University
158 | ICIP 2015 – Technical Program
ARS-P52.2 – BOOSTED HUMAN HEAD POSE ESTIMATION USING KINECT CAMERAAnwar SAEED, Institute for Information Technology and Communications (IIKT)Ayoub AL-HAMADI, Institute for Information Technology and Communications (IIKT)
ARS-P52.3 – INSTANTANEOUS REAL-TIME HEAD POSE AT A DISTANCESankha Subhra MUKHERJEE, Heriot-Watt UniversityRolf Hugh BAXTER, Heriot-Watt UniversityNeil ROBERTSON, Heriot-Watt University
ARS-P52.4 – ACCURATE HUMAN POSE ESTIMATION BY AGGREGATING MULTIPLE POSE HYPOTHESES USING MODIFIED KERNEL DENSITY APPROXIMATIONEunji CHO, Pohang University of Science and TechnologyYeonho KIM, Pohang University of Science and TechnologyDaijin KIM, Pohang University of Science and Technology
ARS-P52.5 – CROSS-MODALITY POSE-INVARIANT FACIAL EXPRESSIONJordan HASHEMI, Duke UniversityQiang QIU, Duke UniversityGuillermo SAPIRO, Duke University
COM-P4: Media Analysis and Understanding Wednesday, 10:30-12:30POSTER Room: POSTER NSession Chair(s): Dan GELB, HP Labs
COM-P4.1 – REPOSITIONING THE SALIENT REGION OF VIDEOS BY USING ACTIVE ILLUMINATIONRene TEIXEIRA, The University of TokyoKiyoharu AIZAWA, The University of Tokyo
COM-P4.2 – LOCAL EXTREMA BASED DIGITAL DROPOUT DETECTION IN DEGRADED ARCHIVED MEDIAGihun SONG, Kyung Hee UniversityJaemyun KIM, Kyung Hee UniversityKiok AHN, Kyung Hee UniversityOksam CHAE, Kyung Hee University
COM-P4.3 – AUDIOVISUAL VOICE ACTIVITY DETECTION USING OFF-THE-SHELF CAMERASSergio MONTAZZOLLI SILVA, Federal University of Rio Grande do SulClaudio ROSITO JUNG, Federal University of Rio Grande do SulDan GELB, HP Labs
COM-P4.4 – PREDICTING AUDIO-VISUAL SALIENT EVENTS BASED ON VISUAL, AUDIO AND TEXT MODALITIES FOR MOVIE SUMMARIZATIONPetros KOUTRAS, National Technical University of AthensAthanasia ZLATINTSI, National Technical University of AthensElias IOSIF, National Technical University of AthensAthanasios KATSAMANIS, National Technical University of AthensPetros MARAGOS, National Technical University of AthensAlexandros POTAMIANOS, National Technical University of Athens
«
ICIP 2015 – Technical Program | 159
COM-P4.5 – DYNAMIC TEXTURE AND GEOMETRY FEATURES FOR FACIAL EXPRESSION RECOGNITION IN VIDEOJunkai CHEN, The Hong Kong Polytechnic UniversityZenghai CHEN, The Hong Kong Polytechnic UniversityZheru CHI, The Hong Kong Polytechnic UniversityHong FU, The Hong Kong Polytechnic University
COM-P4.6 – ESTIMATION OF ANGULAR DIFFERENCE BETWEEN TOMOGRAPHIC PROJECTIONS TAKEN AT UNKNOWN DIRECTIONS IN 3DMinh Son PHAN, University of StrasbourgÉtienne BAUDRIER, University of StrasbourgLoïc MAZO, University of StrasbourgMohamed TAJINE, University of Strasbourg
COM-P6: Video Communication and Networking Wednesday, 10:30-12:30POSTER Room: POSTER OSession Chair(s): Akshaya MISHRA, University of Waterloo
COM-P6.1 – AN ADAPTIVE LAGRANGE MULTIPLIER DETERMINATION METHOD FOR RATE-DISTORTION OPTIMISATION IN HYBRID VIDEO CODECSFan ZHANG, University of BristolDavid BULL, University of Bristol
COM-P6.2 – INFORMATION-THEORETIC ANALYSIS OF BLINN-PHONG LIGHTING WITH APPLICATION TO MOBILE CLOUD GAMINGSeong Ping CHUAH, Singapore University of Technology & DesignNgai-Man CHEUNG, Singapore University of Technology & DesignChau YUEN, Singapore University of Technology & Design
COM-P6.3 – USER ADAPTIVE TRANSCODING FOR VIDEO TELECONFERENCINGLiangping MA, InterDigital Communications, Inc.Dharm VEER, InterDigital Communications, Inc.Wei CHEN, InterDigital Communications, Inc.Gregory STERNBERG, InterDigital Communications, Inc.Yuriy REZNIK, InterDigital Communications, Inc.Ralph NEFF, InterDigital Communications, Inc.
COM-P6.4 – MODELING OF H .264/AVC BASED VIDEO TRANSMISSION DISTORTION OVER WIRELESS NETWORKGuizhong LIU, Xi’an Jiaotong UniversityRui DENG, Xi’an Jiaotong University
COM-P6.5 – SERVICE PROVISIONING AND PROFIT MAXIMIZATION IN NETWORK-ASSISTED ADAPTIVE HTTP STREAMINGZhisheng YAN, State University of New York at BuffaloCedric WESTPHAL, Huawei US R&D Center and UCSCXin WANG, Huawei US R&D CenterChang Wen CHEN, State University of New York at Buffalo
160 | ICIP 2015 – Technical Program
COM-P6.6 – CLUSTER ENCODING FOR MODELLING THE TEMPORAL VARIATION IN VIDEONegar ROSTAMZADEH, DISI, University of Trento, ItalyJasper UIJLINGS, CALVIN group, University of EdinburghIonut MIRONICA, LAPI, University Politehnica of Bucharest, RomaniaMojtaba KHOMAMI ABADI, DISI, University of Trento, ItalyBogdan IONESCU, LAPI, University Politehnica of BucharestNicu SEBE, DISI, University of Trento, Italy
ELI-O6: Multiview Processing Wednesday, 10:30-12:30LECTURE Room: 202Session Chair(s): Atanas GOTCHEV, Tampere University of Technology
10:30 ELI-O6.1 – GUIDED INTEGRAL FILTER FOR LIGHT FIELD STEREO MATCHINGHao SHENG, Beihang UniversityShuo ZHANG, Beihang University Gengliang ZHU, Beihang University Zhang XIONG, Beihang University
10:50 ELI-O6.2 – EFFICIENT COST VOLUME SAMPLING FOR PLANE SWEEPING BASED MULTIVIEW DEPTH ESTIMATIONOlli SUOMINEN, Tampere University of TechnologyAtanas GOTCHEV, Tampere University of Technology
11:10 ELI-O6.3 – LQ-BUNDLE ADJUSTMENTKhurrum AFTAB, Australian National UniversityRichard HARTLEY, Australian National University
11:30 ELI-O6.4 – SUPER-RESOLUTION FOR MIXED-RESOLUTION MULTIVIEW IMAGE PLUS DEPTH DATA USING A NOVEL TWO-STAGE HIGH-FREQUENCY EXTRAPOLATION METHOD FOR OCCLUDED AREASThomas RICHTER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Jürgen SEILER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)Wolfgang SCHNURRER, Friedrich-Alexander University Erlangen-Nürnberg (FAU)André KAUP, Friedrich-Alexander University Erlangen-Nürnberg (FAU)
11:50 ELI-O6.5 – A DATABASE OF REFLECTED IRRADIANCE FIELD WITH DEPTH FOR IMAGE BASED RELIGHTINGYou YANG, Huazhong University of Science and TechnologyQiong LIU, Huazhong University of Science and Technology
12:10 ELI-O6.6 – OPTIMIZED MULTILEVEL FRINGE PATTERNS FOR REAL-TIME 3D SHAPE MEASUREMENT WITH DEFOCUSED PROJECTORZi-Xin XU, The Hong Kong Polytechnic UniversityYuk Hee CHAN, The Hong Kong Polytechnic University
ICIP 2015 – Technical Program | 161
ELI-P6: Hardware, Parallel, and Distributed System Wednesday, 10:30-12:30POSTER Room: POSTER JSession Chair(s): Vladan POPOVIC, EPFL
ELI-P6.1 – MITIGATING MEMORY REQUIREMENTS FOR RANDOM TREES/FERNSChristophe DE VLEESCHOUWER, Université catholique de LouvainAnthony LEGRAND, Université catholique de LouvainLaurent JACQUES, Université catholique de Louvain
ELI-P6.2 – A COMPLEXITY-BASED ADAPTIVE TILE PARTITIONING ALGORITHM FOR HEVC DECODER PARALLELIZATIONHwangjun SONG, POSTECH (Pohang University of Science and Technology)Hyunki BAIK, POSTECH (Pohang University of Science and Technology)
ELI-P6.3 – SVM WITH OPENCL: HIGH PERFORMANCE IMPLEMENTATION OF SUPPORT VECTOR MACHINES ON HETEROGENEOUS SYSTEMSEthan PETERS, Rochester Institute of TechnologyAndreas SAVAKIS, Rochester Institute of Technology
ELI-P6.4 – A LOW-POWER 490 MPIXELS/S HARDWARE ACCELERATOR FOR PYRAMIDAL DECOMPOSITION OF IMAGESVladan POPOVIC, EPFLYusuf LEBLEBICI, EPFL
ELI-P6.5 – HEVC INVERSE TRANSFORM ARCHITECTURE UTILIZING COEFFICIENT SPARSITYMaleen ABEYDEERA, University of MoratuwaAjith PASQUAL, University of Moratuwa
ELI-P6.6 – FAST 2D AND 3D IMAGE PROCESSING WITH OPENCLDaniel Oliveira DANTAS, Universidade Federal de SergipeHelton Danilo Passos LEAL, Universidade Federal de SergipeDavy Oliveira Barros SOUSA, Universidade Federal de Sergipe
IFS-O2: Multimedia Forensics Wednesday, 10:30-12:30LECTURE Room: 203Session Chair(s): Gwenaël DOËRR,Technicolor R&D
10:30 IFS-O2.1 – INCREMENTAL UPDATE OF FEATURE EXTRACTOR FOR CAMERA IDENTIFICATIONRuizhe LI, University of WarwickChang-Tsun LI, University of WarwickYu GUAN, University of Warwick
10:50 IFS-O2.2 – IDENTIFICATION OF ALIASING-BASED PATTERNS IN RE-CAPTURED LCD SCREENSBabak MAHDIAN, ASCRAdam NOVOZÁMSKÝ, ASCRStansilav SAIC, ASCR
162 | ICIP 2015 – Technical Program
11:10 IFS-O2.3 – SPATIAL DOMAIN QUANTIZATION NOISE BASED IMAGE FILTERING DETECTIONHareesh RAVI, Indraprastha Institute of Informaiton TechnologySubramanyam VENKATA, Indraprastha Institute of Informaiton TechnologySabu EMMANUEL, Kuwait University
11:30 IFS-O2.4 – IMAGE SPLICING DETECTION WITH LOCAL ILLUMINATION ESTIMATIONYu FAN, University of PoitiersPhilippe CARRÉ, University of PoitiersChristine FERNANDEZ-MALOIGNE, University of Poitiers
11:50 IFS-O2.5 – SOURCE CAMERA DEVICE IDENTIFICATION BASED ON RAW IMAGESTong QIAO, University of Technology of TroyesFlorent RETRAINT, University of Technology of TroyesRemi COGRANNE, University of Technology of TroyesThanh Hai THAI, University of Technology of Troyes
SMR-O4: Visual Aesthetics and Quality Assessment Wednesday, 10:30-12:30LECTURE Room: 204BSession Chair(s): Sabine SÜSSTRUNK, EPFL
10:30 « SMR-O4.1 – A COMPREHENSIVE AESTHETIC QUALITY ASSESSMENT METHOD FOR NATURAL IMAGES USING BASIC RULES OF PHOTOGRAPHYEftichia MAVRIDAKI, Centre for Research and Technology HellasVasileios MEZARIS, Centre for Research and Technology Hellas
10:50 SMR-O4.2 – VISUAL AESTHETIC QUALITY ASSESSMENT WITH A REGRESSION MODELYueying KAO, Institute of Automation, Chinese Academy of SciencesChong WANG, Institute of Automation, Chinese Academy of SciencesKaiqi HUANG, Institute of Automation, Chinese Academy of Sciences
11:10 SMR-O4.3 – REGION-BASED IMAGE RETARGETING QUALITY ASSESSMENTYichi ZHANG, Department of Electronic Engineering, The Chinese University of Hong KongKing Ngi NGAN, Department of Electronic Engineering, The Chinese University of Hong Kong
11:30 SMR-O4.4 – AUTOMATIC ASSESSMENT OF ONLINE FASHION SHOPPING PHOTO AESTHETIC QUALITYJianyu WANG, Purdue UniversityJan ALLEBACH, Purdue University
11:50 SMR-O4.5 – IMAGE AESTHETICS DEPENDS ON CONTEXTFlorian SIMOND, EPFLNikolaos ARVANITOPOULOS, EPFLSabine SÜSSTRUNK, EPFL
12:10 SMR-O4.6 – PATH VS . DESTINATION: A CASE STUDY OF BLIND NOISE ASSESSMENT USING MODIFIED ANT SHORTEST PATHLi CHEN, wuhan university of science and technologyXiaotong HUANG, wuhan university of science and technologyJing TIAN, wuhan university of science and technology
ICIP 2015 – Technical Program | 163
SMR-P10: Video Quality and Image-based Specific Application Assessment Wednesday, 10:30-12:30POSTER Room: POSTER HSession Chair(s): Ghassan ALREGIB, Georgia Institute of Technology
SMR-P10.1 – A VERY LOW COMPLEXITY REDUCED REFERENCE VIDEO QUALITY METRIC BASED ON SPATIO-TEMPORAL INFORMATION SELECTIONMengmeng WANG, University of BristolFan ZHANG, University of BristolDimitris AGRAFIOTIS, University of Bristol
SMR-P10.2 – AN OBJECTIVE 3D QUALITY ASSESSMENT MODEL TO ADJUST STEREO CAMERA BASELINEMarcelo MIGUEL, National Institute of Industrial PropertyCarla PAGLIARI, Military Institute of EngineeringEduardo SILVA, Federal University of Rio de JaneiroMarcelo PEREZ, Military Institute of Engineering
SMR-P10.3 – PERCEPTUAL EVALUATION OF SINGLE IMAGE DEHAZING ALGORITHMSKede MA, University of WaterlooWentao LIU, University of WaterlooZhou WANG, University of Waterloo
SMR-P10.4 – OBJECTIVE QUALITY METRIC FOR 3D VIRTUAL VIEWSMuhammad Shahid FARID, Universita’ di TorinoMaurizio LUCENTEFORTE, Universita’ di TorinoMarco GRANGETTO, Universita’ di Torino
SMR-P10.5 – A CURVELET-BASED DISTANCE MEASURE FOR SEISMIC IMAGESYazeed ALAUDAH, Georgia Institute of TechnologyGhassan ALREGIB, Georgia Institute of Technology
SMR-P10.6 – BLIND MULTIPLY DISTORTED IMAGE QUALITY ASSESSMENT USING RELEVANT PERCEPTUAL FEATURESChaofeng LI, Jiangnan Univ.Yu ZHANG, Jiangnan Univ.Xiaojun WU, Jiangnan Univ.Wei FANG, Jiangnan Univ.Li MAO, Jiangnan Univ.
SNT-S7: Show & Tell VII Wednesday, 10:30-12:30SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S7.1 – LANDMARK DETECTION AND 3D FACE RECONSTRUCTION USING MODERN C++Patrik HUBER, Centre for Vision, Speech and Signal Processing, University of SurreyZenhua FENG, Centre for Vision, Speech and Signal Processing, University of SurreyThis demonstration will contain a live presentation of a novel 3D face fitting technique . It will run on a webcam and people will be able to try it out live . A second am of this demonstration is to present accompanying libraries for 2D landmark detection and 3D Morphable Face Model fitting that are available as source code on Github
164 | ICIP 2015 – Technical Program
SNT-S7.2 – HOW TO TRACK YOU HEART RATE WITH A CAMERA WHILE EXERCISINGJacob GUNTHER, Utah State UniversityNathan RUBEN, Utah State UniversityWe propose to demonstrate a system in which a stationary machine, such as a treadmill or exercise bike, can be fitted with a simple camera which accurately tracks the heart rate of the user . Participants will be recorded during a short exercise period during the demo, and the system will be used to estimate heart rate .
SNT-S7.3 – BARCODES - A NEW GENERATION OF BINARY DESCRIPTORSHamid R . TIZHOOSH, Univerisity of WaterlooIn this demo, we will demonstrate how content-based barcodes are generated to annotate digital images . Both automated and manual barcode generation will be demonstrated . The demo consists of both a training phase in which barcodes are extracted and stored, and a retrieval phase in which similar images are found for give input images . The audience can participate to challenge the software by selecting input images (e .g . from available data or from Internet)
SNT-S7.4 – AUTOMATIC SEGMENTATION OF NATURAL IMAGE WITH ANISOTROPIC FAST MARCHING ALGORITHM AND GEODESIC VOTINGVijaya Kumar GHORPADE, University Paris Dauphine, CEREMADEWe will demonstrate a method for complete automation of segmentation . Seeds and Tips are automatically detected, and geodesics are calculated using Anisotropic Fast Marching algorithm . Fast marching algorithm computes in a single pass, the evolution of the front, at a speed locally given by its position .
SS10-O1: Perceptual Video Compression – for HEVC and Beyond Wednesday, 10:30-12:30LECTURE Room: 205BSession Chair(s): Sebastian SCHWARZ, BBC Research & Development David BULL, University of Bristol Patrick LE CALLET, Université de Nantes
10:30 SS10-O1.1 – A NO REFERENCE TEXTURE GRANULARITY INDEX AND APPLICATION TO VISUAL MEDIA COMPRESSIONMahesh SUBEDAR, Arizona State UniversityLina J . KARAM, Arizona State University
10:50 SS10-O1.2 – PERCEPTUAL SCREEN CONTENT IMAGE QUALITY ASSESSMENT AND COMPRESSIONShiqi WANG, Dept. of Electrical and Computer Engineering, University of WaterlooKe GU, Shanghai Jiao Tong UniversityKai ZENG, Dept. of Electrical and Computer Engineering, University of WaterlooZhou WANG, Dept. of Electrical and Computer Engineering, University of WaterlooWeisi LIN, Nanyang Technological University
11:10 SS10-O1.3 – ADAPTIVE QUANTISATION IN HEVC FOR CONTOURING ARTEFACTS REMOVAL IN UHD CONTENTNicolo CASALI, BBC R&D - Università degli studi di BresciaMatteo NACCARI, BBC R&DMarta MRAK, BBC R&DRiccardo LEONARDI, Università degli studi di Brescia
ICIP 2015 – Technical Program | 165
11:30 SS10-O1.4 – A VIDEO TEXTURE DATABASE FOR PERCEPTUAL COMPRESSION AND QUALITY ASSESSMENTMiltiadis Alexios PAPADOPOULOS, University of BristolFan ZHANG, University of BristolDimitris AGRAFIOTIS, University of BristolDavid BULL, University of Bristol
11:50 SS10-O1.5 – A FRAME LEVEL METRIC FOR JUST NOTICEABLE TEMPORAL PUMPING ARTIFACT IN VIDEOS ENCODED WITH THE HIERARCHICAL PREDICTION STRUCTUREYanchao GONG, Northwestern Polytechnical UniversityShuai WAN, Northwestern Polytechnical UniversityFuzheng YANG, xidian UniversityHong Ren WU, Royal Melbourne Institute of TechnologyBo LI, Northwestern Polytechnical University
SS1-P1: Industry Special Session I Wednesday, 10:30-12:30POSTER Room: POSTER KSession Chair(s): Tong ZHANG, Hewlett-Packard Labs
SS1-P1.1 – APPLYING IMAGE ANALYSIS TO ASSESS FOOD AESTHETICS AND UNIQUENESSYing LI, IBM T. J. Watson Research CenterAnshul SHEOPURI, IBM T. J. Watson Research Center
SS1-P1.2 – SOFTWARE DEFINED NETWORKING FOR VIDEO: OVERVIEW AND EXAMPLEWai-Tian TAN, Cisco SystemsHerb WILDFEUER, Cisco SystemsJohn APOSTOLOPOULOS, Cisco Systems
SS1-P1.3 – 360 DEGREES VIDEO CODING USING REGION ADAPTIVE SMOOTHING Madhukar BUDAGAVI, Samsung Research America, DallasJohn FURTON, Samsung Research America, DallasGuoxin JIN, Northwestern UniversityAnkur SAXENA, Samsung Research America, DallasJeffrey WILKINSON, Samsung Research America, DallasAndrew DICKERSON, Samsung Research America, Dallas
SS1-P1.4 – BRIDGING COMPUTER VISION AND SOCIAL SCIENCE: A MULTI-CAMERA VISION SYSTEM FOR SOCIAL INTERACTION TRAINING ANALYSISJixu CHEN, GE Global ResearchMing-Ching CHANG, GE Global ResearchTai-Peng TIAN, GE Global ResearchTing YU, GE Global ResearchPeter TU, GE Global Research
«
166 | ICIP 2015 – Technical Program
SS1-P1.5 – COMPUTATIONALLY EFFICIENT, REAL-TIME MOTION RECOGNITION BASED ON BIO-INSPIRED VISUAL AND COGNITIVE PROCESSINGPaul K . J . PARK, Samsung ElectronicsKyoobin LEE, Samsung ElectronicsJun Haeng LEE, Samsung ElectronicsByungkon KANG, Samsung ElectronicsChang-Woo SHIN, Samsung ElectronicsJooyeon WOO, Samsung ElectronicsJun-Seok KIM, Samsung ElectronicsYunjae SUH, Samsung ElectronicsSungho KIM, Samsung ElectronicsSaber MORADI, Samsung ElectronicsOgan GUREL, Samsung ElectronicsHyunsurk RYU, Samsung Electronics
SS1-P2: Industry Special Session II Wednesday, 10:30-12:30POSTER Room: POSTER LSession Chair(s): Tong ZHANG, Hewlett-Packard Labs
SS1-P2.1 – PIRM: FAST BACKGROUND SUBTRACTION UNDER SUDDEN, LOCAL ILLUMINATION CHANGES VIA PROBABILISTIC ILLUMINATION RANGE MODELLINGParthipan SIVA, Aimetis CorpMohammad Javad SHAFIEE, University of WaterlooFrancis LI, University of WaterlooAlexander WONG, University of Waterloo
SS1-P2.2 – TEXTURELESS OBJECT DETECTION USING CUMULATIVE ORIENTATION FEATUREYoshihisa IJIRI, OMRON CorporationMasaki SUWA, OMRON CorporationMasato KAWADE, OMRON CorporationYoshinori KONISHI, OMRON Corporation
SS1-P2.3 – RETURN OF GRID SEAMS: A SUPERPIXEL ALGORITHM USING DISCONTINUOUS MULTI-FUNCTIONAL ENERGY SEAM CARVINGParthipan SIVA, Aimetis CorpChristian SCHARFENBERGER, University of WaterlooIbrahim DAYA, University of WaterlooAkshaya MISHRA, University of WaterlooAlexander WONG, University of Waterloo
SS1-P2.4 – CHALLENGES IN CLOUD BASED INGEST AND ENCODING FOR HIGH QUALITY STREAMING MEDIAAnne AARON, NetflixZhi LI, NetflixMegha MANOHARA, NetflixJoe Yuchieh LIN, University of Southern CaliforniaEddy Chi-Hao WU, University of Southern CaliforniaC .-C . Jay KUO, University of Southern California
ICIP 2015 – Technical Program | 167
SS1-P2.5 – DREM: DECOUPLED REGION ENERGY MODEL FOR IMAGE SEGMENTATIONAkshaya MISHRA, Miovision TechnologiesJustin EICHEL, Miovision TechnologiesTyler ABBOTT, Miovision Technologies
SS1-P2.6 – LOW-COMPLEXITY HOG FOR EFFICIENT VIDEO SALIENCYTeahyung LEE, IntelMyung HWANGBO, IntelTanfer ALAN, Computer Systems Group, TU DarmstadtOmesh TICKOO, IntelRavishankar IYER, Intel
SS1-P3: Industry Special Session III Wednesday, 10:30-12:30POSTER Room: POSTER MSession Chair(s): Tong ZHANG, Hewlett-Packard Labs
SS1-P3.1 – A TWO-STAGE VIDEO OBJECT SEGMENTATION USING MOTION AND COLOR INFORMATIONMarc BOSCH, Qualcomm, Inc.Guiqin LI, Qualcomm, Inc.Kai WANG, Qualcomm, Inc.
SS1-P3.2 – HYPER-PARAMETER OPTIMIZATION OF DEEP CONVOLUTIONAL NETWORKS FOR OBJECT RECOGNITIONSachin TALATHI, Qualcomm Inc
SS1-P3.3 – THE EMBEDDABILITY OF LANE DETECTION ALGORITHMS ON HETEROGENEOUS ARCHITECTURESRomain SAUSSARD, Renault S.A.S.Boubker BOUZID, Renault S.A.S.Marius VASILIU, Institut d’Électronique Fondamentale - Université Paris SudRoger REYNAUD, Institut d’Electronique Fondamentale - Université Paris Sud
TEC-O7: Automated Segmentation of Radiology images Wednesday, 10:30-12:30LECTURE Room: 204ASession Chair(s): Michel DESVIGNES, Grenoble-INP/ GIPSA-LAB
10:30 TEC-O7.1 – CENTER-FREE PFCM FOR MRI BRAIN IMAGE SEGMENTATIONXiangzhi BAI, Image Processing Center, Beihang UniversityZhiguo CHEN, Image Processing Center, Beihang UniversityMiaoming LIU, Image Processing Center, Beihang UniversityYu ZHANG, Image Processing Center, Beihang University
«
«
168 | ICIP 2015 – Technical Program
10:50 TEC-O7.2 – HIERARCHICAL SEGMENTATION AND TRACKING OF CORONARY ARTERIES IN 2D X-RAY ANGIOGRAPHY SEQUENCESFaten M’HIRI, École de technologie supérieureNgan LE T . HOANG, Carnegie Mellon UniversityLuc DUONG, École de technologie supérieureChristian DESROSIERS, École de technologie supérieureMohamed CHERIET, École de technologie supérieure
11:10 TEC-O7.3 – LIVER SEGMENTATION USING SUPERPIXEL-BASED GRAPH CUTS AND RESTRICTED REGIONS OF SHAPE CONSTRAINSTitinunt KITRUNGROTSAKUL, Ritsumeikan UniversityXian-Hua HAN, Ritsumeikan UniversityYen-Wei CHEN, Ritsumeikan University
11:30 TEC-O7.4 – SEGMENTATION OF PATHOLOGICAL LUNGS FROM CT CHEST IMAGESAhmed SOLIMAN, University of LouisvilleAhmed ELNAKIB, University of LouisvilleFahmi KHALIFA, University of LouisvilleMohamed ABOU EL-GHAR, Mansoura UniversityAyman EL-BAZ, University of Louisville
11:50 TEC-O7.5 – DISC SEGMENTATION AND BMO-MRW MEASUREMENT FROM SD-OCT IMAGE USING GRAPH SEARCH AND TRACING OF THREE BENCH MARK LAYERS OF RETINAMd Akter HUSSAIN, The University of MelbourneAlauddin BHUIYAN, The University Of MelbourneKotagiri RAMAMOHANARAO, The University Of Melbourne
12:10 TEC-O7.6 – MYOCARDIUM SEGMENTATION ON 3D SPECT IMAGESJ . POUJOL, GIPSA-LAB, UMR 5216Michel DESVIGNES, GIPSA-LAB, UMR 5216A . BROISAT, GIPSA-LAB, UMR 5216G . BARONE-ROCHETTE, GIPSA-LAB, UMR 5216G . VANZETTO, GIPSA-LAB, UMR 5216D . fa*gRET, GIPSA-LAB, UMR 5216L . RIOU, GIPSA-LAB, UMR 5216C . GHEZZI, GIPSA-LAB, UMR 5216
TEC-P14: Linear and Non-Linear Filtering Wednesday, 10:30-12:30POSTER Room: POSTER GSession Chair(s): Yuichi TANAKA, Tokyo University of Agriculture and Technology
TEC-P14.1 – AN ACCELERATED SEPARABLE MEDIAN FILTER WITH SORTING NETWORKSMinsik KIM, Yonsei UniversityDeokho KIM, Yonsei UniversityMinyong SUNG, Yonsei UniversityWon Woo RO, Yonsei University
ICIP 2015 – Technical Program | 169
TEC-P14.2 – EXTENDING ALPHA-EXPANSION TO A LARGER SET OF REGULARIZATION FUNCTIONSMathias PAGET, IFSTTARJean-Philippe TAREL, IFSTTARLaurent CARAFFA, IGN
TEC-P14.3 – EFFICIENT O(1) EDGE-AWARE FILTERMingcai ZHOU, Samsung Research Center-Beijing, SAIT China LabZhihua LIU, Samsung Research Center-Beijing, SAIT China LabXun SUN, Baidu Institute of Deep Learning, Beijing, ChinaTao HONG, Samsung Research Center-Beijing, SAIT China LabXiying WANG, Samsung Research Center-Beijing, SAIT China LabHaitao WANG, Samsung Research Center-Beijing, SAIT China Lab
TEC-P14.4 – FAST AND ACCURATE BILATERAL FILTERING USING GAUSS-POLYNOMIAL DECOMPOSITIONKunal CHAUDHURY, Indian Institute of Science
TEC-P14.5 – AN ESTIMATION-THEORETIC APPROACH TO VIDEO DENOISEINGJingning HAN, Google Inc.Timothy KOPP, Google Inc.Yaowu XU, Google Inc.
TEC-P14.6 – NON-LOCAL/LOCAL IMAGE FILTERS USING FAST EIGENVALUE FILTERINGMasaki ONUKI, Tokyo University of Agriculture and TechnologyShunsuke ONO, Tokyo Institute of TechnologyKeiichiro SHIRAI, Shinshu UniversityYuichi TANAKA, Tokyo University of Agriculture and Technology
TEC-P21: Parametric and Energy-based Segmentation Wednesday, 10:30-12:30POSTER Room: POSTER ESession Chair(s): Neeraj DHUNGEL, University of Adelaide
TEC-P21.1 – NEW PARAMETRIC 3D SNAKE FOR MEDICAL SEGMENTATION OF STRUCTURES WITH CYLINDRICAL TOPOLOGYDaniel SCHMITTER, EPFLChristophe GAUDET-BLAVIGNAC, EPFLDavide PICCINI, Advanced Clinical Imaging Technology Group, SiemensMichael UNSER, EPFL
TEC-P21.2 – LOCALLY REFINABLE PARAMETRIC SNAKESAnaïs BADOUAL, EPFLDaniel SCHMITTER, EPFLMichael UNSER, EPFL
TEC-P21.3 – AN AUTOMATIC ENERGY-BASED REGION GROWING METHOD FOR ULTRASOUND IMAGE SEGMENTATIONWeining WANG, South China University of TechnologyJiachang LI, South China University of TechnologyYizi JIANG, South China University of TechnologyYi XING, Nanchang Municipal Liver Diseases HospitalXiangmin XU, South China University of Technology
«
170 | ICIP 2015 – Technical Program
TEC-P21.4 – LUNG SEGMENTATION IN CHEST RADIOGRAPHS USING DISTANCE REGULARIZED LEVEL SET AND DEEP-STRUCTURED LEARNING AND INFERENCETuan Anh NGO, The University of AdelaideGustavo CARNEIRO, The University of Adelaide
TEC-P22: Restoration, Denoising and Demosaicking Wednesday, 10:30-12:30POSTER Room: POSTER FSession Chair(s): Jeffrey FESSLER, University of Michigan
TEC-P22.1 – NONPARAMETRIC EMPIRICAL BAYES ESTIMATION FOR MULTIPLICATIVE MULTISCALE INNOVATION IN PHOTON-LIMITED IMAGINGWu CHENG, University of DaytonKeigo HIRAKAWA, University of Dayton
TEC-P22.2 – EFFICIENT REGRESSION PRIORS FOR POST-PROCESSING DEMOSAICED IMAGESJiqing WU, ETH ZurichRadu TIMOFTE, ETH ZurichLuc VAN GOOL, ETH Zurich
TEC-P22.3 – AN OPTIMIZED FIRST-ORDER METHOD FOR IMAGE RESTORATIONDonghwan KIM, University of MichiganJeffrey FESSLER, University of Michigan
TEC-P22.4 – IMAGE COLORIZATION VIA COLOR PROPAGATION AND RANK MINIMIZATIONYonggen LING, Hong Kong University of Science and TechnologyOscar C . AU, Hong Kong University of Science and TechnologyJiahao PANG, Hong Kong University of Science and TechnologyJin ZENG, Hong Kong University of Science and TechnologyYuan YUAN, Hong Kong University of Science and TechnologyAmin ZHENG, Hong Kong University of Science and Technology
TEC-P22.5 – PMPA: A PATCH-BASED MULTISCALE PRODUCTS ALGORITHM FOR IMAGE DENOISINGTao DAI, Tsinghua UniversityChao-Bing SONG, Tsinghua UniversityJi-Ping ZHANG, Tsinghua UniversityShu-Tao XIA, Tsinghua University
TEC-P22.6 – PARAMETER ESTIMATION FOR $L_P$ REGULARIZED IMAGE DECONVOLUTIONXu ZHOU, Beihang UniversityFugen ZHOU, Beihang UniversityXiangzhi BAI, Beihang University
TEC-P6: Focus and Lens Wednesday, 10:30-12:30POSTER Room: POSTER DSession Chair(s): Ivana TOSIC, Ricoh Innovations Corp .
TEC-P6.1 – TRANSFORMATION OF FOCUS PROFILES FOR DIGITAL AUTOFOCUS Dong-Chen TSAI, National Taiwan UniversityHomer CHEN, National Taiwan University
«
«
«
ICIP 2015 – Technical Program | 171
TEC-P6.2 – DEEPFOCAL: A METHOD FOR DIRECT FOCAL LENGTH ESTIMATIONScott WORKMAN, University of KentuckyConnor GREENWELL, University of KentuckyMenghua ZHAI, University of KentuckyRyan BALTENBERGER, University of KentuckyNathan JACOBS, University of Kentucky
TEC-P6.3 – RADIAL LENS DISTORTION CORRECTION USING CASCADED ONE-PARAMETER DIVISION MODELXiang MEI, Peking UniversitySen YANG, Peking UniversityJiangpeng RONG, Peking UniversityXianghua YING, Peking UniversityShiyao HUANG, Peking UniversityHongbin ZHA, Peking University
TEC-P6.4 – PIECEWISE DISTORTION CORRECTION FOR FISHEYE LENSESMarco MARCON, Politecnico di Milano Augusto SARTI, Politecnico di Milano Stefano TUBARO, Politecnico di Milano
TEC-P6.5 – MULTIPLE EXPOSURE INTEGRATION FOR RESTORING ALL IN-FOCUS IMAGESRyo MATSUOKA, The university of kitakyushuHaruki ISHIBASHI, The university of kitakyushuTatsuya BABA, The university of kitakyushuMasahiro OKUDA, The university of kitakyushu
TEC-P6.6 – FOCAL LENGTH CHANGE COMPENSATION FOR MONOCULAR SLAMTakafumi TAKETOMI, Nara Institute of Science and TechnologyJanne HEIKKILÄ, University of Oulu
ARS-O12: Machine Learning and Scene Analysis Wednesday, 14:00-16:00LECTURE Room: 204BSession Chair(s): Benoît HUET, Eurecom
14:00 ARS-O12.1 – RANDOMIZED SPATIAL POOLING IN DEEP CONVOLUTIONAL NETWORKS FOR SCENE RECOGNITIONMu YANG, Tsinghua UniversityBrian LI, Megvii Inc.Yuning JIANG, Megvii Inc.
14:20 ARS-O12.2 – ANOMALY DETECTION BY USING RANDOM PROJECTION FORESTFan CHEN, Japan Advanced Institute of Science and TechnologyZicheng LIU, Microsoft Research RedmondMing-Ting SUN, University of Washington
14:40 ARS-O12.3 – NONPARAMETRIC SCENE PARSING WITH DEEP CONVOLUTIONAL FEATURES AND DENSE ALIGNMENTChiou-Ting HSU, National Tsing Hua UniversityChih-Hao MA, National Tsing Hua UniversityBenoît HUET, Eurecom
172 | ICIP 2015 – Technical Program
15:00 ARS-O12.4 – SWAP NODE: REGULARIZATION APPROACH FOR DEEP CONVOLUTIONAL NEURAL NETWORKTakayoshi YAMAsh*tA, Chubu UniversityMasayuki TANAKA, Tokyo Institute of TechnologyYuji YAMAUCHI, Chubu UniversityHironobu FUJIYOSHI, Chubu University
15:20 ARS-O12.5 – WEATHER CLASSIFICATION WITH DEEP CONVOLUTIONAL NEURAL NETWORKSMohammed ELHOSEINY, Rutgers UniversitySheng HUANG, Chongqing UniversityAhmed ELGAMMAL, Rutgers University
15:40 ARS-O12.6 – CONTEXTUAL KERNEL MAP LEARNING FOR SCENE TRANSDUCTIONPhong VO, CNRS TELECOM ParisTechHichem SAHBI, CNRS TELECOM ParisTech
ARS-O9: Image Segmentation IV Wednesday, 14:00-16:00LECTURE Room: 203Session Chair(s): A . Enis ÇETIN, Bilkent University Oguzhan OGUZ, Bilkent University
14:00 ARS-O9.1 – FINE-GRAINED VISUAL CATEGORIZATION WITH FINE-TUNED SEGMENTATIONLingyun LI, Dalian University of TechnologyYanqing GUO, Dalian University of TechnologyLingxi XIE, Tsinghua UniversityXiangwei KONG, Dalian University of TechnologyQi TIAN, University of Texas at San Antonio
14:20 ARS-O9.2 – DISCRIMINATIVE REGIONAL COLOR CO-OCCURRENCE DESCRIPTORQin ZOU, Wuhan UniversityXianbiao QI, Shenzhen UniversityQingquan LI, Shenzhen UniversitySong WANG, University of South Carolina
14:40 « ARS-O9.3 – PARTIALLY OCCLUDED OBJECT DETECTION BY FINDING THE VISIBLE FEATURES AND PARTSKai Chi CHAN, Purdue UniversityAlper AYVACI, Honda Research InstituteBernd HEISELE, Honda Research Institute
15:00 « ARS-O9.4 – REAL-TIME DYNAMIC TEXTURE RECOGNITION USING RANDOM SAMPLING AND DIMENSION REDUCTIONOsman GUNAY, Bilkent UniversityA . Enis ÇETIN, Bilkent University
15:20 ARS-O9.5 – IMPROVED FINE STRUCTURE MODELING VIA GUIDED STOCHASTIC CLIQUE FORMATION IN FULLY CONNECTED CONDITIONAL RANDOM FIELDSMohammad Javad SHAFIEE, University of WaterlooAudrey CHUNG, University of WaterlooAlexander WONG, University of WaterlooPaul FIEGUTH, University of Waterloo
ICIP 2015 – Technical Program | 173
15:40 ARS-O9.6 – IMPROVING SPATIAL CODIFICATION IN SEMANTIC SEGMENTATIONCarles VENTURA, Universitat Politècnica de CatalunyaXavier GIRÓ-I-NIETO, Universitat Politècnica de CatalunyaVerónica VILAPLANA, Universitat Politècnica de CatalunyaKevin MCGUINNESS, Insight Centre for Data Analytics, Dublin City UniversityFerran MARQUÉS, Universitat Politècnica de CatalunyaNoel E . O’CONNOR, Insight Centre for Data Analytics, Dublin City University
ARS-P20: Machine Learning for Image Segmentation Wednesday, 14:00-16:00POSTER Room: POSTER ASession Chair(s): Andreas UHL, Salzburg University
ARS-P20.1 – IMAGE SEGMENTATION WITH THE COMPETITIVE LEARNING BASED MS MODELJunfeng LUO, Peking UniversityJinwen MA, Peking University
ARS-P20.2 – OBJECT SEGMENTATION WITH DEEP REGRESSIONJianchao LI, Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS)Dan WANG, Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS)Canxiang YAN, Institute of Deep Learning, Baidu, Inc.,Shiguang SHAN, Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS)
ARS-P20.3 – LEARNING SHAPE PRIORS FOR OBJECT SEGMENTATION VIA NEURAL NETWORKSSimon SAFAR, University of California at MercedMing-Hsuan YANG, University of California at Merced
ARS-P20.4 – HOW TO EXPLOIT LARGE IMAGE DATA IN THE FIELDS OF TEXTURE CLASSIFICATION: A CASE STUDY WITH LOCAL BINARY PATTERNSMichael GADERMAYR, University of SalzburgAndreas UHL, University of Salzburg
ARS-P20.5 – RANKED K-MEANS CLUSTERING FOR TERAHERTZ IMAGE SEGMENTATIONMohamed Walid AYECH, Sherbrooke UniversityDjemel ZIOU, Sherbrooke University
ARS-P20.6 – CANNET: CONTEXT AWARE NONLOCAL CONVOLUTIONAL NETWORKS FOR SEMANTIC IMAGE SEGMENTATIONLingyan RAN, Northwestern Polytechnical UnversityYanning ZHANG, Northwestern Polytechnical UnversityGang HUA, Stevens Institute of Technology
174 | ICIP 2015 – Technical Program
ARS-P24: Object Recognition I Wednesday, 14:00-16:00POSTER Room: POSTER CSession Chair(s): Clinton f*ckES, Queensland University of Technology
ARS-P24.1 – OBJECT CLASSIFICATION FROM RGB-D IMAGES USING DEPTH CONTEXT KERNEL DESCRIPTORSHong PAN, University of CopenhagenSøren OLSEN, University of CopenhagenYaping ZHU, University of Copenhagen
ARS-P24.2 – SELECTIVE PARTS FOR FINE-GRAINED RECOGNITIONDong LI, Tsinghua UniversityYali LI, Tsinghua UniversityShengjin WANG, Tsinghua University
ARS-P24.3 – DEPTH UPSAMPLING METHOD VIA MARKOV RANDOM FIELDS WITHOUT EDGE-MISALIGNED ARTIFACTSYifan ZUO, Shanghai UniversityPing AN, Shanghai University
ARS-P24.4 – CONTEXT-AWARE LANE MARKING DETECTION ON URBAN ROADSTao CHEN, Institute for Infocomm Research, Agency for Science, Technology and ResearchShijian LU, Institute for Infocomm Research, Agency for Science, Technology and Research
ARS-P24.5 – LAPLACE-BELTRAMI SPECTRA FOR SHAPE COMPARISON OF SURFACES IN 3D USING THE CLOSEST POINT METHODReynaldo ARTEAGA, Simon Fraser UniversitySteven RUUTH, Simon Fraser University
ARS-P24.6 – COMBAT SPORTS ANALYTICS: BOXING PUNCH CLASSIFICATION USING OVERHEAD DEPTH IMAGERYSoudeh KASIRI BIDHENDI, Queensland University of TechnologyClinton f*ckES, Queensland University of TechnologyStuart MORGAN, Australian Institute of SportDavid MARTIN, Australian Institute of SportSridha SRIDHARAN, Queensland University of Technology
ARS-P25: Object Recognition II Wednesday, 14:00-16:00POSTER Room: POSTER DSession Chair(s): Clinton f*ckES, Queensland University of Technology
ARS-P25.1 – LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTIONMarion CHEVALIER, LIP6, UPMCNicolas THOME, LIP6, UPMCMatthieu CORD, LIP6, UPMCJérôme FOURNIER, Thales Optronique S.A.S.Gilles HENAFF, Thales Optronique S.A.S.Elodie DUSCH, Thales Optronique S.A.S.
ICIP 2015 – Technical Program | 175
ARS-P25.2 – REAL-TIME SEMANTIC CONTEXT LABELING FOR IMAGE UNDERSTANDINGMartin A . R . PIECK, Eindhoven University of TechnologyFons VAN DER SOMMEN, Eindhoven University of TechnologySvitlana ZINGER, Eindhoven University of TechnologyPeter H . N . DE WITH, Eindhoven University of Technology
ARS-P25.3 – MINE THE FINE: FINE-GRAINED FRAGMENT DISCOVERYM . Hadi KIAPOUR, University of North Carolina at Chapel HillWei DI, eBay Research LabsVignesh JAGADEESH, eBay Research LabsRobinson PIRAMUTHU, eBay Research Labs
ARS-P25.4 – EPITOMIC IMAGE FACTORIZATION VIA NEIGHBOR-EMBEDDINGMehmet TURKAN, Technicolor R&D France / Izmir University of EconomicsDominique THOREAU, Technicolor R&D FrancePhilippe GUILLOTEL, Technicolor R&D FranceMartin ALAIN, Technicolor R&D / INRIAChristine GUILLEMOT, INRIA
ARS-P25.5 – GROUND-BASED CLOUD IMAGE CATEGORIZATION USING DEEP CONVOLUTIONAL VISUAL FEATURESLiang YE, Huazhong University of Science and Technology P.R.ChinaZhiguo CAO, Huazhong University of Science and TechnologyYang XIAO, Huazhong University of Science and TechnologyWei LI, Huazhong University of Science and Technology
ARS-P25.6 – ULTRA-FAST PARALLEL REGISTRATION FOR BAYER RAW DATAJunying YANG, Chongqing UniversityZhenghao LI, Chongqing UniversityPeng HAN, Chongqing Academy of Science and TechnologyYang RAN, Chongqing Academy of Science and Technology
ARS-P30: Video Analysis Wednesday, 14:00-16:00POSTER Room: POSTER BSession Chair(s): Irene Yu-Hua GU, Chalmers University of Technology
ARS-P30.1 – EXPLOITING EFFECTS OF PARTS IN FINE-GRAINED CATEGORIZATION OF VEHICLESLiang LIAO, School of Computer Science, Wuhan UniversityRuimin HU, School of Computer Science, Wuhan UniversityJun XIAO, School of Computer Science, Wuhan UniversityQi WANG, School of Computer Science, Wuhan UniversityJing XIAO, School of Computer Science, Wuhan UniversityJun CHEN, School of Computer Science, Wuhan University
ARS-P30.2 – TRUE MOTION COMPENSATION WITH FEATURE DETECTION FOR FRAME RATE UP-CONVERSIONKyungah KIM, Yonsei UniversityMinwoo KIM, Yonsei UniversityDeokho KIM, Yonsei UniversityWon Woo RO, Yonsei University
176 | ICIP 2015 – Technical Program
ARS-P30.3 – RESIDUE BOUNDARY HISTOGRAMS FOR ACTION RECOGNITION IN THE COMPRESSED DOMAINJie MIAO, South China University of TechnologyXiangmin XU, South China University of TechnologyReji MATHEW, The University of New South WalesHaoyu HUANG, South China University of Technology
ARS-P30.4 – HUMAN FALL DETECTION VIA SHAPE ANALYSIS ON RIEMANNIAN MANIFOLDS WITH APPLICATIONS TO ELDERLY CAREYixiao YUN, Chalmers University of TechnologyIrene Yu-Hua GU, Chalmers University of Technology
ARS-P30.5 – TRAFFIC ANALYSIS WITHOUT MOTION FEATURESZhiming LUO, Xiamen University / Université de SherbrookePierre-Marc JODOIN, Université de SherbrookeShao-Zi LI, Xiamen UniversitySong-Zhi SU, Xiamen University
ARS-P30.6 – RERANKING OF PERSON RE-IDENTIFICATION BY MANIFOLD-BASED APPROACHShuai HUANG, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityYun GU, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityJie YANG, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityPengfei SHI, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University
COM-P5: Video Coding II Wednesday, 14:00-16:00POSTER Room: POSTER NSession Chair(s): Onur GULERYUZ, LG Electronics
COM-P5.1 – AN ADAPTIVE SEARCH ORDERING FOR RATE-CONSTRAINED SUCCESSIVE ELIMINATION ALGORITHMSLuc TRUDEAU, École de technologie supérieureStéphane COULOMBE, École de technologie supérieureChristian DESROSIERS, École de technologie supérieure
COM-P5.2 – LOW-COMPLEXITY RATE CONTROL IN VIDEO CODING BASED ON BI-GEOMETRIC TRANSPARENT COMPOSITE MODELSYueming GAO, University of WaterlooEn-Hui YANG, University of WaterlooDa-Ke HE, BlackBerry
COM-P5.3 – A TWO-STAGE VIDEO CODING FRAMEWORK WITH BOTH SELF-ADAPTIVE REDUNDANT DICTIONARY AND ADAPTIVELY ORTHONORMALIZED DCT BASISYuanyi XUE, Polytechnic School of Engineering, New York UniversityYi ZHOU, Polytechnic School of Engineering, New York UniversityYao WANG, Polytechnic School of Engineering, New York University
ICIP 2015 – Technical Program | 177
COM-P5.4 – INTER-PICTURE PREDICTION BASED ON 3D POINT CLOUD MODELTong SHAO, University of Science and Technology of ChinaDong LIU, University of Science and Technology of ChinaHouqiang LI, University of Science and Technology of China
COM-P5.5 – TRANSFORMS FOR INTRA PREDICTION RESIDUALS BASED ON PREDICTION INACCURACY MODELINGXun CAI, Massachusetts Institute of TechnologyJae LIM, Massachusetts Institute of Technology
COM-P5.6 – ASYMPTOTIC CLOSED-LOOP DESIGN FOR TRANSFORM DOMAIN TEMPORAL PREDICTIONShunyao LI, University of California, Santa BarbaraTejaswi NANJUNDASWAMY, University of California, Santa BarbaraYue CHEN, University of California, Santa BarbaraKenneth ROSE, University of California, Santa Barbara
COM-P10: Video Coding III Wednesday, 14:00-16:00POSTER Room: POSTER OSession Chair(s): Onur GULERYUZ, LG Electronics
COM-P10.1 – EFFICIENT SCALABLE COMPRESSION OF SPARSELY SAMPLED IMAGESColas SCHRETTER, Vrije Universiteit BrusselDavid BLINDER, Vrije Universiteit BrusselTim BRUYLANTS, Vrije Universiteit BrusselPeter SCHELKENS, Vrije Universiteit BrusselAdrian MUNTEANU, Vrije Universiteit Brussel
COM-P10.2 – MOTION VECTOR FIELDS BASED VIDEO CODINGAmin ZHENG, Hong Kong University of Science and TechnologyYuan YUAN, Hong Kong University of Science and TechnologyHong ZHANG, Huawei Technologies Co., LtdHaitao YANG, Huawei Technologies Co., LtdPengfei WAN, Hong Kong University of Science and TechnologyOscar C . AU, Hong Kong University of Science and Technology
COM-P10.3 – MOTION ESTIMATION AND COMPENSATION FOR FISHEYE WARPED VIDEOGuoxin JIN, Northwestern UniversityAnkur SAXENA, Samsung Research AmericaMadhukar BUDAGAVI, Samsung Research America
COM-P10.4 – TEMPLATE BASED INTER-LAYER PREDICTION FOR HIGH DYNAMIC RANGE SCALABLE COMPRESSIONMikael LE PENDU, TechnicolorGuillemot CHRISTINE, INRIADominique THOREAU, Technicolor
COM-P10.5 – LOW-COMPLEXITY SEPARABLE MULTIPLIER-LESS LOOP FILTER FOR VIDEO CODINGAnkur SAXENA, Samsung Research AmericaMohammed AABED, Georgia Institute of TechnologyMadhukar BUDAGAVI, Samsung Research America
«
«
«
178 | ICIP 2015 – Technical Program
COM-P10.6 – A COMPUTATIONAL MODEL FOR PREDICTING LOCAL DISTORTION VISIBILITY VIA CONVOLUTIONAL NEURAL NETWORK TRAINED ON NATURAL SCENESMd Mushfiqul ALAM, Oklahoma State UniversityPranita PATIL, Oklahoma State UniversityMartin HAGAN, Oklahoma State UniversityDamon CHANDLER, Oklahoma State University
ELI-O3: 3D Visual Quality Wednesday, 14:00-16:00LECTURE Room: 205ASession Chair(s): Touradj EBRAHIMI, EPFL
14:00 ELI-O3.1 – A MAJORIZE-MINIMIZE APPROACH FOR HIGH-QUALITY DEPTH UPSAMPLINGYoungjung KIM, Yonsei UniversitySunghwan CHOI, Yonsei UniversityChangjae OH, Yonsei UniversityKwanghoon SOHN, Yonsei University
14:20 ELI-O3.2 – POST INSERTED OBJECT CALIBRATION FOR STEREO VIDEO RECTIFICATIONWeiming LI, Samsung R&D Institute China-BeijingZhihua LIU, Samsung R&D Institute China-BeijingKang XUE, Samsung R&D Institute China-BeijingYangho CHO, Samsung Advanced Institute of Technology (SAIT)Xiying WANG, Samsung R&D Institute China-BeijingGengyu MA, Samsung R&D Institute China-BeijingHaitao WANG, Samsung R&D Institute China-Beijing
14:40 ELI-O3.3 – TEMPORALLY CONSISTENT HOLE FILLING METHOD BASED ON GLOBAL OPTIMIZATION WITH LABEL PROPAGATION FOR 3D VIDEOHak Gu KIM, Korea Advanced Institute of Science and Technology (KAIST)Soo Sung YOON, Korea Advanced Institute of Science and Technology (KAIST)Yong Man RO, Korea Advanced Institute of Science and Technology (KAIST)
15:00 ELI-O3.4 – UPSAMPLING THE DEPTH MAP WITH ITS OWN PROPERTIESWei LIU, Shanghai Jiao Tong UniversityPenglin LI, Shanghai Jiao Tong UniversityJie YANG, Shanghai Jiao Tong UniversityPengfei SHI, Shanghai Jiao Tong University
15:20 ELI-O3.5 – VISUAL COMFORT ASSESSMENT FOR STEREOSCOPIC 3D IMAGES BASED ON SALIENT DISCOMFORT REGIONSCheolkon JUNG, Xidian UniversityHongmin LIU, Xidian University
ICIP 2015 – Technical Program | 179
ELI-P7: Infrared, Multispectral and Hyperspectral imaging Wednesday, 14:00-16:00POSTER Room: POSTER KSession Chair(s): Gaurav SHARMA, University of Rochester
ELI-P7.1 – LGHD: A FEATURE DESCRIPTOR FOR MATCHING ACROSS NON-LINEAR INTENSITY VARIATIONSCristhian AGUILERA, Autonomous University of BarcelonaAngel SAPPA, Autonomous University of BarcelonaRicardo TOLEDO, Autonomous University of Barcelona
ELI-P7.2 – GENERALIZED INPAINTING METHOD FOR HYPERSPECTRAL IMAGE ACQUISITIONKévin DEGRAUX, Université catholique de LouvainValerio CAMBARERI, University of BolognaLaurent JACQUES, Université catholique de LouvainBert GEELEN, IMECCarolina BLANCH, IMECGauthier LAFRUIT, IMEC and Université Libre de Bruxelles
ELI-P7.3 – AN $\ELL_{1/2}$ REGULARIZED LOW-RANK REPRESENTATION FOR HYPERSPECTRAL IMAGERY CLASSIFICATIONSen JIA, College of Computer Science and Software Engineering, Shenzhen UniversityXiujun ZHANG, College of Information Engineering, Shenzhen UniversityLin DENG, College of Information Engineering, Shenzhen UniversityShu ZHENQIU, School of Computer Science and Engineering, Nanjing University of Science and Technology
ELI-P7.4 – DUAL-ARM VIS/NIR COMPRESSIVE SPECTRAL IMAGERHoover RUEDA, University of DelawareHenry ARGUELLO, Universidad Industrial de SantanderGonzalo R . ARCE, University of Delaware
ELI-P7.5 – SINGLE-SHOT FOURIER TRANSFORM MULTISPECTROSCOPYJie JIA, University of DaytonKeigo HIRAKAWA, University of Dayton
ELI-P7.6 – LOW-RANK TENSOR DECOMPOSITION BASED ANOMALY DETECTION FOR HYPERSPECTRAL IMAGERYShuangjiang LI, The University of TennesseeWei WANG, The University of TennesseeHairong QI, The University of TennesseeBulent AYHAN, Signal Processing Inc.Chiman KWAN, Signal Processing Inc.Steven STEVEN VANCE, Jet Propulsion Laboratory
ELI-P8: Multiview Image Processing Wednesday, 14:00-16:00POSTER Room: POSTER MSession Chair(s): Atanas GOTCHEV, Tampere University of Technology
ELI-P8.1 – ROBUST VIDEO STITCHING USING ADAPTIVE PIXEL TRANSFERKyu-Yul LEE, Ulsan National Institute of Science and TechnologyJae-Young SIM, Ulsan National Institute of Science and Technology
«
180 | ICIP 2015 – Technical Program
ELI-P8.2 – IMAGE BASED RENDERING TECHNIQUE VIA SPARSE REPRESENTATION IN SHEARLET DOMAIN Suren VAGHARSHAKYAN, Tampere University of TechnologyRobert BREGOVIC, Tampere University of TechnologyAtanas GOTCHEV, Tampere University of Technology
ELI-P8.3 – GRAPH MODELLING OF 3D GEOMETRIC INFORMATION FOR COLOR CONSISTENCY OF MULTIVIEW IMAGESManohar KUSE, The Hong Kong University of Science and TechnologySunil Prasad JAISWAL, The Hong Kong University of Science and Technology
ELI-P8.4 – PROGRESSIVE FEATURE MATCHING VIA TRIPLET GRAPHChuan YU, Tsinghua UniversityLu TIAN, Tsinghua UniversityHan HU, Tsinghua UniversityYueqi DUAN, Tsinghua UniversityJie ZHOU, Tsinghua University
ELI-P8.5 – THERMOGRAPHY SPATIAL RESOLUTION ENHANCEMENT BY NON-RIGID REGISTRATION WITH VISIBLE IMAGERYGerald MWANGI, University of HeidelbergPaul FIEGUTH, University of Waterloo, CanadaChristoph S . GARBE, University of Heidelberg
ELI-P8.6 – INTERACTIVE MULTIVIEW VIDEO SCHEDULING THROUGH BARGAININGWeiliang XU, Shanghai UniversityJunni ZOU, Shanghai UniversityHongkai XIONG, Shanghai Jiao Tong University
ELI-P9: Stereo Image Processing Wednesday, 14:00-16:00POSTER Room: POSTER LSession Chair(s): A . Aydin ALATAN, Middle East Techincal University
ELI-P9.1 – BI-DCT: DCT-BASED LOCAL BINARY DESCRIPTOR FOR DENSE STEREO MATCHINGSujung KIM, KAISTKyunghyung PAENG, KAISTJa-Won SEO, KAISTSeong Dae KIM, KAIST
ELI-P9.2 – MULTI-CAMERA INTERFERENCE CANCELLATION OF TIME-OF-FLIGHT (TOF) CAMERASLianhua LI, Huazhong University of Science & TechnologySen XIANG, Huazhong University of Science & TechnologyYou YANG, Huazhong University of Science & TechnologyLi YU, Huazhong University of Science & Technology
ELI-P9.3 – HIGH-ORDER REGULARIZATION FOR STEREO COLOR EDITINGKuo-Chin LIEN, UCSBJerry GIBSON, UCSBMatthew TURK, UCSB
«
ICIP 2015 – Technical Program | 181
ELI-P9.4 – STAIR DETECTION AND TRACKING FROM EGOCENTRIC STEREO VISIONTobias SCHWARZE, Karlsruhe Institute of TechnologyZhichao ZHONG, Centrum Wiskunde & Informatica
ELI-P9.5 – SPARSE RECURSIVE FILTERING FORO(1) STEREO MATCHINGYeti Ziya GÜRBÜZ, Middle East Techincal UniversityCevahir CIGLA, ASELSAN Inc.A . Aydin ALATAN, Middle East Techincal University
IFS-P4: Social and Affective Media Wednesday, 14:00-16:00POSTER Room: POSTER JSession Chair(s): Gwenaël DOËRR,Technicolor R&D
IFS-P4.1 – PREDICTING DISCRETE PROBABILITY DISTRIBUTION OF IMAGE EMOTIONSSicheng ZHAO, Harbin Institute of TechnologyHongxun YAO, Harbin Institute of TechnologyXiaolei JIANG, Harbin Institute of TechnologyXiaoshuai SUN, Harbin Institute of Technology
IFS-P4.2 – FACIAL EXPRESSION RECOGNITION IN THE WILD USING RICH DEEP FEATURESAbubakrelsedik KARALI, SiemensAhmad BASSIOUNY, AUCMotaz EL-SABAN, Microsoft
IFS-P4.3 – CREATING DESCRIPTIVE VISUAL WORDS FOR TAG RANKING OF COMPRESSED SOCIAL IMAGEXin LIU, Signal and Information Processing Laboratory, Beijing University of TechnologyJing ZHANG, Signal and Information Processing Laboratory, Beijing University of TechnologyLi ZHUO, Signal and Information Processing Laboratory, Beijing University of TechnologyYing YANG, Signal and Information Processing Laboratory, Beijing University of Technology
IFS-P4.4 – LEARNING DEEP FEATURES FOR IMAGE EMOTION CLASSIFICATIONMing CHEN, Purdue UniversityLu ZHANG, Purdue UniversityJan ALLEBACH, Purdue University
SMR-O5: Omnidirectional imaging and Plenoptics Wednesday, 14:00-16:00LECTURE Room: 202Session Chair(s): Ivana TOSIC, Ricoh Innovations Corp.
14:00 « SMR-O5.1 – ONLINE VIEW SAMPLING FOR ESTIMATING DEPTH FROM LIGHT FIELDSChangil KIM, Disney Research Zurich / ETH ZurichKartic SUBR, Disney Research ZurichKenny MITCHELL, Disney Research ZurichAlexander SORKINE-HORNUNG, Disney Research ZurichMarkus GROSS, Disney Research Zurich / ETH Zurich
«
182 | ICIP 2015 – Technical Program
14:20 « SMR-O5.2 – PARALLAX RECTIFICATION FOR SPECTRALLY-CODED PLENOPTIC CAMERASLingfei MENG, Ricoh Innovations, Corp.Kathrin BERKNER, Ricoh Innovations, Corp.
14:40 SMR-O5.3 – DEPTH AND ANGULAR RESOLUTION IN PLENOPTIC CAMERASMitra DAMGHANIAN, Mid Sweden UniversityRoger OLSSON, Mid Sweden UniversityMårten SJÖSTRÖM, Mid Sweden University
15:00 « SMR-O5.4 – GENERALIZED SOBEL FILTERS FOR GRADIENT ESTIMATION OF DISTORTED IMAGESAntonino FURNARI, University of CataniaGiovanni M . FARINELLA, University of CataniaArcangelo R . BRUNA, STMicroelectronicsSebastiano BATTIATO, University of Catania
15:20 SMR-O5.5 – A MULTI-RESOLUTION APPROACH TO DEPTH FIELD ESTIMATION IN DENSE IMAGE ARRAYSAlessandro NERI, Università degli Studi Roma TREMarco CARLI, Università degli Studi Roma TREFederica BATTISTI, Università degli Studi Roma TRE
15:40 SMR-O5.6 – LENSELET IMAGE COMPRESSION SCHEME BASED ON SUBAPERTURE IMAGES STREAMINGFeng DAI, Institute of Computing Technology, Chinese Academy of Sciences Jun ZHANG, Institute of Computing Technology, Chinese Academy of Sciences Yongdong ZHANG, Institute of Computing Technology, Chinese Academy of Sciences Yike MA, Institute of Computing Technology, Chinese Academy of Sciences
SMR-P8: Sparse Representations and Applications Wednesday, 14:00-16:00POSTER Room: POSTER HSession Chair(s): Eduardo A .B . DA SILVA, Universidade Federal do Rio de Janeiro
SMR-P8.1 – EXTERNAL AND INTERNAL LEARNING FOR SINGLE-IMAGE SUPER-RESOLUTIONShuang WANG, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of EducationShaopeng LIN, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of EducationXuefeng LIANG, IST, Graduate School of Informatics, Kyoto UniversityBo YUE, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of EducationLicheng JIAO, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education
SMR-P8.2 – TRANSLATIONAL AND ROTATIONAL JITTER INVARIANT INCREMENTAL PRINCIPAL COMPONENT PURSUIT FOR VIDEO BACKGROUND MODELINGPaul RODRIGUEZ, Pontificia Universidad Católica del PerúBrendt WOHLBERG, Los Alamos National Laboratory
ICIP 2015 – Technical Program | 183
SMR-P8.3 – A SAMPLE SET PERSPECTIVE ON THE CLASSIFICATION OF HYPERSPECTRAL IMAGE WITH WEIGHTED AFFINE CONSTRAINTDing NI, Department of Electronic Engineering, Tsinghua UniversityHongbing MA, Department of Electronic Engineering, Tsinghua University
SMR-P8.4 – IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCEYulun ZHANG, Tsinghua UniversityKaiyu GU, Ningbo Vision 3D Display Technology Co., LtdYongbing ZHANG, Tsinghua UniversityJian ZHANG, Peking UniversityQionghai DAI, Tsinghua University
SMR-P8.5 – BI-SPARSITY PURSUIT FOR ROBUST SUBSPACE RECOVERYXiao BIAN, North Carolina State UniversityHamid KRIM, North Carolina State Univ.
SMR-P8.6 – LEARNING THE DISCRIMINATIVE DICTIONARY FOR SPARSE REPRESENTATION BY A GENERAL FISHER REGULARIZED MODELQingfeng LIU, New Jersey Institute of TechnologyAjit PUTHENPUTHUSSERY, New Jersey Institute of TechnologyChengjun LIU, New Jersey Institute of Technology
SNT-S8: Show & Tell VIII Wednesday, 14:00-16:00SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S8.1 – A NOVEL CONTINUOUS AUTOFOCUS TECHNIQUEHomer CHEN, National Taiwan UniversityDong-chen TSAI, National Taiwan UniversityThis session will demonstrate a fast and accurate continuous autofocus technique with minimal bouncing and overshoot for shooting videos of moving objects . This technique has been successfully applied to surveillance, consumer, smartphone, and digital cinema cameras .
SNT-S8.2 – A REAL-TIME ACTION RECOGNITION SYSTEM USING DEPTH AND INERTIAL SENSOR FUSIONChen CHEN, University of Texas at DallasNasser KEHTARNAVAZ, University of Texas at DallasThis demonstration presents a human action recognition system that runs in real-time and uses a combination of a depth camera and an inertial sensor simultaneously . Computationally efficient depth image features and inertial signals features are fed into two computationally efficient collaborative representative classifiers . A decision-level fusion is then performed . The demonstration consists of a subject-specific training for say three hand actions followed by a real-time testing or operation . Attendees are asked to stand in front of the camera and perform say two or three hand actions to train the system . Then they will be asked to perform the same actions in random order to see whether the actions are recognized .
184 | ICIP 2015 – Technical Program
SNT-S8.3 – SENSORY GAP: WHY YOU SHOULDN’T OVERLOOK ITReza BAHMANYAR, Institute of Remote Sensing Technology (IMF), German Aerospace Center (DLR)Ambar MURILLO MONTES DE OCA, Institute of Remote Sensing Technology (IMF), German Aerospace Center (DLR)This Show & Tell session will begin by introducing the sensory and semantic gap . The sensory gap will then be the focus, and its causes (e .g ., resolution, perspective, scale, field of view) will be highlighted with a visual demonstration . This will be followed by a quick experiment involving the audience, and results will be processed in real time, with the purpose of visually quantifying and demonstrating the sensory gap . Concluding the Show & Tell session will be a section concentrating on why the sensory gap is important to consider for practical applications, such as annotation tools, and image learning and mining systems
SNT-S8.4 – APPLICATIONS OF HISTOGRAM OF GRADIENT MAGNITUDES Monika SHARMA, TCS Innovation LabsHiranmay GHOSH, TCS Innovation LabsWe would demonstrate the applications of our proposed descriptor, Histogram of Gradient Magnitudes, in the field of computer vision, including Infrastructure planning like finding out the best location for establishing a new school in a city and Telecom Equipment Localisation in a collection of street view images .
SS5-O1: Privacy and Security in the New Generation Video Coding Systems Wednesday, 14:00-16:00LECTURE Room: 205BSession Chair(s): Wassim HAMIDOUCHE, IETR INSA Rennes William PUECH, Université de Montellier
14:00 SS5-O1.1 – HEVC VIDEO AUTHENTICATION USING DATA EMBEDDING TECHNIQUEYiqi TEW, UNIVERSITY OF MALAYAKoksheik WONG, UNIVERSITY OF MALAYARaphael C .-W . PHAN, MULTIMEDIA UNIVERSITY
14:20 SS5-O1.2 – AUTO-SYNCHRONIZED SELECTIVE ENCRYPTION OF VIDEO CONTENTS FOR AN IMPROVED TRANSMISSION ROBUSTNESS OVER ERROR-PRONE CHANNELSBenoit BOYADJIS, Thales communications and securityCyril BERGERON, Thales communications and securitySébastien LECOMTE, Thales communications and security
14:40 SS5-O1.3 – ROI ENCRYPTION FOR THE HEVC CODED VIDEO CONTENTSMousa FARADJALLAH, IETR Lab / Polytech NantesWassim HAMIDOUCHE, IETR Lab / INSA de Rennes
15:00 SS5-O1.4 – OUT-OF-THE-LOOP INFORMATION HIDING FOR HEVC VIDEOLuong PHAM VAN, Ghent University - iMinds - Multimedia LabJohan DE PRAETER, Ghent University - iMinds - Multimedia Lab, Ghent, BelgiumGlenn VAN WALLENDAEL, Ghent University - iMinds - Multimedia Lab, GhentJan DE co*ck, Ghent University - iMinds - Multimedia LabRik VAN DE WALLE, Ghent University - iMinds - Multimedia Lab
ICIP 2015 – Technical Program | 185
15:20 SS5-O1.5 – ENCRYPTING ONLY AC COEFFICIENT SIGNS CONSIDERED HARMFULHeinz HOFBAUER, University of SalzburgAndreas UNTERWEGER, University of SalzburgAndreas UHL, University of Salzburg
TEC-O5: Image Superresolution Wednesday, 14:00-16:00LECTURE Room: 204ASession Chair(s): Christine GUILLEMOT, INRIA
14:00 TEC-O5.1 – MISSING DATA SUPER-RESOLUTION USING NON-LOCAL AND STATISTICAL PRIORSRonan FABLET, Institut Mines-Télécom/Télécom BretagneFrancois ROUSSEAU, Institut Mines-Télécom/Télécom Bretagne
14:20 TEC-O5.2 – IMAGE RESOLUTION ENHANCEMENT BASED ON NOVEL VIEW SYNTHESISYusuke HAYASHI, Graduate School of Information Science Nara Institute of Science TechnologyNorihiko KAWAI, Graduate School of Information Science Nara Institute of Science TechnologyTomokazu SATO, Graduate School of Information Science Nara Institute of Science TechnologyNaokazu YOKOYA, Graduate School of Information Science Nara Institute of Science Technology
14:40 TEC-O5.3 – REGULARIZED SINGLE-IMAGE SUPER-RESOLUTION BASED ON PROGRESSIVE GRADIENT ESTIMATIONLejun YU, College of Information Science and Technology, Beijing Normal UniversityXiaoyu WU, College of Information Science and Technology, Beijing Normal UniversityFengxiang GE, College of Information Science and Technology, Beijing Normal UniversityBo SUN, College of Information Science and Technology, Beijing Normal UniversityJun HE, College of Information Science and Technology, Beijing Normal UniversityRobert SABLATNIG, Vienna University of Technology
15:00 TEC-O5.4 – SINGLE IMAGE SUPER-RESOLUTION BASED ON SELF-EXAMPLES USING CONTEXT-DEPENDENT SUBPATCHESJae-Seok CHOI, Korea Advanced Institute of Science and TechnologySung-Ho BAE, Korea Advanced Institute of Science and TechnologyMunchurl KIM, Korea Advanced Institute of Science and Technology
15:20 TEC-O5.5 – SPARSITY-BASED DEPTH IMAGE RESTORATION USING SURFACE PRIORS AND RGB-D CORRELATIONSXiaowei DENG, McMaster UniversityXiaolin WU, McMaster University
15:40 TEC-O5.6 – UHD IMAGE RECONSTRUCTION BY ESTIMATING INTERPOLATION ERRORKai BERGER, Inria, Rennes Bretagne-AtlantiqueKongfeng BERGER, IRCCyN UMR CNRS 6597Patrick LE CALLET, IRCCyN UMR CNRS 6597
186 | ICIP 2015 – Technical Program
TEC-P11: Image Registration, Fusion and Mosaicking I Wednesday, 14:00-16:00POSTER Room: POSTER FSession Chair(s): Alin ACHIM, University of Bristol
TEC-P11.1 – UNIFIED IMAGE FUSION BASED ON APPLICATION-ADAPTIVE IMPORTANCE MEASURETakashi SHIBATA, NEC CorporationMasayuki TANAKA, Tokyo Institute of TechnologyMasatoshi OKUTOMI, Tokyo Institute of Technology
TEC-P11.2 – $L_1$-FUSION: ROBUST LINEAR-TIME IMAGE RECOVERY FROM FEW SEVERELY CORRUPTED COPIESPanos MARKOPOULOS, University at Buffalo, The State University of New YorkSandipan KUNDU, University at Buffalo, The State University of New YorkDimitris PADOS, University at Buffalo, The State University of New York
TEC-P11.3 – MULTI-EXPOSURE IMAGE FUSION: A PATCH-WISE APPROACHKede MA, Dept. of Electrical and Computer Engineering, The University of WaterlooZhou WANG, Dept. of Electrical and Computer Engineering, The University of Waterloo
TEC-P11.4 – EDGE MODEL BASED FUSION OF MULTI-FOCUS IMAGES USING MATTING METHODYibo CHEN, The Chinese University of Hong KongWai-Kuen CHAM, The Chinese University of Hong Kong
TEC-P11.5 – MULTIFOCUS IMAGE FUSION BASED ON SURFACE AREA ANALYSIS Iman ROOSTA, Isfahan University of TechnologyNader KARIMI, Isfahan University of TechnologyShadrokh SAMAVI, Isfahan University of Technology,McMaster UniversityShahram SHIRANI, McMaster University
TEC-P11.6 – NON-PARAMETRIC ENSEMBLE KALMAN METHODS FOR THE INPAINTING OF NOISY DYNAMIC TEXTURESRedouane LGUENSAT, Telecom BretagnePierre TANDEO, Telecom BretagneRonan FABLET, Telecom BretagnePierre AILLIOT, University of Brest
TEC-P29: Image Registration, Fusion and Mosaicking II Wednesday, 14:00-16:00POSTER Room: POSTER GSession Chair(s): Alin ACHIM, University of Bristol
TEC-P29.1 – A CONTRARIO PATCH MATCHING, WITH APPLICATION TO KEYPOINT MATCHES VALIDATIONRafael GROMPONE VON GIOI, ENS CachanViorica PATRAUCEAN, University of Cambridge
TEC-P29.2 – LINE MEETS AS-PROJECTIVE-AS-POSSIBLE IMAGE STITCHING WITH MOVING DLTKyungdon JOO, Korea Advanced Institute of Science and Technology (KAIST)Namil KIM, Korea Advanced Institute of Science and Technology (KAIST)Tae-Hyun OH, Korea Advanced Institute of Science and Technology (KAIST)In So KWEON, Korea Advanced Institute of Science and Technology (KAIST)
«
«
ICIP 2015 – Technical Program | 187
TEC-P29.3 – COERCIVE REGION-LEVEL REGISTRATION FOR MULTI-MODAL IMAGESYu-Hui CHEN, University of Michigan, Ann ArborDennis WEI, IBM Watson Research CenterGregory NEWSTADT, Google Inc.Jeffrey SIMMONS, US Air Force Research LaboratoryAlfred HERO, University of Michigan, Ann Arbor
TEC-P29.4 – A NEW GLOBAL CONSISTENCE METHOD FOR MOSAICING OF AERIAL IMAGES Menghan XIA, Wuhan UniversityJian YAO, Wuhan UniversityLi LI, Wuhan UniversityXiaohu LU, Wuhan University
TEC-P29.5 – FAST AFFINE-INVARIANT IMAGE MATCHING BASED ON BHATTACHARYYA DISTANCE AND ADAPTIVE TREEJongin SON, Yonsei UniversitySeungryong KIM, Yonsei UniversityKwanghoon SOHN, Yonsei University
TEC-P7: Hystocytological Feature Extraction and Classification Wednesday, 14:00-16:00POSTER Room: POSTER ESession Chair(s): Smriti BHANDARI, Walchand College of Engineering
TEC-P7.1 – ENCODING ROTATION INVARIANT FEATURES IN HEP-2 CELL CLASSIFICATIONXiang XU, Nanyang Technological UniversityFeng LIN, Nanyang Technological UniversityCarol NG, Tan Tock Seng HospitalKhai Pang LEONG, Tan Tock Seng Hospital
TEC-P7.2 – AUTOMATIC DETECTION OF NECROSIS, NORMOXIA AND HYPOXIA IN TUMORS FROM MULTIMODAL CYTOLOGICAL IMAGESGustavo CARNEIRO, The University of AdelaideTingying PENG, Technical University of MunichChristine BAYER, Technical University of MunichNassir NAVAB, Technical University of Munich
TEC-P7.3 – LEARNING HISTOPATHOLOGICAL REGIONS OF INTEREST BY FUSING BOTTOM-UP AND TOP-DOWN INFORMATIONGermán CORREDOR, Universidad Nacional de ColombiaEduardo ROMERO, Universidad Nacional de Colombia
TEC-P7.4 – THE MEASUREMENT OF CELL VIABILITY BASED ON TEMPORAL BAG OF WORDS FOR IMAGE SEQUENCESFengqian PANG, Beijing Institute of TechnologyZhiwen LIU, Beijing Institute of TechnologyHeng LI, Beijing Institute of TechnologyYonggang SHI, Beijing Institute of Technology
«
«
«
188 | ICIP 2015 – Technical Program
TEC-P7.5 – A BAG-OF-FEATURES APPROACH FOR MALIGNANCY DETECTION IN BREAST HISTOPATHOLOGY IMAGESSmriti BHANDARI, Walchand College of Engineering
ARS-O11: Learning-based Visual Applications Wednesday, 16:30-18:30LECTURE Room: 205ASession Chair(s): Xiangwei KONG, Dalian Univesity of Technology
16:30 ARS-O11.1 – MULTIPLE DICTIONARIES SPARSE CODING FOR PEDESTRIAN DETECTIONYazhou LIU, Nanjing University of Science and TechnologyPongsak LASANG, Panasonic R&D Center SingaporeMel SIEGEL, Carnegie Mellon UniversityQuansen SUN, Nanjing University of Science and Technology
16:50 ARS-O11.2 – MULTITHREADING ADABOOST FRAMEWORK FOR OBJECT RECOGNITIONJinhui CHEN, Kobe UniversityTetsuya TAKIGUCHI, Kobe UniversityYasuo ARIKI, Kobe University
17:10 ARS-O11.3 – NOVEL GENERAL KNN CLASSIFIER AND GENERAL NEAREST MEAN CLASSIFIER FOR VISUAL CLASSIFICATIONQingfeng LIU, New Jersey Institute of TechnologyAjit PUTHENPUTHUSSERY, New Jersey Institute of TechnologyChengjun LIU, New Jersey Institute of Technology
17:30 ARS-O11.4 – BEYOND LOCAL PHASE QUANTIZATION: MID-LEVEL BLURRED IMAGE REPRESENTATION USING FISHER VECTORMengyu ZHU, Huazhong University of Science and TechnologyZhiguo CAO, Huazhong University of Science and TechnologyYang XIAO, Huazhong University of Science and TechnologyXiaokang XIE, Huazhong University of Science and Technology
17:50 ARS-O11.5 – IMPROVED CLUSTER CENTER ADAPTION FOR IMAGE CLASSIFICATIONMingmin ZHEN, Peking UniversityWenmin WANG, Peking University
18:10 ARS-O11.6 – FEATURE EXTRACTION VIA MULTI-VIEW NON-NEGATIVE MATRIX FACTORIZATION WITH LOCAL GRAPH REGULARIZATIONZhenfan WANG, Dalian University of TechnologyXiangwei KONG, Dalian University of TechnologyHaiyan FU, Dalian University of TechnologyMing LI, Dalian University of TechnologyYujia ZHANG, Fordham University
ICIP 2015 – Technical Program | 189
ARS-O18: Superpixel Segmentation Wednesday, 16:30-18:30LECTURE Room: 204BSession Chair(s): A . Aydin ALATAN, Middle East Techincal University
16:30 ARS-O18.1 – WATERSHED SUPERPIXELZhongwen HU, Shenzhen UniversityQin ZOU, Wuhan UniversityQingquan LI, Shenzhen University
16:50 ARS-O18.2 – FAST LABEL PROPAGATION FOR REAL-TIME SUPERPIXELS FOR VIDEO CONTENTMatthias RESO, Leibniz Universität HannoverJörn JACHALSKY, Technicolor Research & InnovationBodo ROSENHAHN, Leibniz Universität HannoverJörn OSTERMANN, Leibniz Universität Hannover
17:10 ARS-O18.3 – UNSUPERVISED SEGMENTATION USING DYNAMIC SUPERPIXEL RANDOM WALKSChristian DESROSIERS, École de technologie supérieure
17:30 « ARS-O18.4 – A FAST METHOD FOR INFERRING HIGH-QUALITY SIMPLY-CONNECTED SUPERPIXELSOren FREIFELD, MITYixin LI, MITJohn FISHER III, MIT
17:50 ARS-O18.5 – LASP: LOCAL ADAPTIVE SUPER-PIXELSKutalmis Gokalp INCE, Middle East Technical University, ASELSAN INC.Cevahir CIGLA, ASELSAN Inc.A . Aydin ALATAN, Middle East Technical University, ASELSAN Inc.
18:10 ARS-O18.6 – NSLIC: SLIC SUPERPIXELS BASED ON NONSTATIONARITY MEASUREShaoyong JIA, Institue of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityShijie GENG, Institue of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityYun GU, Institue of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityYu QIAO, Institue of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityJie YANG, Institue of Image Processing and Pattern Recognition, Shanghai Jiao Tong UniversityPengfei SHI, Institue of Image Processing and Pattern Recognition, Shanghai Jiao Tong University
190 | ICIP 2015 – Technical Program
ARS-O22: Pose Estimation and Human Activity Recognition Wednesday, 16:30-18:30LECTURE Room: 202Session Chair(s): Kalpathi RAMAKRISHNAN, Indian Institute of Science
16:30 « ARS-O22.1 – UTD-MAD: A MULTIMODAL DATASET FOR HUMAN ACTION RECOGNITION UTILIZING A DEPTH CAMERA AND A WEARABLE INERTIAL SENSOR Chen CHEN, University of Texas at DallasRoozbeh JAFARI, University of Texas at DallasNasser KEHTARNAVAZ, University of Texas at Dallas
16:50 ARS-O22.2 – ONLINE PERSON ORIENTATION ESTIMATION BASED ON CLASSIFIER UPDATEHong LIU, Shenzhen Graduate School, Peking UniversityLiqian MA, Shenzhen Graduate School, Peking University
17:10 ARS-O22.3 – REAL-TIME UPPER BODY POSE ESTIMATION FROM DEPTH IMAGESMing-Han TSAI, National Chiao Tung UniversityKuan-Hua CHEN, National Chiao Tung UniversityI-Chen LIN, National Chiao Tung University
17:30 ARS-O22.4 – HUMAN ACTIVITY RECOGNITION BASED ON POSE POINTS SELECTIONKe XU, Shanghai Jiao Tong UniversityXinghao JIANG, Shanghai Jiao Tong UniversityTanfeng SUN, Shanghai Jiao Tong University
17:50 « ARS-O22.5 – MOTION RETRIEVAL USING CONSISTENCY OF EPIPOLAR GEOMETRYNazim ASHRAF, FC College (A Chartered University)Hassan FOROOSH, University of Central Florida
18:10 ARS-O22.6 – ON THE UTILITY OF CANONICAL CORRELATION ANALYSIS FOR DOMAIN ADAPTATION IN MULTI-VIEW HEADPOSE ESTIMATIONAnoop RAJAGOPAL, Indian Institute of ScienceRamanathan SUBRAMANIAN, Advanced Digital Sciences CenterVassilios VONIKAKIS, Advanced Digital Sciences CenterKalpathi RAMAKRISHNAN, Indian Institute of ScienceStefan WINKLER, Advanced Digital Sciences Center
ARS-P16: Image Processing Applications I Wednesday, 16:30-18:30POSTER Room: POSTER FSession Chair(s): Peter SCHELKENS, Vrije Universiteit Brussel
ARS-P16.1 – REAL TIME VEHICLE BACK-UP WARNING SYSTEM WITH SINGLE CAMERAJun CAO, Intel CorpYilin WANG, School of Computing, Arizona State UniversityBaoxin LI, School of Computing, Arizona State University
ARS-P16.2 – BELIEF-PROPAGATION-BASED ROBUST DECODING FOR TWO-DIMENSIONAL BARCODES TO OVERCOME DISTORTION AND OCCLUSION AND ITS EXTENSION TO MULTI-VIEW DECODINGKohei KAMIZURU, Kagoshima UniversityYudai KAWAKAMI, Kagoshima UniversityHiroshi KAWASAKI, Kagoshima UniversitySatoshi ONO, Kagoshima University
ICIP 2015 – Technical Program | 191
ARS-P16.3 – APPLICATION OF IMAGE PROCESSING TECHNIQUES FOR FROG CALL CLASSIFICATIONJie XIE, Queensland University of TechnologyMichael TOWSEY, Queensland University of TechnologyJinglan ZHANG, Queensland University of TechnologyXueyan DONG, Queensland University of TechnologyPaul ROE, Queensland University of Technology
ARS-P16.4 – CONSTRUCTION OF A BIRD IMAGE DATASET FOR ECOLOGICAL INVESTIGATIONSRyota YOSHIHASHI, The University of TokyoRei KAWAKAMI, The University of TokyoMakoto IIDA, The University of TokyoTakeshi NAEMURA, The University of Tokyo
ARS-P16.5 – LOW-COST LICENSE PLATE DETECTION USING A CALIBRATED CAMERAHenrique WEBER, Federal University of Rio Grande do SulClaudio Rosito JUNG, Federal University of Rio Grande do Sul
ARS-P2: Active Contours and Levelset Methods Wednesday, 16:30-18:30POSTER Room: POSTER DSession Chair(s): Vijayan K . ASARI, University of Dayton
ARS-P2.1 – EREL: EXTREMAL REGIONS OF EXTREMUM LEVELSMehdi FARAJI, Kharazmi UniversityJamshid SHANBEHZADEH, Kharazmi UniversityKamal NASROLLAHI, Aalborg UniversityThomas B . MOESLUND, Aalborg University
ARS-P2.2 – ADAPTIVE REGULARIZATION LEVEL SET EVOLUTION FOR MEDICAL IMAGE SEGMENTATION AND BIAS FIELD CORRECTIONXiaomeng XIN, NLPR, Institute of Automation, Chinese Academy of SciencesLingfeng WANG, NLPR, Institute of Automation, Chinese Academy of SciencesChunhong PAN, NLPR, Institute of Automation, Chinese Academy of SciencesShigang LIU, School of Computer Science, Shaanxi Normal University
ARS-P2.3 – A SELF-ORGANIZING LATTICE BOLTZMANN ACTIVE CONTOUR (SOLBAC) APPROACH FOR FAST AND ROBUST OBJECT REGION SEGMENTATIONFatema ALBALOOSHI, University of DaytonVijayan K . ASARI, University of Dayton
ARS-P2.4 – SEGMENTING SIMILAR SHAPES VIA WEIGHTED GROUP-SIMILARITY ACTIVE CONTOURSPeng LV, Beijing Key Lab of Intelligent Information TechnologyQingjie ZHAO, Beijing Key Lab of Intelligent Information TechnologyDongbing GU, School of Computer Science and Electronic Engineering, University of Essex
ARS-P2.5 – IMAGE SEGMENTATION USING CLIQUE BASED SHAPE PRIOR AND THE MUMFORD SHAH FUNCTIONALFredrick PARK, Whittier College
«
192 | ICIP 2015 – Technical Program
ARS-P2.6 – A LEVEL SET-BASED FRAMEWORK FOR 3D KIDNEY SEGMENTATION FROM DIFFUSIONMR IMAGESMohamed SHEHATA, University of LouisvilleFahmi KHALIFA, University of LouisvilleAhmed SOLIMAN, University of LouisvilleRahaf ELREFAI, University of LouisvilleMohamed ABOU EL-GHAR, University of LouisvilleAmy DWYER, University of LouisvilleRosemary OUSEPH, University of LouisvilleAyman EL-BAZ, University of Louisville
ARS-P33: Video Surveillance I Wednesday, 16:30-18:30POSTER Room: POSTER CSession Chair(s): Henri NICOLAS, LaBRI
ARS-P33.1 – HOW MUCH BANDWIDTH DOES SURVEILLANCE SYSTEM REQUIRE?Zengmin XU, Wuhan UniversityRuimin HU, Wuhan UniversityJun CHEN, Wuhan UniversityHongyang LI, Wuhan UniversityHuafeng CHEN, Wuhan University
ARS-P33.2 – A DISCRIMINATIVE TRACKLETS REPRESENTATION FOR CROWD ANALYSISChongjing WANG, Shanghai Jiao Tong UniversityZheng SHOU, Shanghai Jiao Tong UniversityYi ZOU, Shanghai Jiao Tong UniversityXu ZHAO, Shanghai Jiao Tong UniversityYuncai LIU, Shanghai Jiao Tong University
ARS-P33.3 – ABANDONED OBJECT DETECTION USING OPERATOR-SPACE PURSUITLucas THOMAZ, Universidade Federal do Rio de JaneiroAllan DA SILVA, Universidade Federal do Rio de JaneiroEduardo A .B . DA SILVA, Universidade Federal do Rio de JaneiroSergio NETTO, Universidade Federal do Rio de JaneiroXiao BIAN, North Carolina State UniversityHamid KRIM, North Carolina State University
ARS-P33.4 – OBJECT MODELING AND TRAJECTORY ESTIMATIONS FOR TRAFFIC ANALYSISHenri NICOLAS, University of Bordeaux
ARS-P33.5 – OBJECT TRACKING VIA DENSE SIFT DESCRIPTORS AND LOW-RANK REPRESENTATIONYong WANG, Shenzhen Branch of Hisilicon Research Department, Hisilicon TechnologiesHaibo LIU, Shenzhen Branch of Hisilicon Research Department, Hisilicon TechnologiesShiqiang HU, School of Aeronautics and Astronautics, Shanghai Jiao Tong University
ARS-P33.6 – OBJECT TRACKING BASED ON HUBER LOSS FUNCTIONYong WANG, Shenzhen Branch of Hisilicon Research Department, Hisilicon TechnologiesShandong WU, Imaging Research Division, Department of Radiology, University of PittsburghHaibo LIU, Shenzhen Branch of Hisilicon Research Department, Hisilicon TechnologiesShiqiang HU, School of Aeronautics and Astronautics, Shanghai Jiao Tong University
ICIP 2015 – Technical Program | 193
ARS-P39: Video Surveillance II Wednesday, 16:30-18:30POSTER Room: POSTER BSession Chair(s): Henri NICOLAS, LaBRI
ARS-P39.1 – ANOMALY DETECTION IN CROWD SCENES VIA ONLINE ADAPTIVE ONE-CLASS SUPPORT VECTOR MACHINESHanhe LIN, University of OtagoJeremiah DENG, University of OtagoBrendon WOODFORD, University of Otago
ARS-P39.2 – IS PEDESTRIAN DETECTION ROBUST FOR SURVEILLANCE?Yuan YUAN, Nanyang Technological UniversityYuming FANG, Jiangxi University of Finance and EconomicsWeisi LIN, Nanyang Technological University
ARS-P39.3 – SEEING AS IT HAPPENS: REAL TIME 3D VIDEO EVENT VISUALIZATIONYueming YANG, University at Albany, State University of New YorkMing-Ching CHANG, GE Global ResearchPeter TU, GE Global ResearchSiwei LYU, University at Albany, State University of New York
ARS-P39.4 – A PARTICLE FILTER BASED SEQUENTIAL TRAJECTORY CLASSIFIER FOR BEHAVIOR ANALYSIS IN VIDEO SURVEILLANCEVahid BASTANI, University of GenovaLucio MARCENARO, University of GenovaCarlo REGAZZONI, University of Genova
ARS-P39.5 – SYNTHETIC FACE GENERATION UNDER VARIOUS OPERATIONAL CONDITIONS IN VIDEO SURVEILLANCE Faniya MOKHAYYERI, École de technologie supérieureEric GRANGER, École de technologie supérieureGuillaume-Alexandre BILODEAU, École polytechnique de Montréal
ARS-P4: Classification III Wednesday, 16:30-18:30POSTER Room: POSTER ASession Chair(s): Wenmin WANG, Peking University
ARS-P4.1 – CLUSTERED EXEMPLAR-SVM: DISCOVERING SUB-CATEGORIES FOR VISUAL RECOGNITIONNataliya SHAPOVALOVA, Simon Fraser UniversityGreg MORI, Simon Fraser University
ARS-P4.2 – FINE-GRAINED BIRD SPECIES RECOGNITION VIA HIERARCHICAL SUBSET LEARNINGZongyuan GE, QUTChristopher MCCOOL, Queensland University of Technology Conrad SANDERSON, NICTAAlex BEWLEY, Queensland University of Technology Zetao CHEN, QUTPeter CORKE, Queensland University of Technology
194 | ICIP 2015 – Technical Program
ARS-P4.3 – IMAGE CLASSIFICATION USING RBM TO ENCODE LOCAL DESCRIPTORS WITH GROUP-SPARSE LEARNINGJinzhuo WANG, Shenzhen Graduate School, Peking UniversityWenmin WANG, Shenzhen Graduate School, Peking UniversityRonggang WANG, Shenzhen Graduate School, Peking UniversityWen GAO, Peking University
ARS-P4.4 – CROSS-LAYER FEATURES IN CONVOLUTIONAL NEURAL NETWORKS FOR GENERIC CLASSIFICATION TASKSKuan-Chuan PENG, Cornell UniversityTsuhan CHEN, Cornell University
ARS-P4.5 – MODELLING LOCAL DEEP CONVOLUTIONAL NEURAL NETWORK FEATURESTO IMPROVE FINE-GRAINED IMAGE CLASSIFICATIONZongyuan GE, Queensland University of Technology Christopher MCCOOL, Queensland University of Technology Conrad SANDERSON, NICTAPeter CORKE, Queensland University of Technology
ARS-P4.6 – ASK THE DICTIONARY:SOFT-ASSIGNMENT LOCATION-ORIENTATION POOLING FOR IMAGE CLASSIFICATIONQilong WANG, Dalian University of TechnologyXiaona DENG, Dalian University of TechnologyPeihua LI, Dalian University of TechnologyLei ZHANG, The Hong Kong Polytechnic University
ARS-P46: Object Detection and Tracking III Wednesday, 16:30-18:30POSTER Room: POSTER ESession Chair(s): Yongyi YANG, Illinois Institute of Technology
ARS-P46.1 – EXTRACTING MAJOR LINES BY RECRUITING ZERO-THRESHOLD CANNY EDGE LINKS ALONG SOBEL HIGHLIGHTSJaewoong KIM, School of Information and Communication Engineering of Sungkyunkwan UniversitySukhan LEE, School of Information and Communication Engineering of Sungkyunkwan University
ARS-P46.2 – IMPROVING UNIFORMITY IN DETECTION PERFORMANCE OF CLUSTERED MICROCALCIFICATIONS IN MAMMOGRAMS Maria V . SAINZ DE CEA, Illinois Institute of TechnologyYongyi YANG, Illinois Institute of Technology
ARS-P46.3 – BONE EXTRACTION IN X-RAY IMAGES BY ANALYSIS OF LINE FLUCTUATIONSSalome KAZEMINIA, Isfahan University of TechnologyNader KARIMI, Isfahan University of TechnologyBehzad MIRMAHBOUB, Italian Institute of TechnologyS .M .Reza SOROUSHMEHR, University of Michigan, Ann ArborShadrokh SAMAVI, Isfahan University of Technology
«
«
«
ICIP 2015 – Technical Program | 195
ARS-P46.4 – EXTERNAL FORCES FOR ACTIVE CONTOURS USING THE UNDECIMATED WAVELET TRANSFORMAhmed GAWISH, University of WaterooPaul FIEGUTH, University of Wateroo
ARS-P46.5 – A PARAMETRIC MODEL FOR MULTI-LANES DETECTIONMohammed Elamine MOUMENE, Université d’Oran, Laboratoire LITIODjemel ZIOU, Université de Sherbrooke, Département d’InformatiqueRachid NOURINE, Université d’Oran, Laboratoire LITIO
ARS-P46.6 – EFFICIENT BACKGROUND SUBTRACTION WITH LOW-RANK AND SPARSE MATRIX DECOMPOSITIONSalehe ERFANIAN EBADI, MMV (Multimedia and Vision) Lab/Queen Mary University of LondonValia GUERRA ONES, MMV (Multimedia and Vision) Lab/Queen Mary University of London/Delft University of TechnologyEbroul IZQUIERDO, MMV (Multimedia and Vision) Lab/Queen Mary University of London
ARS-P8: Face Image Analysis I Wednesday, 16:30-18:30POSTER Room: POSTER HSession Chair(s): Riccardo LEONARDI, Univerity of Brescia
ARS-P8.1 – EVOLUTIONARY FUSION OF LOCAL TEXTURE PATTERNS FOR FACIAL EXPRESSION RECOGNITIONFaisal AHMED, University of CalgaryPadma Polash PAUL, University of CalgaryMarina GAVRILOVA, University of Calgary
ARS-P8.2 – AGE ESTIMATION UNDER CHANGES IN IMAGE QUALITY: AN EXPERIMENTAL STUDYFares ALNAJAR, Informatics Institute, Faculty of Science, University of AmsterdamTheo GEVERS, Informatics Institute, Faculty of Science, University of AmsterdamSezer KARAOGLU, University of Amsterdam
ARS-P8.3 – FACIAL MAKEUP DETECTION VIA SELECTED GRADIENT ORIENTATION OF ENTROPY INFORMATIONKuan-Hsien LIU, Academia SinicaTsung-Jung LIU, National Chung Hsing UniversityHsin-Hua LIU, National Taiwan UniversitySoo-Chang PEI, National Taiwan University
ARS-P8.4 – FACE ATTRIBUTE CLASSIFICATION USING ATTRIBUTE-AWARE CORRELATION MAP AND GATED CONVOLUTIONAL NEURAL NETWORKSSunghun KANG, Korea Advanced Institute of Science and TechnologyDonghoon LEE, Korea Advanced Institute of Science and TechnologyChang D . YOO, Korea Advanced Institute of Science and Technology
196 | ICIP 2015 – Technical Program
ARS-P51: Face Image Analysis II Wednesday, 16:30-18:30POSTER Room: POSTER JSession Chair(s): Riccardo LEONARDI, Univerity of Brescia
ARS-P51.1 – REAL-TIME EYE LOCALIZATION, BLINK DETECTION, AND GAZE ESTIMATION SYSTEM WITHOUT INFRARED ILLUMINATIONBo Chun CHEN, Graduate Institute of Electronics Engineering National Taiwan UniversityPo Chen WU, Graduate Institute of Electronics Engineering National Taiwan UniversityShao Yi CHIEN, Graduate Institute of Electronics Engineering National Taiwan University
ARS-P51.2 – MULTI-CLASS SEMANTIC SEGMENTATION OF FACESKhalil KHAN, Università degli Studi di BresciaMassimo MAURO, Università degli Studi di BresciaRiccardo LEONARDI, Università degli Studi di Brescia
ARS-P51.3 – FACE HALLUCINATION BASED ON NONPARAMETRIC BAYESIAN LEARNINGMinqi LI, University of TechnologyRichard Yi Da XU, University of Technology
ARS-P51.4 – RANDOM CASCADED-REGRESSION COPSE FOR ROBUST FACIAL LANDMARK DETECTIONZhen-Hua FENG, Jiangnan UnversityPatrik HUBER, University of SurreyJosef KITTLER, University of SurreyWilliam CHRISTMAS, University of SurreyXiao-Jun WU, University of Surrey
ARS-P51.5 – SINGLE FACE IMAGE SUPER-RESOLUTION VIA SOLO DICTIONARY LEARNINGFelix JUEFEI-XU, Carnegie Mellon UniversityMarios SAVVIDES, Carnegie Mellon University
ARS-P51.6 – CONFIDENCE MEASURE USING COMPOSITE FEATURES FOR EYE DETECTION IN A FACE RECOGNITION SYSTEMSang-Il CHOI, Dankook UniversityYonggeol LEE, Dankook UniversityChunghoon KIM, VTOUCH
ARS-P53: Image Processing Applications II Wednesday, 16:30-18:30POSTER Room: POSTER GSession Chair(s): Peter SCHELKENS, Vrije Universiteit Brussel
ARS-P53.1 – VIDEO DENOISING BY ONLINE 3D SPARSIFYING TRANSFORM LEARNINGBihan WEN, University of Illinois at Urbana-ChampaignSaiprasad RAVISHANKAR, University of Illinois at Urbana-ChampaignYoram BRESLER, University of Illinois at Urbana-Champaign
ARS-P53.2 – A STRUCTURE-BASED REGION DETECTOR FOR RETINAL IMAGE REGISTRATIONZeinab GHASSABI, Department of Computer Engineering, Science and Research Branch, Islamic Azad UniversityJamshid SHANBEHZADEH, 2Department of Computer Engineering, Kharazmi UniversityAli MOHAMMADZADEH, Department of Remote Sensing, K.N.Toosi University of Technology
«
«
ICIP 2015 – Technical Program | 197
ARS-P53.3 – DIGITAL IMAGE CORRELATION FOR SMALL STRAIN MEASUREMENT IN DEFORMABLE SOLIDS AND GEOMECHANICAL STRUCTURESNghia DINH, University of Western AustraliaGhulam Mubashar HASSAN, University of Western AustraliaArcady DYSKIN, University of Western AustraliaCara MACNISH, University of Western Australia
ARS-P53.4 – TEXTURE CLASSIFICATION USING RAO’S DISTANCE: AN EM ALGORITHM ON THE POINCARÉ HALF PLANESalem SAID, CNRS, Laboratoire IMS UMR 5218Lionel BOMBRUN, Bordeaux Science Agro, Laboratoire IMSYannick BERTHOUMIEU, Bordeaux INP, Laboratoire IMS
ARS-P53.5 – 3D VISUAL DISCOMFORT PREDICTOR BASED ON NEURAL ACTIVITY STATISTICSHeeseok OH, Dept. Electrical and Electronic Engineering, Yonsei Univ.Jongyoo KIM, Dept. Electrical and Electronic Engineering, Yonsei Univ.Sanghoon LEE, Dept. Electrical and Electronic Engineering, Yonsei Univ.Alan BOVIK, Dept. Electrical and Computer Engineering, The Univ. of Texas at Austin
ARS-P53.6 – UTILIZING IMAGE-FEATURES IN BIOMEDICAL DOCUMENT CLASSIFICATIONKaidi MA, CIS Dept. University of DelawareHogyeong JEONG, CIS Dept. University of DelawareRohith MV, CIS Dept. University of DelawareGowri SOMANATH, CIS Dept. University of DelawareRyan TARPINE, GoogleKyle SCHUTTER, Center for Computational Molecular Biology, CS Dept., Brown UniversityDorothea BLOSTEIN, School of Computing, Queen’s UniversitySorin ISTRAIL, Center for Computational Molecular Biology, CS Dept., Brown UniversityChandra KAMBHAMETTU, CIS Dept. University of DelawareHagit SHATKAY, CIS Dept. University of Delaware;School of Computing, Queen’s University; Center for Bioinformatics
ELI-O7: Object Detection in Very High Resolution Satellite Images Wednesday, 16:30-18:30LECTURE Room: 203Session Chair(s): Pierre BLANCHART, CNAM
16:30 « ELI-O7.1 – LOCAL INTEGRITY CONSTRAINTS FOR STRUCTURE DETECTION AND SEGMENTATION IN HIGH-RESOLUTION EARTH OBSERVATION IMAGESPierre BLANCHART, CNAMMarin FERECATU, CNAM
16:50 « ELI-O7.2 – EVALUATING THE SENSORY GAP FOR EARTH OBSERVATION IMAGES USING HUMAN PERCEPTION ANDAN LDA-BASED COMPUTATIONAL MODELGholamreza BAHMANYAR, German Aerospace Center (DLR)Ambar MURILLO MONTES DE OCA, German Aerospace Center (DLR)
«
198 | ICIP 2015 – Technical Program
17:10 ELI-O7.3 – CLASSIFICATION OF INTERFEROMETRIC SAR IMAGES BASED ON PARAMETRIC MODELING IN THE FRACTIONAL FOURIER TRANSFORM DOMAINNazli Deniz CAGATAY, German Aerospace Center (DLR)Mihai DATCU, German Aerospace Center (DLR)
17:30 ELI-O7.4 – ORIENTATION ROBUST OBJECT DETECTION IN AERIAL IMAGES USING DEEPCONVOLUTIONAL NEURAL NETWORKHaigang ZHU, University of Chinese Academy of SciencesXiaogang CHEN, University of Chinese Academy of SciencesWeiqun DAI, University of Chinese Academy of SciencesKun FU, Institute of Electronics, Chinese Academy of SciencesQixiang YE, University of Chinese Academy of SciencesJianbin JIAO, University of Chinese Academy of Sciences
17:50 ELI-O7.5 – FAST AIRCRAFT DETECTION IN SATELLITE IMAGES BASED ON CONVOLUTIONAL NEURAL NETWORKSWu HUI, ISCASZhang HUI, ISCASZhang JINFANG, ISCASXu FANJIANG, ISCAS
18:10 ELI-O7.6 – A NON-PARAMETRIC CFAR DETECTOR BASED ON SAR SEA CLUTTER STATISTICAL MODELINGJaime MARTIN-DE-NICOLAS, University of AlcalaPilar JARABO-AMORES, University of AlcalaNerea REY-MAESTRE, University of AlcalaDavid MATA-MOYA, University of AlcalaJose-Luis BARCENA-HUMANES, University of Alcala
SNT-S9: Show & Tell IX Wednesday, 16:30-18:30SHOW & TELL Room: SHOW & TELLSession Chair(s): Fabrice LABEAU, McGill University
SNT-S9.1 – FACIAL EXPRESSION RECOGNITION IN THE WILD USING DEEP FEATURES AND DOMAIN KNOWLEDGEMotaz EL-SABAN, Microsoft Advanced Technology LabAbubakrelsedik KARALI, Swedish institute of computer scienceAhmad BASSIOUNY, American university in CairoIn this demo, we will show our work in the paper “facial expression recognition in the wild using rich deep features” in action . The demo will be accepting an image with possibly multiple persons, it will detect the several faces and will output for each face confidence values for a set of pre-trained facial expressions, namely: surprise, fear, disgust, happiness, sadness and anger . While several approaches have been developed to solve the facial expression problem, solving it in the wild on real-world images remains an area where much work is still needed . To this end, we present a novel approach towards facial expression recognition . We fuse rich deep features with domain knowledge through encoding discriminant facial patches .
ICIP 2015 – Technical Program | 199
SNT-S9.2 – VISUAL DEMONSTRATION OF INSTABILITY IN CLOSED-LOOP PREDICTOR DESIGN AND SOLUTION VIA ASYMPTOTIC CLOSED-LOOP DESIGN FOR TRANSFORM DOMAIN TEMPORAL PREDICTIONShunyao LI, University of California, Santa BarbaraTejaswi NANJUNDASWAMY, University of California, Santa Barbara Yue CHEN, University of California, Santa BarbaraKenneth ROSE, University of California, Santa BarbaraWe propose to demonstrate the instability problem of the predictor design due to quantization error propagation in the traditional closed-loop approach for transform domain temporal prediction in video coders . We will then demonstrate how we employ the Asymptotic Closed-Loop (ACL) design to address this problem .
SNT-S9.3 – LOW-RANK TENSOR DECOMPOSITION BASED ANOMALY DETECTION FOR HYPERSPECTRAL IMAGERYHairong QI, University of TennesseeWe will demonstrate our novel Tensor Decomposition based anomaly Detection (LTDD) algorithm for Hyperspectral Imagery . Based on the obtained low-rank tensor, LTDD further decomposes the low-rank tensor using Tucker decomposition to extract the core tensor which is treated as the “support” of the anomaly spectral signatures . LTDD then adopts an unmixing approach to the reconstructed core tensor for anomaly detection .
SS4-O1: Very High Resolution Satellite Image Information Extraction Wednesday, 16:30-18:30LECTURE Room: 205BSession Chair(s): Mihai DATCU, German Aerospace Center (DLR) Daniele RICCIO, University of Napoli Federico I
16:30 SS4-O1.1 – INFORMATION EXTRACTION FROM VERY HIGH RESOLUTION SATELITE SAR DATA TIME SERIES USING GRAPH BASED CONNECTED FEATURESDusan GLEICH, University of Maribor
16:50 SS4-O1.2 – CLASSIFICATION OF POLARIMETRIC SAR IMAGERY USING UNSUPERVISED H/ AND EXTENDED H/ SCHEMES TO DETECT ANOMALIES ON EARTHEN LEVEESRamakalavathi MARAPAREDDY, Mississippi State UniversityJames V . AANSTOOS, Mississippi State UniversityNicolas H . YOUNAN, Mississippi State University
17:10 SS4-O1.3 – AUTOMATIC RECTANGULAR BUILDING DETECTION FROM VHR AERIAL IMAGERY USING SHADOW AND IMAGE SEGMENTATIONTran-thanh NGO, ICube, University of Strasbourg, CNRSChristophe COLLET, ICube, University of Strasbourg, CNRSVincent MAZET, ICube, University of Strasbourg, CNRS
17:30 SS4-O1.4 – IMAGE CLASSIFICATION: NO FEATURES, NO CLUSTERINGShiyong CUI, German Aerospace Center (DLR)Gottfried SCHWARZ, German Aerospace Center (DLR)Mihai DATCU, German Aerospace Center (DLR)
200 | ICIP 2015 – Technical Program
17:50 SS4-O1.5 – LAND USE AND LAND COVER CLASSIFICATION BASE ON IMAGE SALIENCY MAP COOPERATED CODINGHui ZHANG, Institute of Software, Chinese Academy of Sciences (ISCAS)Jinfang ZHANG, Institute of Software, Chinese Academy of Sciences (ISCAS)Fanjiang XU, Institute of Software, Chinese Academy of Sciences (ISCAS)
TEC-O6: Inpainting and Stitching Wednesday, 16:30-18:30LECTURE Room: 204ASession Chair(s): Thrasyvoulos N . PAPPAS, Northwestern University
16:30 TEC-O6.1 – A USER-FRIENDLY INTERACTIVE IMAGE INPAINTING FRAMEWORK USING LAPLACIAN COORDINATESWallace CASACA, Brown University / University of Sao PauloDanilo MOTTA, University of Sao PauloGabriel TAUBIN, Brown UniversityLuis Gustavo NONATO, University of Sao Paulo
16:50 TEC-O6.2 – MULTI-VIEW IMAGE INPAINTING WITH SPARSE REPRESENTATIONS Sandhya THASKANI, TCS Innovation Labs- TRDDCShirish KARANDE, TCS Innovation Labs- TRDDCSachin LODHA, TCS Innovation Labs- TRDDC
17:10 TEC-O6.3 – FACE SKETCH SYNTHESIS USING NON-LOCAL MEANS AND PATCH-BASED SEAMINGLiang CHANG, Beijing Normal UniversityYves ROZENHOLC, Université Paris DescartesXiaoming DENG, Institute of Software, Chinese Academy of SciencesFuqing DUAN, Beijing Normal UniversityMingquan ZHOU, Beijing Normal University
17:30 TEC-O6.4 – GUIDED INPAINTING WITH CLUSTER-BASED AUXILIARY INFORMATIONThomas MAUGEY, INRIAPascal FROSSARD, EPFLChristine GUILLEMOT, INRIA
17:50 TEC-O6.5 – PATTERN-BASED K-LEVEL CUTSET RECONSTRUCTIONShengxin ZHA, Northwestern UniversityThrasyvoulos N . PAPPAS, Northwestern University
18:10 TEC-O6.6 – SUPERPIXEL-BASED DEPTH MAP INPAINTING FOR RGB-D VIEW SYNTHESISPierre BUYSSENS, GREYCMaxime DAISY, GREYCDavid TSCHUMPERLE, GREYCOlivier LEZORAY, GREYC
ICIP 2015 – Technical Program | 201
TEC-P16: Medical Feature Extraction and Analysis I Wednesday, 16:30-18:30POSTER Room: POSTER OSession Chair(s): Kjersti ENGAN, University of Stavanger
TEC-P16.1 – AUTOMATIC DETECTION OF COLONOSCOPIC ANOMALIES USING CAPSULE ENDOSCOPYLimamou GUEYE, Gjøvik University College (GUC)Sule Yildirim YAYILGAN, Gjøvik University College (GUC)Faouzi ALAYA CHEIKH, Faculty of Computer Science, Gjøvik University College
TEC-P16.2 – AUTOMATIC CLASSIFICATION OF TISSUES USING T1 AND T2 RELAXATION TIMESFROM PROSTATE MRI: A STEP TOWARDS GENERATION OF PET/MR ATTENUATION MAPJorge Arturo ZAVALA BOJORQUEZ, Université de BourgogneStéphanie BRICQ, Université de BourgognePaul Michael WALKER, Université de BourgogneAlain LALANDE, Université de Bourgogne
TEC-P16.3 – NOVEL FEATURES FOR MICROCALCIFICATION DETECTION IN DIGITAL MAMMOGRAM IMAGES BASED ON WAVELET AND STATISTICAL ANALYSISAya KHALAF, Cairo UniversityInas YASSINE, Cairo University
TEC-P16.4 – PROSTATE DETECTION FROM ABDOMINAL ULTRASOUND IMAGES: A PART BASED APPROACH Nur ALBAYRAK, Gebze Technical UniversityAyse OKTAY, Istanbul Medeniyet UniversitesiYusuf AKGUL, Gebze Technical University
TEC-P16.5 – FEATURE EXTRACTION FROM BILATERAL DISSIMILARITY IN DBT RECONSTRUCTED VOLUMEDae Hoe KIM, KAISTSeong Tae KIM, KAISTWissam J . BADDAR, KAISTYong Man RO, KAIST
TEC-P16.6 – HELICOBACTER PYLORI INFECTION DETECTION FROM MULTIPLE X-RAY IMAGES BASED ON COMBINATION USE OF SUPPORT VECTOR MACHINE AND MULTIPLE KERNEL LEARNINGKenta ISHIHARA, Hokkaido UniversityTakahiro OGAWA, Hokkaido UniversityMiki HASEYAMA, Hokkaido University
«
202 | ICIP 2015 – Technical Program
TEC-P17: Medical Feature Extraction and Analysis II Wednesday, 16:30-18:30POSTER Room: POSTER NSession Chair(s): Kjersti ENGAN, University of Stavanger
TEC-P17.1 – AUTOMATIC CLASSIFICATION OF SKIN LESIONS USING GEOMETRICAL MEASUREMENTS OF ADAPTIVE NEIGHBORHOODS AND LOCAL BINARY PATTERNSVictor GONZALEZ-CASTRO, École Nationale Supérieure des Mines de Saint-ÉtienneJohan DEBAYLE, École Nationale Supérieure des Mines de Saint-ÉtienneYanal WAZAEFI, Aix-Marseille University, LSIS UMR CNRS 7296Mehdi RAHIM, Aix-Marseille University, LSIS UMR CNRS 7296Caroline GAUDY, Hôpital de la Timone de Marseille, Service de DermatologieJean-Jacques GROB, Hôpital de la Timone de Marseille, Service de DermatologieBernard FERTIL, Aix-Marseille University, LSIS UMR CNRS 7296
TEC-P17.2 – ESTIMATING TWO-DIMENSIONAL BLOOD FLOW VELOCITIES FROM VIDEOSJun YANG, MCRLab, University of OttawaBenjamin GUTHIER, MCRLab, University of OttawaAbdulmotaleb EL SADDIK, MCRLab, University of Ottawa
TEC-P17.3 – SIMULTANEOUS EXTRACTION OF TWO ADJACENT BONY STRUCTURES IN X-RAY IMAGES: APPLICATION TO HIP JOINT SEGMENTATIONFatma OUERTANI, École de technologie supérieureCarlos VAZQUEZ, École de technologie supérieureThierry CRESSON, École de technologie supérieureJacques DE GUISE, École de technologie supérieure
TEC-P17.4 – DETECTION OF DIABETIC RETINOPATHY AND AGE-RELATED MACULAR DEGENERATION FROM FUNDUS IMAGES THROUGH LOCAL BINARY PATTERNS AND RANDOM FORESTSSandra MORALES, Universitat Politècnica de ValènciaKjersti ENGAN, University of StavangerValery NARANJO, Universitat Politècnica de ValènciaAdrián COLOMER, Universitat Politècnica de València
TEC-P19: Multiresolution and Wavelets Wednesday, 16:30-18:30POSTER Room: POSTER LSession Chair(s): Laurent NAVARRO, École des Mines de Saint-Étienne
TEC-P19.1 – FOUR-CHANNEL LIFTING-HOUSEHOLDER-BASED HADAMARD TRANSFORMTaizo SUZUKI, University of Tsukuba
TEC-P19.2 – DIVERGENCE-FREE WAVELET FRAMESEmrah BOSTAN, EPFLMichael UNSER, EPFLJohn Paul WARD, EPFL
TEC-P19.3 – LOGARITHMIC MULTIRESOLUTION ANALYSISLaurent NAVARRO, Mines Saint-Étienne, CIS-EMSE, CNRS: UMR 5307, LGFMichel JOURLIN, University of Saint-Etienne, Lab. H. Curien UMR CNRS 5516, FranceGuy COURBEBAISSE, University of Lyon, CREATIS, CNRS UMR 5220, INSERM U1044, UCB Lyon1, INSA Lyon
«
ICIP 2015 – Technical Program | 203
TEC-P19.4 – OPTIMIZED LIFTING SCHEMES BASED ON ENO STENCILS FOR IMAGEAPPROXIMATIONMounir KAANICHE, Institut Galilée, Université Paris 13Basarab MATEI, Institut Galilée, Université Paris 13Sylvain MEIGNEN, University of Grenoble
TEC-P19.5 – IMPROVED VARIATIONAL DENOISING OF FLOW FIELDS WITH APPLICATION TO PHASE-CONTRAST MRI DATAEmrah BOSTAN, EPFLStamatios LEFKIMMIATIS, UCLAOrestis VARDOULIS, EPFLNikolaos STERGIOPULOS, EPFLMichael UNSER, EPFL
TEC-P25: Supervised and Dictionary-based Approaches Wednesday, 16:30-18:30POSTER Room: POSTER KSession Chair(s): Ayman EL-BAZ, University of Louisville
TEC-P25.1 – A NOVEL FRAMEWORK FOR THE SEGMENTATION OF MR INFANT BRAIN IMAGESMahmoud MOSTAPHA, University of LouisvilleManuel CASANOVA, University of LouisvilleAyman EL-BAZ, University of Louisville
TEC-P25.2 – CLINICAL DEEP BRAIN STIMULATION REGION PREDICTION USING REGRESSIONFORESTS FROM HIGH-FIELD MRIJinyoung KIM, Duke University, Surgical Information Sciences (SIS)Yuval DUCHIN, University of Minnesota, Surgical Information Sciences (SIS)Guillermo SAPIRO, Duke University, Surgical Information Sciences (SIS)Jerrold VITEK, University of Minnesota, Surgical Information Sciences (SIS)Noam HAREL, University of Minnesota, Surgical Information Sciences (SIS)
TEC-P25.3 – SUPERTEXTON-BASED SEGMENTATION IN EARLY DROSOPHILA OOGENESISRodrigo NAVA, Czech Technical University in PragueJan KYBIC, Czech Technical University in Prague
TEC-P25.4 – SPARSITY PRESERVING MULTIPLE CANONICAL CORRELATION ANALYSIS WITH VISUAL EMOTION RECOGNITION TO MULTI-FEATURE FUSIONLei GAO, Zhengzhou University and son UniversityLin QI, Zhengzhou UniversityLing GUAN, Zhengzhou University and Ryerson University
TEC-P25.5 – DEEP STRUCTURED LEARNING FOR MASS SEGMENTATION FROM MAMMOGRAMSNeeraj DHUNGEL, The University of AdelaideGustavo CARNEIRO, The University of AdelaideAndrew BRADLEY, School of Information Technology and Electrical Engineering, The University of Queensland
TEC-P25.6 – AUTOMATIC SEGMENTATION OF PATHOLOGICAL LUNG USING INCREMENTAL NONNEGATIVE MATRIX FACTORIZATIONEhsan HOSSEINI-ASL, University of LouisvilleAyman EL-BAZ, University of LouisvilleJacek M . ZURADA, University of Louisville
«
«
«
«
204 | ICIP 2015 – Technical Program
TEC-P28: Filtering Wednesday, 16:30-18:30POSTER Room: POSTER MSession Chair(s): Keigo HIRAKAWA, University of Dayton
TEC-P28.1 – STOCHASTIC BILATERAL FILTER FOR HIGH-DIMENSIONAL IMAGESChristina KARAM, University of DaytonChong CHEN, University of DaytonKeigo HIRAKAWA, University of Dayton
TEC-P28.2 – ATOMIC DECOMPOSITION BASED ANISOTROPIC NON-LOCAL STRUCTURE TENSORZheng YUHUI, Nanjing University of Information Science and TechnologyZhou XIAOZHOU, Nanjing University of Information Science and TechnologyJeon BYEUNGWOO, Sungkyunkwan UniversitySun QUANSEN, Nanjing University of Science and TechnologyWu YI, Nanjing University of Information Science and Technology
TEC-P28.3 – HOW TO MAKE ND IMAGES WELL-COMPOSED WITHOUT INTERPOLATIONNicolas BOUTRY, EPITA Research & Development Laboratory (LRDE)Thierry GÉRAUD, EPITA Research & Development Laboratory (LRDE)Laurent NAJMAN, Laboratoire d’Informatique Gaspard-Monge (LIGM)
TEC-P28.4 – LOCALLY CONTROLLED REGULARIZED SPATIOTEMPORAL ANISOTROPIC DIFFUSIONPierre PORTEJOIE, CREATIS, INSA de Lyon, Université de Lyon, CNRS UMR 5220 – INSERM U1044 Simon MURE, CREATIS, INSA de Lyon, Université de Lyon, CNRS UMR 5220 INSERM U1044 Hugues BENOIT-CATTIN, CREATIS, INSA de Lyon, Université de Lyon, CNRS UMR 5220 INSERM U1044 Thomas GRENIER, CREATIS, INSA de Lyon, Université de Lyon, CNRS UMR 5220 INSERM U1044
TEC-P28.5 – EXPOSURE-ROBUST ALIGNMENT OF DIFFERENTLY EXPOSED IMAGESZhengguo LI, Institute for Infocomm ResearchJinghong ZHENG, Institute for Infocomm ResearchZijian ZHU, Institute for Infocomm ResearchShiqian WU, Wuhan University of Science and Technology
«
«
ICIP 2015 – Sponsors & Exhibitors | 205
SPONSORS & EXHIBITORS
CiscoWe create solutions built on intelligent networks that solve our customers challenges . Join us to make network and applications work better together . Help turn the Internet of Things into reality . Create novel network-based multimedia analytics, and build innovative cloud, wireless, and software-defined networking systems for video and collaboration .
Disney ResearchDisney Research is an international network of research labs, with the mission to push the scientific and technological forefront of innovation at The Walt Disney Company .Disney Research combines the best of academia and industry, by doing both basic and application-driven research .We honor Walt Disney’s legacy by innovating and deploying our innovations on a global scale .
Faciometrics FacioMetrics LLC licenses technology for facial image analysis (e .g ., 2D/3D facial feature tracking, facial expression analysis, head pose and gaze estimation, facial attribute recognition, face recognition, 3D face reconstruction) . We target applications in retail sentiment analysis, facial animation, face editing, face recognition, virtual makeup, emotion measurement and analytics among others .
GoogleMuch of the world’s data is in the form of visual media . We help capture, enhance, organize, and index this information . We build systems that range from cameras, to processing algorithms, to storage, enhancement, and sharing platforms . These systems are designed to enable computer perception of visual data enabled by machine learning, computational imaging, and advanced image and video processing techniques . Our approach is data-driven, on both mobile and cloud platforms, leveraging large data-sets and parallel computing clusters to solve problems at scale .Our work in image/video annotation and enhancement positively impacts a wide variety of Google products including Android, Google Photos, Image Search, Street View, Google Earth, and many more .As a leader in image processing research, Google will have a strong technical presence at ICIP 2015 in Quebec City, with several Googlers publishing work . Stop by our booth and chat with our researchers about the projects and opportunities at Google that go into enabling imaging at scale for hundreds of millions of people!
206 | ICIP 2015 – Words from Sponsors & Exhibitors
ICIP 2016The 23rd IEEE International Conference on Image Processing (www .icip2016 .com) will be held on September 25-28, 2016, Phoenix, Arizona, the Grand Canyon State . ICIP attendees include experienced researchers/developers in image/video processing and computer vision, providing great learning, networking and recruiting opportunities . ICIP2016 features world-class speakers, tutorials, exhibits, and vision technology showcase .
International Year of the LightOn December 23, 2013, The United Nations General Assembly proclaimed 2015 as the International Year of Light and Light-based Technologies (IYL2015) . Championed by scientific organizations around the world, IYL2015 will promote improved public and political understanding of the central role of light in the modern world and celebrate significant scientific anniversaries occurring in 2015 . Vist IYL web site at www .light2015 .org/Home .html
LogitechLogitech is a world leader in products that connect people to the digital experiences they care about . Spanning multiple computing, communication and entertainment platforms, Logitech’s combined hardware and software enable or enhance digital navigation, music and video entertainment, gaming, social networking, audio and video communication over the Internet, video security and home-entertainment control . Founded in 1981, Logitech International is a Swiss public company listed on the SIX Swiss Exchange (LOGN) and on the Nasdaq Global Select Market (LOGI) .
MathWorksMathWorks is the leading developer of mathematical computing software for engineers and scientists . Founded in 1984, MathWorks employs over 3000 people in 15 countries, with headquarters in Natick, Massachusetts, U .S .A .MATLAB®, the language of technical computing, is a programming environment for algorithm development, data analysis, visualization, and numeric computation . Simulink® is a graphical environment for simulation and Model-Based Design of multidomain dynamic and embedded systems . The company produces nearly 100 additional products for specialized tasks such as data analysis and image processing .
Microsoft ResearchFounded in 1991, Microsoft Research conducts both basic and applied research in computer science and software engineering in order to advance the state of the art of computing, help fuel the long-term growth of Microsoft and its products, and solve some of the world’s toughest problems through technological innovation .
ICIP 2015 – Sponsors & Exhibitors | 207
NetflixNetflix is the world’s leading internet subscription service for enjoying movies and TV shows .Netflix is the world’s leading Internet television network with over 62 million members in over 50 countries enjoying more than 100 million hours of TV shows and movies per day, including original series, documentaries and feature films . Members can watch as much as they want, anytime, anywhere, on nearly any Internet-connected screen . Members can play, pause and resume watching, all without commercials or commitments .
NvidiaSince 1993, NVIDIA (NASDAQ: NVDA) has pioneered the art and science of visual computing . The company’s technologies are transforming a world of displays into a world of interactive discovery -- for everyone from gamers to scientists, and consumers to enterprise customers . More information at http://nvidianews .nvidia .com/ and http://blogs .nvidia .com/ .
OMRONOmron Corporation is an electronics company based in Kyoto, Japan . Omron’s primary business is the manufacture and sale of automation components, equipment and systems, which includes machine vision systems for factory automation, face recognition software for digital equipment and visual surveillance systems for safety and security in public space .
master QC logo
QualcommBillions, maybe trillions of times a day… That’s how often people around the world touch something made better by Qualcomm . It could be the smartphone in your pocket, the tablet on your coffee table, that wireless modem in your briefcase… it could even be that navigation system in your car or that action camera strapped to your chest . Who is Qualcomm, and what do we do? We are engineers, scientists and business strategists . We are from many different countries and speak many different languages . We come from diverse cultures and have unique perspectives . Together, we focus on a single goal—invent mobile technology breakthroughs .
Québec City Tourism OfficeBienvenue à Québec! We are so happy you’re finally here . We know the frenzy of preparing to go to a convention . You’re excited to meet your peers and make new connections . You need to keep on top of your work but have the urge to take in all Québec City has to offer . We don’t blame you! Thanks to André Morin, President of Optelis and one of Québec City’s most dedicated and efficient event ambassador, you get to experience our 400-year history and discover our European flair . Québec City will welcome you as you are, all to better send you home relaxed, with a head full of memories and a tummy full of yummy meals . We know you want to be productive while in Québec . Stay connected using the Québec City Convention Centre’s free wireless high-speed Internet and the city’s vast network of free Wi-Fi thanks to ZAPQuébec .org . We bet your success will make history, and we’re here for you, every step of the way . We hope to see you again soon . À bientôt! Visit us at www .quebecbusinessdestination .com
208 | ICIP 2015 – Words from Sponsors & Exhibitors
SpringerLooking to publish your research? Discover Springer’s print and electronic publication services, including Open Access! Get high-quality review, maximum readership and rapid distribution . Visit our booth or springer .com/authors . You can also browse key titles in your field and buy (e)books at discount prices . With Springer you are in good company .
TechnicolorTechnicolor is a worldwide technology leader in the media and entertainment sector . Our three research and innovation centers and our creative talent pool enable us to lead the market in delivering advanced services to content creators and distributors . We offer content-related technologies and services to the motion picture, broadcast and commercial advertising industries, as well as a wide range of solutions to Pay-TV operators and network service providers for the delivery of digital entertainment, data, voice, and smart home services . We also benefit from an extensive intellectual property portfolio focused on imaging and sound technologies, supporting our thriving licensing business .
YouTubeAt YouTube we process more than 300 hours of video every minute and create hundreds of output formats faster than real time, using Google’s distributed computing platforms . As part of Google, our video infrastructure pipeline processes video for other products e .g . Photos, Google Play Movies and Drive . We work with all the video imaging teams at Google including Research, Android, Chrome Media, Hangouts and VR . We’re involved with launching products in video compression, transcoding, enhancement and analysis, especially for video fingerprinting . Recent product launches including 360Video (omnidirectional) processing, multiangle video playback, slo-motion effects, advanced video compression and automated video denoising, have all leveraged our close relationships with the DSP research community . We are delighted to be sponsoring ICIP again . Once more we are hosting a workshop to introduce our activities in Imaging DSP/Vision research and open source codec development to the community . Stop by our booth and attend our workshop on Tuesday morning at 10:30 am for a snapshot of exciting new developments, with which you can get involved!
ICIP 2015 – Useful Information | 209
Conference Information
VenueQuébec City Convention Centre
900, René-Lévesque East Blvd, 2nd floorQuébec QC G1R 2B5CANADAPhone: +1418644 4000 (US & Canada 1888679 4000)Fax: +1418644-6455 www .convention .qc .ca
ICIP Entrance900, Honoré-Mercier BoulevardQuébec QC G1R 5T8CANADA
Registration Desk
The registration desk is located in Hall 2000 of the main floor of the Convention Centre .
Hours of operationSunday September 27, 2015 07:00 – 19:00Monday, September 28, 2015 07:00 – 18:00Tuesday, September 29, 2015 07:00 – 18:00Wednesday, September 30, 2015 07:00 – 18:00
Speaker Ready Room
All presenters of ORAL presentations are mandatorily required to visit the speaker ready room and provide their presentation on a USB key to the IT technician . This will ensure that the technician has met with all presenters and that he/she is fully aware of your presentation requirements . Your collaboration is required to that all sessions run as smoothly as possible . Shortly before the session where you talk is scheduled starts, your presentation and any associated material will automatically be pushed to the computer .
This methodology has a number of advantages:• Your session chair will know ahead of time that you are attending and will be able to track now-shows;• You will be insured that all your material will show up properly on the conference AV systems and you
will have the support of a technician to correct problems, if any, before they happen• The sessions will run more smoothly .
There will NO copies of ant presentation material kept after the end of the conference .
The speaker ready room is located in room 2102A on the 2nd floor of the Québec City Convention Centre . This room will be available for all presenters to upload their presentations with the assistance of an IT technician .
USEFUL INFORMATION
210 | ICIP 2015 – Useful Information
Operating hours:Sunday, September 27 16:00 – 18:00 Tuesday September 29 07:00 – 18:00Monday, September 28 07:00 – 18:00 Wednesday, September 30 07:00 – 16:30
In case of EmergencyIn case of Emergency, please contact Mr . Pierre Bolduc at +1418928-4854 .
Internet CaféThe Internet Café is located on level 3 in the Foyer area . You are welcome to use this at any time during the official opening hours .
WiFi InternetICIP 2015 is pleased to offer all participants free wireless Internet access for the duration of the conference . This connection offers speeds of 5 Mbps and a total 3GB bandwidth per day per device . Wireless Internet Connection Procedure:1 . Activate the wireless networking card on your device;2 . Select the Videotron_Centre_des_congrès network from the list of available networks;3 . Open a browser; you will be redirected to the Free Wireless Internet Access Vidéotron page) .4 . Select Access wireless Internet then Access Internet with Access Code and then enter the access code 915 5 . Accept the terms and conditions;6 . Click on « Connect now » . Notes1 . Complete this procedure only on the first connection to the network .2 . For any problem concerning the configuration or the connectivity of this connection, please call
+1 418 649-5219 3 . The access code will be valid until September 30, 2015 at 23:30
Mobile AppThe "ICIP 2015" is available on the following app stores:- Apple App Store (iOS 7 and higher)- Google Play (Android 2 .2 .3 and higher)- BlackBerry World (BlackBerry 10 and higher)- Windows Phone Store (Windows Phone 8 and higher) You can also view the app online at http://eventmobi .com/icip2015/
MessagesMessages received by the Organizers for delegates will be posted on the message board located close to the Registration Desk in Hall 2000 . Messages between delegates may also be left on this board .
Mobile PhonePlease ensure that your cellular phone, pager, etc ., are turned off or put on silent/vibrate mode during sessions .
ICIP 2015 – Useful Information | 211
Badges
Please wear your name badge at all times . This will ensure your access to the technical sessions and the Exhibition Hall .
Tickets for Social Events
You will be given a package containing your name badge and the tickets you ordered for the tours and social events when you check in at the Registration Desk . Please bring the appropriate ticket(s) to all social events . Additional tickets based on space availability will be available for purchase at the Registration Desk .
Accessible Facilities
At the Québec City Convention Centre, you will find spaces, entrances, equipment, and services by an underground passageway adapted to meet the needs of each and every guest . The Centre is a secure facility and offers guests with disabilities enhanced greeting services and personalized support . The Convention Centre is also linked by underground passageway to the Delta Québec, which has 20 rooms adapted for the mobility impaired .
• The facilities are adapted to the needs of the mobility impaired and comply with the National Building Code of Canada as well as the American Disability Act;
• Telephone device for the deaf;• Restrooms with automatic doors;• Each public floor is wheelchair accessible;• Wheelchairs available upon request;• Adapted elevators and mobile ramps for wheelchairs;• Help and supervision for the mobility impaired during emergencies .
Travel Tips
Currency, Banking, ATM Machines & Credit Cards
The monetary system in Canada is based on dollars and cents and the currency is the Canadian Dollar .
Foreign currencies can be exchanged at banks and at foreign currency exchange offices either at the Airport or at other locations throughout the city .
Bank debit or credit cards are the most convenient means of getting cash at the many Automatic Teller Machines (ATMs) . ATMs are spread throughout the city and accept cards with the Interac, Plus, and Cirrus networks . Most are in operation 24 hours a day / 7 days a week .
Most businesses accept U .S . currency and traveler’s cheque, as well as major credit cards (Visa, MasterCard, and American Express) .
Sales Taxes
There is a 5% Goods and Services Tax (GST) in effect in Canada and a Provincial Sales Tax (PST) of 9,975% in the Province of Québec, for a combined tax rate of 14,975% . This tax is applicable to most items and is not refundable . An additional tax is applicable to hotel rooms .
212 | ICIP 2015 – Useful Information
Medical Insurance
Visitors are not covered by Canadian health insurance plans . Check with your personal medical plan before leaving your home country to ensure you have adequate travel insurance .
Language
French and English are Canada’s two official languages . French is the predominant language in Québec City . However, most, if not all, banks, hotels, airline offices, shops, and key visitor attractions have multilingual staff and most citizens will be able to answer in both languages .
Electricity
The electrical current is the same as in the United States: 110 volts AC at 60Hz adapters are required for appliances from other countries .
Weather
During the autumn months in September and October, the Canadian maple trees blaze with colour for weeks on end and the skies are often dazzling blue . The so-called Indian summer arrives early in Québec City . It usually lasts 2-3 weeks from mid/late September to early/mid-October . Nature’s beauty is very colorful in the fall and a very popular time to visit the province . With average minimum and maximum daily temperatures of 7 and 18°C (45-65°F) in September, you may need a light jacket or sweater to keep warm .
Time Zone
Québec City is in the Eastern Standard Time Zone (GMT-0500) . Daylight Savings Time (DST) is in effect from 2:00 a .m . on March 8, 2015 until 2:00 a .m . on November 1, 2015 .
Telephone Service
Québec City employs two separate area codes: 418 and 581 . Calls within the greater Québec City area are local regardless of the area code . However, you will need to dial all ten digits of the phone number in order to be connected . Check with your cellular service provider to ensure your plan offers roaming/long distance service in Québec City .
Getting Around the City
Airport Transfers
The Jean-Lesage International Airport is located 16 km (10 miles) from the centre of the city . Cab fare from the airport to the city centre is a flat CAD $35 . All of these services accept major credit cards .http://www.aeroportdequebec.com/en/to-and-from-the-airport/taxis/
ICIP 2015 – Useful Information | 213
Public Transit (RTC local buses)
The city bus network (Réseau de transport de la capitale (RTC)) serves Québec City, Saint-Augustin-de-Desmaures, Wendake, and Ancienne-Lorette . The bus fares is CAD 3 .25 Effective as September 1, 2014 . Exact change is requiredDaily passes as well as 2-day and weekly passes are also available and are generally advantageous solutions .http://www.rtcquebec.ca/
Ferry
The ferry links Québec City and Lévis 7 days a week, 365 days a year . It sails every half hour during day time and hourly at night .http://traversiers.com/traverses/quebeclevis_1.php
Limousine
Limousine rentals services are available from various suppliers .
Taxi
Québec City area taxis can be identified by the sign on their roof . There are several companies . We suggest that you call one of them and they will send a car . You can also get a cab at one of the various taxi stands in the city and in front of any major hotels .
Car
Car rentals can provide a practical way to visit areas less than an hour from downtown, such as the Orleans Island (Île d’Orléans), and nearby regions such as Côte-de-Beaupré, Jacques-Cartier, and Portneuf .
Information on vehicle and parking regulations: http://www.quebecregion.com/en/useful-information
Motorcycle
Motorcycles can be rented . However, note that motorcycles are not allowed inside the walls of the Old City unless you have a reservation at a hotel inside the walls .
Cycling
The Québec City area has close to 400 km of bicycle paths and bikeways . For bicycles rentals, visit:www.cycloservices.net www.velopasse-sport.com
214 | ICIP 2015 – Useful Information
Addresses & Phone Numbers
Airlines
Air Canada (www.aircanada.com) Reservations: 1-888-247-2262 Information: 1-888-422-7533
Porter Airlines (www.flyporter.com) Reservations: 1-888-619-8622
United Airlines (www.united.com) Reservations: 1-800-538-2929 (International) 1-800-864-8331 (Domestic)
WestJet (www.westjet.com) Reservations & flight status: 1-888-937-8538 (1-888-WESTJET)
Hilton Québec1100, Boulevard René-Lévesque EstQuébec QC G1R 4PPhone: +1 418-647-241Fax: +1 418-647-6488
Hôtel Clarendon57, rue Sainte-Anne,Québec QC G1R 3X4Phone: +1 418-692-2480Fax: +1 418-692-4652
Hôtel Le Concorde1225 Cours du Général-de Montcalm, Québec, QC G1R 4W6 Phone: +1 418-647-2222
Hôtel Quartier2955 Boulevard LaurierQuébec QC G1V 2M2Phone : +1418 650-1616
Manoir Victoria44, Côte du Palais,Québec QC G1R 4H8Phone: +1 418-692-1030Fax: +1 418-692-3822
Mariott Courtyard Québec850 Place D’Youville,Québec QC G1R 3P6Phone: +1 418-694-4004Fax: +1 418-694-4007
Palace Royal775 Honoré-Mercier AveQuébec QC G1R 6A5Phone: +1418 694-2000
TRYP Hotel Pur395 Rue de la Couronne,Québec QC G1K 7X4Phone: +1418 647-2611
US Airways (www.usairways.com) Reservations: 1- 888-240-4770
American Airlines (www.aa.com) Reservations: 1-800-433-7300
Delta (www.delta.com) Reservations: 1-800-241-4141 (International) 1-800-221-1212 (Domestic)
Air Transat (http://www.airtransat.com) Reservations: 1-866-255-4871
Taxis
Taxi Coop 1-418-525-5191Taxi Québec 1-418-522-2001
Hotels
Château Bellevue16 rue de la Porte,Québec QC G1R 4M9Phone: +1 418-692-2573Fax: +1 418-692-4876
Château Frontenac1 rue des Carrières,Québec QC G1R 4P5Phone: +1418 692-3861
Château Laurier1220, Place George-V Ouest,Québec QC G1R 5B8Phone: +1 418-522-8108Fax: +1 418 -524-8768
Delta690, Boulevard René-Lévesque Est,Québec QC G1R 5A8Phone: +1 418 647-1717Fax: +1 418 647-2146
Join us to make networks and applications work better together. Help turn the Internet of Things into reality. Create novel network-based multimedia analytics, and build innovative cloud, wireless, and software-defined networking systems for video and collaboration.
Send us your resume [emailprotected] Learn more at research.cisco.com
We create solutions built on intelligent networks that solve our customers’ challenges
Research & Innovation at Cisco
216 | ICIP 2015 – Index of Authors and Session Chairs
AAABED, Mohammed 146, 177AANSTOOS, James V . 199AARON, Anne 166ABBAS, Hazem 80ABBOTT, Tyler 167ABBOUD, Feriel 108ABBOUD, Michel 91ABDEL-MOTTALEB, Mohamed 86ABDELFATTAH, Riadh 74ABEYDEERA, Maleen 161ABOU EL-GHAR, Mohamed 168,
192ABRY, Patrice 61ACHIM, Alin 70, 82, 117, 186ACTON, Scott T . 104ADAM, Katerina 103ADEL, Mouloud 150ADHIKARI, Lasith 148AELTERMAN, Jan 128AFIFI, Yusuf 80AFLAKI, Payman 127AFONSO, Manya 94AFONSO, Vladimir 108AFRIDI, Hina 156AFTAB, Khurrum 160AGENJO, Javi 95AGOSTINI, Luciano 108AGRAFIOTIS, Dimitris 76, 163,
165AGUILERA, Cristhian 179AHMAD, Ola 73AHMAD, Omer Rashid 90AHMAD, Rizwan 63AHMED, Faisal 195AHN, Kiok 158AI, Haizhou 122AILLIOT, Pierre 186AIZAWA, Kiyo 121AIZAWA, Kiyoharu 122, 143, 158AKERFELT, Malin 81AKGUL, Yusuf 201AKHAN, Ece 118AKHLAG, Mohammadreza 150AKIL, Mohamed 143AKIYAMA, Hiroki 149AL ALWANI, Adnan 157AL-HAMADI, Ayoub 90, 158AL-MAADEED, Somaya 150ALAGHBARI, Zaher 105ALAIN, Martin 175ALAM, Md Mushfiqul 178
ALAN, Tanfer 167ALATA, Olivier 60ALATAN, A . Aydin 180, 181, 189ALAUDAH, Yazeed 163ALAYA CHEIKH, Faouzi 201ALBALOOSHI, Fatema 191ALBAYRAK, Nur 201ALEXANDER, Daniel 136ALI CHERIF, Arab 150ALJADAANY, Raied 137ALKHALDI, Nora 117ALLARD, Michelle 152ALLEBACH, Jan 143, 145, 162,
181ALLILI, Mohand Said 105ALNAJAR, Fares 195ALREGIB, Ghassan 75, 146, 163AMANO, Toshiyuki 142AMER, Maria Aishy 66, 67, 143,
144, 145AMIN, Asjad 75AMIOT, Carole 135AMON, Peter 107AN, Lingling 77AN, Ping 174ANANTRASIRICHAI, Nantheera
138ANDROUTSOS, Dimitrios 76ANGST, Roland 51ANTONINI, Marc 108AOKI, Takafumi 75AOUADA, Djamila 91APAZA-AGÜERO, Karl 129, 131APOSTOLOPOULOS, John 165APPLEBOIM, Eli 49ARAUJO, Andre 51ARAUJO, Arnaldo 73ARCE, Gonzalo R . 179ARDABILIAN, Mohsen 91, 92, 128ARGUELLO, Henry 179ARIKI, Yasuo 188ARNFRED, Jonas 124ARRUFAT, Adrià 126ARTEAGA, Reynaldo 174ARVANITOPOULOS, Nikolaos 162ASAD, Muhammad 111ASAKAWA, Chieko 67ASARI, Vijayan K . 73, 191ASH, Joshua 63ASHRAF, Nazim 190ASPIRAS, Theus 73ATADJANOV, Ibragim 70
INDEX OF AUTHORS AND SESSION CHAIRS
ATALAY, Rengül Ç . 118ATHAR, Shahrukh 109ATNAFU, Dessalegn 121ATTO, Abdourrahmane 60AU, Oscar C . 89, 170, 177AUDIGIER, Romaric 73AURÍA, Anna 136AVGERINAKIS, Konstantinos 103,
147AYDIN, Tunc 76AYECH, Mohamed Walid 173AYHAN, Bulent 179AYTEKIN, Caglar 51AYVACI, Alper 172AZIMIFAR, Zohreh 72
BBA, Silèye 68BABA, Tatsuya 56, 171BABAEE, Maryam 87BABAEE, Mohammadreza 87, 113BABAEIAN, Amir 113BACKES, Andre 131BADDAR, Wissam J . 105, 201BADOUAL, Anaïs 169BAE, Sung-Ho 185BAHMANYAR, Gholamreza 197BAHMANYAR, Reza 184BAI, Jun 97BAI, Li 84, 97BAI, Xiangzhi 167, 170BAIK, Hyunki 161BALANOV, Amnon 145BALTENBERGER, Ryan 171BAMPIS, Christos 78BANDARABADI, Mojtaba 113BANIC, Nikola 64BARANIUK, Richard 148BARCELOS, Celia 131BARCENA-HUMANES, Jose-Luis
198BARDIA, Rishabh 68BARDONNET, Antoine 119BAROFFIO, Luca 138BARONE-ROCHETTE, G . 168BASARU, Rilwan Remilekun 111BASKURT, Atilla 141BASSIOUNY, Ahmad 181, 198BASTANI, Farokh 138BASTANI, Vahid 193BASTIN, Philippe 119BATABYAL, Tamal 104, 157
ICIP 2015 – Index of Authors and Session Chairs | 217
BATENBURG, Kees Joost 106BATOOL, Nazre 80BATTIATO, Sebastiano 182BATTISTI, Federica 182BÄTZ, Michel 89, 135BAUDRIER, Étienne 159BAXTER, Rolf Hugh 69, 157, 158BAYER, Christine 187BAYESTEHTASHK, Alireza 113BAYRAMOGLU, Neslihan 81BECKER, Jean-Marie 98BELLON, Olga 129, 131BEN ABDALLAH, Wajih 74BEN AHMED, Olfa 152BEN AMAR, Chokri 152BEN MAKHLOUF, Mehdi 70BEN-ARTZI, Gil 125BENEZETH, Yannick 57BENGTSON, Kurt 143BENNAMOUN, Mohammed 142BENOIS-PINEAU, Jenny 101, 124,
134, 147, 148, 152BENOIT-CATTIN, Hugues 204BENRHAIEM, Rania 69BENSRHAIR, Abdelaziz 55BENZINOU, Abdesslam 91BERAN, Vitezslav 96BERGER, Kai 185BERGER, Kongfeng 185BERGERON, Cyril 184BERGEVIN, Robert 67BERKNER, Kathrin 182BERRETTI, Stefano 102BERTAUX, Aurélie 57BERTHOUMIEU, Yannick 48,
141, 197BERTOLINO, Pascal 59, 78BESTAGINI, Paolo 130BETANCOURT, Alejandro 139BETTENS, Stijn 113BEWLEY, Alex 193BHAGAVATULA, Chandrasekhar
68BHALERAO, Abhir 49BHANDARI, Smriti 187, 188BHANU, Bir 153BHASKAR, Harish 66BHAVSAR, Arnav 137BHUIYAN, Alauddin 168BHUIYAN, Amran 94BHUYAN, M . K . 119BIAN, Xiao 183, 192BIDAN, Christophe 95BILODEAU, Guillaume-Alexandre
67, 73, 83, 84, 193BLANCH, Carolina 179BLANCHART, Pierre 197BLASI, Saverio G . 54, 79BLASINSKI, Henryk 112BLAT, Josep 95BLINDER, David 113, 177
BLOSTEIN, Dorothea 116, 197BLU, Thierry 88, 119, 149BOGISCHEF, Viktor 145BOKARIS, Panagiotis-Alexandros
57BOMBRUN, Lionel 65, 197BOMMA, Sushma 156BONETTO, Margherita 94BORDA, Monica 65BORS, Adrian 58, 79BOSCH, Marc 167BOSILJ, Petra 132BOSTAN, Emrah 202, 203BOUACHIR, Wassim 67BOUBCHIR, Larbi 150BOUGUILA, Nizar 60BOUKIR, Samia 86BOULKENAFET, Zinelabidine 137BOULMERKA, Aissa 105BOUMAN, Charles 63, 106, 116,
134BOURENNANE, Salah 150BOURIDANE, Ahmed 150BOUTIN, Mireille 114BOUTRY, Nicolas 204BOUTTEAU, Rémi 55BOUZID, Boubker 167BOVIK, Alan 62, 197BOYADJIS, Benoit 184BOZORGTABAR, Behzad 157BRADLEY, Andrew 203BRECKON, Toby 111, 140BREGOVIC, Robert 180BREIER, Matthias 143BRESLER, Yoram 196BRIASSOULI, Alexia 103, 147BRICQ, Stéphanie 201BRIZUELA, Marcos 152BROISAT, A . 168BRONSTEIN, Alex 111BRUCE, Neil 146BRUNA, Arcangelo R . 182BRUYLANTS, Tim 177BUDAGAVI, Madhukar 165, 177BUDDLE, Lachlan 136BUGEAU, Aurelie 130BUI, Tu 143BULL, David 59, 70, 76, 138, 145,
159, 164, 165BUNKE, Horst 57BURGHARDT, Tilo 103BURN, Jeremy 59, 138BUSHNEVSKIY, Andrey 110, 133BUSO, Vincent 148BUYSSENS, Pierre 62, 78, 200BYEUNGWOO, Jeon 204
CCABARET, Laurent 123CABEZAS, Ferran 140CABRERA, Julián 92
CAELLI, Terry 57CAGATAY, Nazli Deniz 198CAGNAZZO, Marco 109CAI, Bolun 69CAI, Dongqi 157CAI, Jianfei 85CAI, Jiji 89CAI, Ling 134CAI, Qiang 49CAI, Weidong 136, 150CAI, Xun 177CAINIAN, Li 81CAKIR, Fatih 83CALHOUN, Vince D . 150CAMARA CHAVEZ, Guillermo 89CAMBARERI, Valerio 179CAMPBELL, Neill 103CAMPISI, Patrizio 87, 120CANAGARAJAH, Nishan 103CANALES-RODRÍGUEZ, Erick 136CAO, Baoxiang 81CAO, Donglin 135CAO, Guo 74CAO, Jian 49, 77CAO, Jun 190CAO, Xiaochun 49CAO, Yu 141CAO, Zhiguo 141, 175, 188CARAFFA, Laurent 169CARLI, Marco 182CARLIER, Axel 140CARNEIRO, Gustavo 115, 120,
170, 187, 203CARRÉ, Philippe 62, 162CASACA, Wallace 200CASANOVA, Manuel 154, 203CATHELINE, Gwenaelle 152CAVALCANTI, George 68, 139CAVALLARO, Joseph 81CAVESTANY, Pedro 111CESANA, Matteo 138ÇETIN, A . Enis 118, 119, 172ÇETIN, Mujdat 85, 116ÇETIN, Mustafa S . 150CHAE, Oksam 158CHAHIR, Youssef 157CHAI, Eric 99CHAI, Xiujuan 88CHAIB-DRAA, Brahim 119CHAINAIS, Pierre 72CHAKER, Rima 105CHAKRAVORTY, Tanushri 73CHAM, Wai-Kuen 126, 186CHAN, Chee Seng 101CHAN, Kai Chi 172CHAN, Shingchow 118CHAN, Stanley 151, 152CHAN, Yui-Lam 127CHAN, Yuk Hee 160CHANDLER, Damon 178CHANDRASEKHAR, Vijay 53, 90
218 | ICIP 2015 – Index of Authors and Session Chairs
CHANG, Hsing-Chun 129CHANG, Kai-Hsiang 92CHANG, Liang 200CHANG, Ming-Ching 165, 193CHANG, Wen-Tsung 77CHANG, Yi 75CHANNAPPAYYA, Sumohana 63CHANUSSOT, Jocelyn 135CHAO, Hongyang 56CHAO, Yung-Hsuan 78CHARRIER, Christophe 51, 62CHARVILLAT, Vincent 140CHATEAU, Thierry 55CHATTOPADHYAY, Tanushyam
157CHAUDHURI, Subhasis 52CHAUDHURY, Kunal 149, 169CHAUX, Caroline 75CHAVES, Jason 51CHE, Wenbin 82CHELLAPPA, Rama 75, 87, 88,
111, 123CHEN, Baohua 114CHEN, Bin 154CHEN, Bo Chun 196CHEN, Boqi 117CHEN, Chang 67CHEN, Chang Wen 67, 159CHEN, Chen 183, 190CHEN, Chong 204CHEN, Danny 71CHEN, Dongming 128CHEN, Fan 171CHEN, Gengjie 67CHEN, Homer 56, 170, 183CHEN, Huafeng 192CHEN, Hui 50CHEN, Hwann-Tzong 71CHEN, Jiahui 73CHEN, Jiansheng 130CHEN, Jing 141CHEN, Jinhui 188CHEN, Jixu 165CHEN, Jun 157, 175, 192CHEN, Jun-Cheng 88CHEN, Junkai 159CHEN, Junyou 107CHEN, Kuan-Hua 190CHEN, Li 162CHEN, Liming 128CHEN, Ming 181CHEN, Po-Chang 56CHEN, Qian 142CHEN, Rui 72CHEN, Shuixian 94CHEN, Suen-Yu 121CHEN, Tao 66, 77, 174CHEN, Tsuhan 194CHEN, Wei 92, 159CHEN, Wei-Yu 142CHEN, Wenyu 60, 70, 155
CHEN, Wujun 99CHEN, Xiaogang 198CHEN, Xiaozhi 84CHEN, Xilin 88CHEN, Xin 118CHEN, Xu 135, 147CHEN, Yang 154CHEN, Yanyun 141CHEN, Yen-Wei 168CHEN, Yi-Wen 54CHEN, Yibo 186CHEN, Ying 54CHEN, Yingying 105CHEN, Yong 128CHEN, Yong-Sheng 127CHEN, Yu 92CHEN, Yu-Hui 187CHEN, Yue 177, 199CHEN, Zenghai 159CHEN, Zetao 193CHEN, Zhaoyun 73CHEN, Zhiguo 167CHENG-LONG, Xiao 91CHENG, Guangliang 123CHENG, Hengda 52, 136CHENG, Jierong 60, 70, 155CHENG, Jun 157CHENG, Wu 170CHENOT, Jean-Hugues 108CHERIET, Mohamed 112, 168CHEUNG, Gene 57, 93CHEUNG, Ngai-Man 159CHEUNG, Sen-Ching Samson 61,
106, 129, 137CHEVALDONNÉ, Marc 55CHEVALIER, Marion 174CHI, Zheru 159CHIA, Shue Ching 60, 70, 155CHIEN, Shao Yi 56, 196CHIN, Sang 149CHO, Eunji 158CHO, Yangho 178CHOE, Gyeongmin 103, 128CHOI, Jae-Seok 185CHOI, Jin Young 57, 104, 155CHOI, Jongwon 57, 155CHOI, Sang-Il 196CHOI, Sunghwan 128, 178CHOI, Yukyung 122CHOMAZ, Jean-Marc 57CHOU, Philip A . 78, 110CHOU, Shih-Hung 76CHOUDHURY, Anustup 135CHOUZENOUX, Emilie 108CHRISTIANSON, James 90CHRISTINE, Guillemot 177CHRISTMAS, William 139, 196CHUAH, Seong Ping 159CHUANG, Jen-hui 127CHUANG, Tzu-Der 54CHUNG, Audrey 99, 124, 172
CHUNG, Shang-Luen 92CHUNXIA, Zhao 74CHWYL, Brendan 99, 124CICCONET, Marcelo 48CIGLA, Cevahir 181, 189CLAUSI, David 62, 124CLIFFORD, Jeff 96COGRANNE, Remi 162COHEN, Laurent 153COLEMAN, Sonya 58COLLET, Christophe 73, 199COLLOMOSSE, John 143COLOMER, Adrián 202COMER, Mary 99CONCI, Nicola 105, 156CONG, Yang 153CONNOR, Barry 106CONTE, Donatello 150CORD, Matthieu 50, 174CORDARA, Giovanni 55CORKE, Peter 193, 194CORNACCHIA, Maria 138, 139CORREDOR, Germán 187COSMAN, Pamela 99COSSAIRT, Oliver 116COSTA, Adriano 68COSTA, Filipe 130COULOMBE, Stéphane 48, 101,
126, 155, 176COURBEBAISSE, Guy 150, 202COUTO, Leandro 131COZOT, Rémi 114CRESSON, Thierry 202CREUSERE, Charles 88CRIVELLI, Tomas 69CRUCIANU, Michel 124CUI, Shiyong 199CUI, Zhiming 120
DDA SILVA, Allan 192DA SILVA, Eduardo A .B . 108,
182, 192DA, Feipeng 121DADUCCI, Alessandro 136DAHM, Nicholas 57DAI, Donghai 152DAI, Feng 182DAI, Ji 104DAI, Qionghai 142, 183DAI, Qiqin 135DAI, Tao 170DAI, Weiqun 198DAISY, Maxime 200DAMGHANIAN, Mitra 182DAN, Wang 132DANG, Chinh 151DANIELS, Geoffrey 59DANSEREAU, Richard 53DANTAS, Daniel Oliveira 161DAS, Abir 157
ICIP 2015 – Index of Authors and Session Chairs | 219
DAS, Samarjit 142DATCU, Mihai 74, 198, 199DAUPHIN, Gabriel 127DAVIS, Philip 88DAYA, Ibrahim 166DE BEENHOUWER, Jan 63DE co*ck, Jan 184DE GOUSSENCOURT, Timothée
59, 78DE GUISE, Jacques 202DE NATALE, Francesco G .B . 156DE PIERRO, Alvaro 63DE PRAETER, Johan 184DE QUEIROZ, Ricardo 96, 138DE VLEESCHOUWER, Christophe
161DE WITH, Peter H . N . 175DE, Tiago CARVALHO 68DEBAYLE, Johan 202DÉFORGES, Olivier 126DEGRAUX, Kévin 179DEL BLANCO ADÁN, Carlos
Roberto 111DELBOS, Alain 150DELBRACIO, Mauricio 138DELEFORGE, Antoine 68DELON, Julie 98DELP, Edward J . 83, 133DEMISSE, Girum 91DEN SDEKKER, Arnold Jan 63,
118DENG, Jeremiah 193DENG, Lei 114DENG, Lin 179DENG, Rui 159DENG, Xiaoming 200DENG, Xiaona 194DENG, Xiaowei 98, 185DENG, Xing 121DENIS, Loic 98DENIS, Valérie 61DENMAN, Hugh 79DENMAN, Simon 105DERICHE, Mohamed 70, 75DESROSIERS, Christian 112, 155,
156, 168, 176, 189DESVIGNES, Michel 135, 167,
168DEV, Soumyabrata 75, 86DHOME, Yoann 73DHUNGEL, Neeraj 95, 169, 203DI, Huijun 122DI, Jia 91DI, Wei 175DIANAT, Sohail 98DIAS, Zanoni 130DÍAZ, César 92DICKERSON, Andrew 165DING, Jianrui 52, 136DING, Xinghao 102DING, Yuchun 97
DINH, Khanh 82DINH, Nghia 197DOERMANN, David 144DOËRR, Gwenaël 77, 161, 181DOERSCHUK, Peter 106, 116,
128, 129, 147DOGAN, Emre 141DOGHRAJI, Salma 48DOMENGER, Jean-Philippe 130DONG, Jing 76DONG, Linhao 50DONG, Qiulei 58DONG, Shengfu 54DONG, Xueyan 191DONG, Yanchao 68DONIAS, Marc 48DONNÉ, Simon 128DOURADO, Antonio 113DOUTSI, Effrosyni 108DRAELOS, Mark 111DRAGOTTI, Pier Luigi 151DREW, Mark S . 99DROUARD, Vincent 68DRUMMY, Lawrence 63DU, Dandan 71DU, Jia 60, 70, 155DU, Longshan 109DUAN, Fuqing 200DUAN, Jinming 97, 106DUAN, Ling-Yu 83, 134DUAN, Xiaodong 102, 121DUAN, Yueqi 114, 180DUAN, Zhemin 109DUANMU, Fanyi 109DUCANU, Dan R . 74DUCHIN, Yuval 203DUFAUX, Frédéric 124DUGELAY, Jean-Luc 65, 100,
112, 124DUONG, Luc 168DUSCH, Elodie 174DUVA, Corina V . 74DUVAL, Laurent 75DWYER, Amy 192DYRBY, Tim 136DYSKIN, Arcady 197
EEBRAHIMI, Touradj 77, 94, 107,
178EDERRA, Cristina 118EGILMEZ, Hilmi E . 78EHMANN, Jana 60, 107, 108, 109EICHEL, Justin 167EICHENSEER, Andrea 89, 135EISERT, Peter 85EKLUND, Lauri 81EL SADDIK, Abdulmotaleb 202EL-BAZ, Ayman 154, 168, 192,
203EL-SABAN, Motaz 181, 198
ELDEKEN, Alaa 53ELGAMMAL, Ahmed 172ELHOSEINY, Mohammed 172ELLIETHY, Ahmed 88ELNAKIB, Ahmed 154, 168ELREFAI, Rahaf 192ELTANTAWY, Agwad 139EMMANUEL, Sabu 162ENGAN, Kjersti 201, 202ERCAN, Ali Özer 140ERDEM, A . Tanju 140EREN, Gönen 141ERFANIAN EBADI, Salehe 195ESCOBEDO CARDENAS, Edwin 89ETIEMBLE, Daniel 123EVANGELIDIS, Georgios 68EVANS, Alun 95EVANS, Brian 146EVERTS, Ivo 124
FFABLET, Ronan 73, 74, 185, 186FACCIOLO, Gabriele 149fa*gOT-BOUQUET, Loïc 73fa*gRET, D . 168FAN, Guoliang 67, 103, 120FAN, Huijie 153FAN, Jiayuan 77FAN, Tao 53FAN, Wentao 60FAN, Xiaopeng 58, 82FAN, Xin 57FAN, Yabo 121FAN, Yu 162FANG, Wei 163FANG, Xiaozhao 88FANG, Yuming 144, 193FANJIANG, Xu 198FARADJALLAH, Mousa 184FARAJI, Mehdi 191FARIA, Sérgio 108FARID, Muhammad Shahid 163FARINELLA, Giovanni M . 182FARRELL, Joyce 112FAZLALI, Hamidreza 151FENG, Dagan 136, 150FENG, Guocan 89FENG, Hao 121FENG, Litong 137FENG, Qingxiang 120FENG, Wei 86FENG, Xuetao 121, 142FENG, Zenhua 163FENG, Zhen-Hua 139, 196FERECATU, Marin 124, 197FERNANDEZ ARGUEDAS, Virginia
94FERNANDEZ-MALOIGNE, Christine
62, 162FERNÁNDEZ-MARQUÉS, Javier
118
220 | ICIP 2015 – Index of Authors and Session Chairs
FERNANDO, Anil 54FERON, Cyrielle 95FERTIL, Bernard 202FESSLER, Jeffrey 116, 170FIEGUTH, Paul 48, 131, 172,
180, 195FILLATRE, Lionel 108FISHER III, John 189FLIERL, Markus 86, 120FLUSSER, Jan 80f*ckES, Clinton 105, 139, 174FORD, Nancy 64FOROOSH, Hassan 50, 190FORSTNER, Andreas 129FORTIER, Paul 47, 100, 154FOUAD, Mohamed 53FOURNIER, Jérôme 174FOWLER, James 111, 112FRACASTORO, Giulia 77, 78FRANCHE, Jean-François 126FRANCIS, K . J . 63FRECON, Jordan 61FREIFELD, Oren 189FRIGO, Oriel 98FROSSARD, Pascal 78, 93, 113,
200FU, Chang-Hong 127FU, Haiyan 102, 122, 188FU, Hong 159FU, Keren 51, 84FU, Kun 198FU, Lianrui 122FU, Xiaowei 52FU, Zhihui 126FUJII, Toshiaki 113, 148FUJIYOSHI, Hironobu 90, 172FURCH, Johannes 85FURNARI, Antonino 182FURON, Teddy 61FURTON, John 165
GGABBOUJ, Moncef 51, 127GABR, Refaat 81GADERMAYR, Michael 173GADGIL, Neeraj 83GAO, Difei 72GAO, Jin 84GAO, Lei 203GAO, Longfei 54GAO, Mingfei 125GAO, Wen 54, 83, 97, 117, 194GAO, Xinbo 77GAO, Xinwei 82, 117GAO, Yang 71GAO, Yongsheng 57, 132GAO, Yuan 109GAO, Yueming 176GARALI, Imène 150GARBE, Christoph S . 48, 180GARCÍA SANTOS, Narciso 111
GARCIA, Diogo 96, 138GARCÍA, Narciso 92, 111GARG, Saurabh 118GARNIER, Christelle 72GAUDET-BLAVIGNAC, Christophe
146, 169GAUDY, Caroline 202GAULMIN, Julien 108GAVRILOVA, Marina 195GAWISH, Ahmed 195GE, Chenjie 84GE, Fengxiang 185GE, Shiming 94GE, Song 67GE, Ting 140GE, Zongyuan 193, 194GEELEN, Bert 179GEIGER, Davi 48, 79GELB, Dan 90, 158GEMIGNANI, Giorgio 105GENG, Shijie 189GENG, Yufeng 93GENTET, Enguerrand 111GÉRAUD, Thierry 204GERMAIN, Christian 65GEROGIANNIS, Demetrios 107GEUDER, Walther 107GEVERS, Theo 124, 195GHADESI, Amin 113GHADIYARAM, Deepti 62GHASEMI, Alireza 113, 133GHASSABI, Zeinab 196GHEZZI, C . 168GHORPADE, Vijaya Kumar 153,
164GHOSH, Hiranmay 131, 184GIBERT, Xavier 123, 147GIBSON, David 103GIBSON, Jerry 180GILBOA, Guy 49, 98GILLES, Antonin 114GILLIAM, Christopher 88, 119GIMEL'FARB, Georgy 154GIOIA, Patrick 114GIORDANO, Daniela 120GIRARD, Catherine 135GIRÓ-I-NIETO, Xavier 140, 173GIROD, Bernd 51GLEICH, Dusan 199GOECKE, Roland 157GOH, Hanlin 53GOLESTANEH, S . Alireza 145GONG, Chen 51GONG, Lujin 121GONG, Minglun 98GONG, Shaogang 101GONG, Wenyong 98GONG, Yanchao 165GONG, Yihong 151GONG, Yongchao 123GONG, Yunye 106
GONZALEZ-CASTRO, Victor 202GONZALEZ-DIAZ, Ivan 148GOOSSENS, Bart 128, 149GOPALAKRISHNAN, Viswanath
123GOTCHEV, Atanas 160, 179, 180GOTO, Hideaki 127, 128GOUIFFÈS, Michèle 57GRANGER, Eric 73, 193GRANGETTO, Marco 78, 163GREENWELL, Connor 171GRENIER, Thomas 204GROB, Jean-Jacques 202GROMPONE VON GIOI, Rafael
186GROSS, Markus 181GRUNDHÖFER, Anselm 76GU, Dongbing 191GU, Irene Yu-Hua 51, 175, 176GU, Kaiyu 183GU, Ke 164GU, Ying 60, 70, 155GU, Yun 83, 84, 176, 189GUAN, Ling 203GUAN, Yu 161GUARDA, André 108GUDIVADA, Sravan 58GUEDJ, Eric 150GUERRA ONES, Valia 195GUEYE, Limamou 201GUEZIRI, Houssem-Eddine 80GUI, Liangyan 80GUILLEMOT, Christine 175, 185,
200GUILLOTEL, Philippe 175GULERYUZ, Onur 53, 176, 177GUNAY, Osman 172GUNDOGDU, Erhan 83GUNGOR, Alper 116GUNTHER, Jacob 153, 164GUO, Cindy Xiaopeng 58GUO, Haiyun 134GUO, Jing-ming 76GUO, Jun 56, 86GUO, Rui 68GUO, Yandong 145GUO, Yanqing 86, 172GUO, Zhenhua 114GUO, Zhili 145GUO, Zongming 93, 136, 151GUPTA, Krati 137GUPTA, Phalguni 50GUPTA, Vibha 137GÜRBÜZ, Yeti Ziya 181GUREL, Ogan 166GUTHIER, Benjamin 202GUVEN, H . Emre 116
HHA, Jeongmok 153HADDAD, Zehira 128
ICIP 2015 – Index of Authors and Session Chairs | 221
HADID, Abdenour 137HADJERCI, Oussama 150HAFIANE, Adel 150HAGAN, Martin 178HAMIDOUCHE, Wassim 184HAN, Dongyoon 92HAN, Jae-joon 121, 142HAN, Jingning 169HAN, Peng 175HAN, Qinglong 126HAN, Sangchun 114HAN, Tony X . 125, 127HAN, Xian-Hua 168HANAI, Yuki 119HANHART, Philippe 107HANNUKSELA, Miska Matias 110,
127HAO, Aimin 132HARA, Kosuke 55HARAKAWA, Ryosuke 87HAREL, Noam 203HARIYONO, Joko 104HARTLEY, Richard 160HASEYAMA, Miki 87, 93, 201HASHEMI, Jordan 158HASSAN, Ghulam Mubashar 197HATI, Avik 52HAVLICEK, Joseph 85HAYASHI, Yusuke 185HE, Da-Ke 176HE, Jun 185HE, Kun 95HE, Xiangjian 66HE, Yun 107HE, Zhihai 125, 127HEIKKILÄ, Janne 81, 171HEISELE, Bernd 172HELLIER, Pierre 98HELM, Emma 49HELOU, Elias 63HELWANI, Karim 113HENAFF, Gilles 174HENRY, Morgane 137HEO, Jingu 69HERBIN, Stephane 50HERO, Alfred 187HERRERA CONEJERO, José Luis
111HILSMANN, Anna 85HILTON, Adrian 96HIRAKAWA, Keigo 138, 151, 170,
179, 204HITTAWE, Mohamad Mazen 66HOANG, Ngan LE T . 168HOEDLMOSER, Michael 113, 114HOFBAUER, Heinz 185HONG, Hui-Xin 136HONG, Tao 169HONG, Yan 124HORAUD, Radu 68HOROWITZ, Mark 81
HOSHEN, Yedid 140HOSPEDALES, Timothy 101HOSSEINI-ASL, Ehsan 203HOSSEINI, Mahdi S . 82HOU, Cheng-an 142HOU, Guangqi 111HOU, Ming 119HSIAO, Yu Zhe 56HSU, Chiou-Ting 171HSU, Gee-Sern 92HSU, Tsu-Ming Harry 142HU, Han 180HU, Nan 55HU, Ping 112HU, Ruimin 175, 192HU, Shiqiang 192HU, Weiming 84, 121HU, Zhencheng 68HU, Zhongwen 189HUA, Gang 173HUANG, Haoyu 176HUANG, Jiawen 120HUANG, Kaiqi 122, 162HUANG, Shao 122HUANG, Sheng 172HUANG, Shih-Chieh 92HUANG, Shiyao 91, 171HUANG, Shuai 176HUANG, Siyuan 114HUANG, Szu-Hao 129HUANG, Thomas 125HUANG, Tiejun 83, 135HUANG, Xiaotong 162HUANG, Xin 60HUANG, Xuehui 127HUANG, Yea-Shuan 121HUANG, Yongzhen 156HUANG, Yu-Wen 54HUANG, Yue 102HUANG, Zhangshuai 134HUANG, Zhitong 96HUBER-MOERK, Reinhold 130HUBER, Patrik 139, 163, 196HUET, Benoît 171HUI, Wu 198HUI, Zhang 198HUNG, Edson Mintsu 54, 79, 96HUNTER, Alan 93HUSSAIN, Md Akter 168HUTCHINSON, Charles 49HWANG, Soonmin 122HWANG, Wonjun 121HWANGBO, Myung 167
IIIDA, Makoto 191IJIRI, Yoshihisa 166IKEBE, Masayuki 99ILEA, Ioana 65IM, Sung-hoon 128IMAOKA, Hitoshi 69
IMRE, Evren 96INCE, Kutalmis Gokalp 189IONESCU, Bogdan 160IOSIF, Elias 158IOSIFIDIS, Alexandros 79, 125,
157ISHIBASHI, Haruki 171ISHIHARA, Kenta 201ISHIHARA, Tatsuya 67ISHWAR, Prakash 90, 104ISLAM, Mohammad 79ISMAIL, Marwa 154ISTRAIL, Sorin 116, 197ITIER, Vincent 77ITO, Koichi 75ITO, Satoshi 64IWAHORI, Yuji 119IYER, Ravishankar 167IZQUIERDO, Ebroul 54, 195
JJACHALSKY, Jörn 189JACOBS, Nathan 79, 171JACQUEMIN, Christian 57JACQUES, Laurent 161, 179JAFARI, Roozbeh 190JAGADEESH, Vignesh 175JAISWAL, Sunil Prasad 89, 180JAN PALENSTIJN, Willem 63JANG, Won-Dong 50JANG, Yunhun 122JANSSENS, Eline 63JARABO-AMORES, Pilar 198JAUREGUIZAR, Fernando 92JAZAR, Mustapha 91JEON, Byeongchan 153JEON, Byeungwoo 82JEON, Hae-Gon 128JEON, Jeayoung 153JEON, Jin 142JEONG, Hogyeong 116, 197JEONG, Hong 153JEONG, Seong-Gyun 49JERRIPOTHULA, Koteswar Rao
85JI, Dong Jin 152JI, Rongrong 134, 135JI, Xiaopeng 157JI, Yuefeng 96JI, Zhangjian 71JIA, Jie 179JIA, Sen 179JIA, Shaoyong 189JIA, Wenjing 51JIANG, Feng 82, 117JIANG, Gangyi 145JIANG, Jifeng 57JIANG, Tingting 58JIANG, Xiaolei 181JIANG, Xinghao 190JIANG, Yizi 169
222 | ICIP 2015 – Index of Authors and Session Chairs
JIANG, Yuning 171JIANGUO, Zhang 81JIAO, Jianbin 198JIAO, Licheng 182JIN-GUANG, Sun 91JIN, Guoxin 165, 177JIN, Jesse J . 101JIN, Pengchong 106, 134JIN, Xin 142JINDE, Liu 93JINFANG, Zhang 198JING, Min 58JING, Xiaoyuan 141JINJUN, Wang 89JO, Kang_Hyun 104JO, Sung Yong 153JOACHIMIAK, Michal 127JODOIN, Pierre-Marc 176JOHNSON, Matthew 91JONSCHER, Markus 135JOO, Kyungdon 186JOURLIN, Michel 138, 202JOVANOV, Ljubomir 149JU, Ran 52JUEFEI-XU, Felix 68, 89, 103, 196JUN, Zhou 74JUNEJO, Imran 105JUNG, Cheolkon 89, 112, 156,
178JUNG, Claudio Rosito 90, 191
KKAAKINEN, Mika 81KAANICHE, Mounir 127, 203KACHOURI, Rostom 143KAFIEH, Rahele 150KAIQI, Huang 93KAMBHAMETTU, Chandra 110,
116, 197KAMGAR-PARSI, Behrooz 59KAMGAR-PARSI, Behzad 59KAMGAR-PARSI, Kian 59KAMIZURU, Kohei 190KANG, Byungkon 166KANG, Le 144KANG, Sunghun 195KANG, Xiangui 130, 131KANG, Zhengjian 71KANJ, Ali 64KANNALA, Juho 81KAO, Yueying 162KAPPELER, Armin 135KARALI, Abubakrelsedik 181, 198KARAM, Christina 204KARAM, Lina J . 145, 164KARANDE, Shirish 200KARAOGLU, Sezer 124, 195KARIMI, Davood 64KARIMI, Nader 151, 186, 194KARL, Clem 116KARNYACZKI, Stefan 156
KARPUSHIN, Maxim 124KARTHIKEYAN, S . 87KASIRI BIDHENDI, Soudeh 174KASUGAI, Kunio 119KATO, Jien 156KATSAGGELOS, Aggelos K . 116,
135, 148KATSAMANIS, Athanasios 158KATZIR, Oren 98KAUP, André 65, 89, 135, 160KAWADE, Masato 166KAWAI, Norihiko 185KAWAKAMI, Rei 191KAWAKAMI, Yudai 190KAWASAKI, Atsushi 55KAWASAKI, Hiroshi 190KAZEMINIA, Salome 194KAZEMZADEH, Farnoud 99KEHTARNAVAZ, Nasser 76, 183,
190KHALAF, Aya 201KHALIFA, Fahmi 154, 168, 192KHALIL, Mahmoud 80KHAN, Khalil 196KHOMAMI ABADI, Mojtaba 160KHORSANDI, Rahman 86KIANI GALOOGAHI, Hamed 104KIAPOUR, M . Hadi 175KIEFFER, Michel 109KIJAK, Ewa 132KIKINIS, Ron 150KIKU, Daisuke 56KIM, Chang-Su 50, 96, 149KIM, Changil 181KIM, Chunghoon 196KIM, Dae Hoe 105, 152, 201KIM, Dae Woo 99KIM, Dae-Shik 122KIM, Daijin 158KIM, Deokho 168, 175KIM, Donghwan 170KIM, Hak Gu 178KIM, Haksub 145KIM, Hansung 96KIM, Hyoung Joong 121KIM, Hyung-Il 103KIM, Jaemyun 158KIM, Jaewoong 194KIM, Jihyun 85KIM, Jin-Hwan 149KIM, Jinyoung 203KIM, Jiwhan 92KIM, Jongyoo 197KIM, Joonsoo 133KIM, Jun-Seok 166KIM, Junghwan 145KIM, Junmo 92KIM, Ki-Jung 119KIM, Kyung-Rae 50KIM, Kyungah 175KIM, Minsik 168
KIM, Minwoo 175KIM, Munchurl 142, 185KIM, Namil 122, 186KIM, Sehoon 96KIM, Seong Dae 99, 180KIM, Seong Tae 152, 201KIM, Seungryong 187KIM, Suah 121KIM, Sujung 180KIM, Sungho 166KIM, Sunok 128KIM, Wonjun 142KIM, Yeonho 158KIM, Yoon Hyuk 119KIM, Youngbae 96KIM, Youngjung 85, 178KIMURA, Masatoshi 90KIMURA, Yuta 99KING, Michael 106KIRANYAZ, Serkan 51KITANI, Kris 67KITRUNGROTSAKUL, Titinunt 168KITTLER, Josef 139, 196KLICNAR, Lukas 96KODIKARA ARACHCHI, Hemantha
54KOEPPEL, Martin 70KOH, Yeong Jun 96KOKARAM, Anil 79KOLAGUNDA, Abhishek 110KOLODA, Jan 65KOMPATSIARIS, Ioannis 103, 147KOMULAINEN, Jukka 137KONDI, Lisimachos P . 107, 144KONDRAD, Lukasz 113KONG, Qingqun 58KONG, Seong G . 98KONG, Xiangwei 102, 122, 172,
188KONISHI, Yoshinori 166KONRAD, Janusz 46, 47, 89, 90,
104, 111KOPP, Timothy 169KORSHUNOV, Pavel 94KOSSAIFI, Jean 90KOTERA, Jan 97KOTTUR, Satwik 80KOUTAKI, Gou 56KOUTRAS, Petros 68, 158KOVANEN, Samu 143KOW, Victor Ter Shen 70KOZUBEK, Michal 118KRIEGER, Evan 73KRIM, Hamid 183, 192KROGER, Jim 88KRUTHIVENTI, Srinivas S . S . 140KUMAR, Himanshu 67KUMAR, Neeraj 64KUMAR, Raushan 123KUNDU, Debarati 146KUNDU, Sandipan 186
ICIP 2015 – Index of Authors and Session Chairs | 223
KUO, C .-C . Jay 166KURIBAYASHI, Minoru 76KUSE, Manohar 180KWAK, Nojun 64, 127KWAN, Chiman 179KWEON, In So 103, 122, 128, 186KYAN, Matthew 76KYBIC, Jan 80, 119, 203KYOCHI, Seisuke 97, 107
LLABEAU, Fabrice 61, 78, 95, 115,
133, 146, 163, 183, 198LABORELLI, Louis 108LACASSAGNE, Lionel 123, 125LAFRUIT, Gauthier 179LAGACHE, Thibault 119LAI, Polin 54LAI, Shang-Hong 129LAI, Zhihui 88LALANDE, Alain 201LALL, Brejesh 52LAMBERT, Lukás 119LAMERI, Silvia 130LANG, Yankun 142LAO, Songyang 131LAPORTE, Catherine 80LASANG, Pongsak 188LATTARI, Lucas 84LAUDE, Thorsten 55LE BARZ, Cedric 50LE CALLET, Patrick 49, 51, 52,
164, 185LE GUELVOUIT, Gaetan 61, 95LE, Mikael PENDU 177LE, T . Hoang Ngan 102LEACH, Michael 69LEAL, Helton Danilo Passos 161LEBLEBICI, Yusuf 161LECOMTE, Sébastien 184LEDOUX, Audrey 62LEE, Byeongju 57LEE, Changhoon 83LEE, Chul 59LEE, Chulwoo 96LEE, Donghoon 195LEE, Hyeogjin 127LEE, Hyun-Seung 59LEE, Ji-Young 59LEE, Jiann-Der 76LEE, Jun Haeng 166LEE, Kyoobin 166LEE, Kyu-Yul 179LEE, Minhaeng 117LEE, Sanghoon 50, 59, 145, 197LEE, Seung Ho 103LEE, Seungkyu 70, 119LEE, Sue Han 101LEE, Sukhan 194LEE, Teahyung 167LEE, Yee Hui 75, 86
LEE, Yonggeol 196LEFÈVRE, Sébastien 132LEFKIMMIATIS, Stamatios 203LEGAL AYALA, Horacio 152LEGRAND, Anthony 161LEI, Hang 142LEI, Shawmin 54LEI, Tong 74LELE, Cheng 89LEONARDI, Riccardo 77, 164,
195, 196LEONG, Khai Pang 187LERASLE, Frédéric 73LETOURNEL, Geoffrey 130LEZORAY, Olivier 51, 62, 78, 200LGUENSAT, Redouane 186LI, Bangyu 97LI, Baoxin 190LI, Bo 165LI, Brian 171LI, Chang-Tsun 123, 161LI, Changqing 148LI, Chao 73LI, Chaofeng 163LI, Chun-Guang 67LI, Dong 174, 177LI, Fan 62LI, Francis 99, 124, 166LI, Fu 71LI, Guiqin 167LI, Haisheng 49LI, Haopeng 120LI, He 133LI, Heng 187LI, Hongliang 146LI, Hongyang 192LI, Houqiang 83, 97, 110, 127,
177LI, Jiachang 169LI, Jianchao 173LI, ji*zhou 119LI, Junling 49LI, Junxia 66LI, Kai 91LI, Li 91, 93, 131, 187LI, Lianhua 180LI, Lin 117LI, Lingxiao 135LI, Lingyun 172LI, Liyuan 90LI, Ming 86, 102, 188LI, Minqi 196LI, Ning 104LI, Peihua 137, 194LI, Penglin 178LI, Qingquan 172, 189LI, Ruizhe 161LI, Runlin 141LI, Shao-Zi 134, 135, 176LI, Shuai 132LI, Shuangjiang 179
LI, Shunyao 177, 199LI, Shuzhen 52LI, Wei 143, 175, 178LI, Weifeng 120LI, Weihai 74LI, Weiming 178LI, Weiping 97LI, Wenbin 71LI, Wenjing 102LI, Xi 87LI, Xingyu 119LI, Xue 59LI, Yali 174LI, Yan 53LI, Yandong 142LI, Yang 50LI, Yanghao 136LI, Yi 86, 138, 144LI, Yijun 84LI, Yin 133LI, Ying 115, 165LI, Yixin 189LI, Yong 134LI, Yuelong 59LI, Yuenan 77LI, Yuming 137LI, Ze-Nian 70LI, Zhengguo 99, 204LI, Zhenghao 175LI, Zhi 166LI, Ziyi 104LI, Zongmin 141LIAN, Xiaocong 109LIAN, Yongjian 67LIANG, Bin 157LIANG, Jie 148, 149LIANG, Jiuzhen 102LIANG, Xuefeng 182LIANG, Yudong 151LIAO, Liang 175LIAO, Qingmin 61LIAO, Zhibin 120LIE, Wen-nung 127LIEN, Kuo-Chin 180LIM, Jae 177LIM, Jaemoon 149LIM, Joo Hwee 90LIN, Baowei 110LIN, Chuang 57LIN, Dazhen 135LIN, Fang-Ju 71LIN, Feng 187LIN, Hanhe 193LIN, I-Chen 190LIN, Jie 53, 83, 134LIN, Joe Yuchieh 166LIN, Qiuyan 131LIN, Shaopeng 182LIN, Weisi 164, 193LIN, Xianming 134LIN, Xiaodan 131
224 | ICIP 2015 – Index of Authors and Session Chairs
LIN, Yao-Chung 79LIN, Yuewei 141LING, Yonggen 170LINGRAND, Diane 52LIU, Baodi 59LIU, Bin 67LIU, Bozhi 56LIU, Chang 74LIU, Chengjun 183, 188LIU, Chin-Wei 127LIU, Dong 177LIU, Fei 111LIU, Guizhong 159LIU, Hai 75LIU, Haibo 192LIU, Hantao 143, 144LIU, Hong 69, 90, 152, 190LIU, Hongbin 54LIU, Hongmin 178LIU, Hsin-Hua 144, 195LIU, Jiang 137LIU, Jiaying 136, 151LIU, Jing 76, 85, 134LIU, Jingyu 156LIU, Junjie 109LIU, Kejia 67LIU, Kuan-Hsien 144, 195LIU, Li 93, 131LIU, Limei 74LIU, Lingzhi 99LIU, Mengyuan 152LIU, Miaoming 167LIU, Peng 58, 120LIU, Qingfeng 183, 188LIU, Qiong 160LIU, Risheng 57, 72LIU, Sanya 75LIU, Shan 54LIU, Shanshan 145LIU, Shigang 191LIU, Sidong 150LIU, Siqi 150LIU, Tingting 75LIU, Tong 129LIU, Tsung-Jung 144, 195LIU, Wang 129LIU, Wei 178LIU, Weiyang 114LIU, Wentao 163LIU, Xianming 57, 125LIU, Xiao 81LIU, Xiaoming 74LIU, Xin 181LIU, Xiuwen 122, 156LIU, Xuehui 141LIU, Yaqi 49LIU, Yazhou 74, 188LIU, Yiqun 126LIU, Yu 149LIU, Yun-Fu 76LIU, Yuncai 70, 157, 192
LIU, Zhenyu 109LIU, Zhihua 169, 178LIU, Zhiwen 187LIU, Zicheng 171LIU, Zikun 139LODHA, Sachin 200LOKKOJU, Satish 123LONCARIC, Sven 64LONG, Zhiling 75LOPEZ KRAHE, Jaime 128LOPEZ, Stephanie 52LOSSON, Olivier 62LOTUFO, Roberto A . 61, 131, 132LOVSTROM, Benny 144LU, Hanqing 85, 105, 134LU, Hao 141LU, Huchuan 49, 71LU, Jichuan 50LU, Ke 71, 85, 112, 128LU, Shijian 66, 174LU, Xiaohu 91, 187LU, Xiqun 125LU, Xiusheng 124LU, Ya 142LU, Yan-heng 127LU, Yao 121, 122, 140LU, Yue 143, 152LU, Zhenbo 97LU, Zongqing 61LUCAS, Luis 108LUCENTEFORTE, Maurizio 163LUO, Bin 115LUO, Jack 81, 82LUO, Junfeng 173LUO, Lei 73LUO, Limin 154LUO, Tiannan 129LUO, Wei 92LUO, Zhiming 176LUONG, Hiep 149LUU, Khoa 102, 137LV, Feng 122LV, Ke 50LV, Peng 191LV, Shiwen 121LV, Yaqi 145LYU, Siwei 193
MM .C, Padma 128M'HIRI, Faten 168MA, Chao 71MA, Chih-Hao 171MA, Gengyu 178MA, Hongbing 183MA, Huadong 102MA, Huimin 84MA, Jinwen 173MA, Kai-Kuang 49MA, Kaidi 116, 197MA, Kede 144, 163, 186
MA, Liangping 92, 159MA, Liqian 190MA, Puhao 122MA, Siwei 97, 135MA, Wei-Chiu 67MA, Yike 182MA, Zhan 109MACAIRE, Ludovic 62MACCHIAVELLO, Bruno 54, 79MACHADO, Rubens 61, 132MACKIN, Alex 145MACNISH, Cara 197MADOOEI, Ali 99MAEDA, Keisuke 93MAGLI, Enrico 77, 78MAHAPATRA, Ansuman 53MAHDIAN, Babak 161MAHFOODH, Abo-Talib 135MAHMUDI, Tahereh 150MAICH, Henrique 108MAITRE, Emmanuel 137MAJHI, Banshidhar 53MAJUMDAR, Angshul 64, 82MAKRIS, Pascal 150MALEKI, Arian 148MAN, Hong 59MANCEAU, Aldric 57MANDAL, Bappaditya 90MANJUNATH, B .S . 65, 66, 87MANOHARA, Megha 166MANSOUR, Hassan 103MAO, Li 163MAO, Wentao 123MAO, Xiao-Jiao 104MARAGOS, Petros 68, 78, 158MARAPAREDDY, Ramakalavathi
199MARCENARO, Lucio 139, 193MARCIA, Roummel 148MARCON, Marco 171MARCOU, Quentin 119MARKATOPOULOU, Foteini 53MARKOPOULOS, Panos 186MARQUÉS, Ferran 173MARS, David 120MARTIN-DE-NICOLAS, Jaime 198MARTIN, David 174MARTÍNEZ-BARBERÁ, Humberto
111MARTINEZ-CAMARENA, Marc 68MARTÍNEZ-MARTÍNEZ, Francisco
119MARUKI, Daiki 75MASKA, Martin 118MATA-MOYA, David 198MATEI, Basarab 203MATHEW, Reji 176MATSUI, Yusuke 122MATSUNAGA, Nobutomo 56MATSUOKA, Ryo 56, 171MAUGEY, Thomas 108, 200
ICIP 2015 – Index of Authors and Session Chairs | 225
MAURO, Massimo 196MAVRIDAKI, Eftichia 162MAXUDOV, Nekruzjon 140MAZET, Vincent 199MAZO, Loïc 159MCCOOL, Christopher 193, 194MCGINNITY, Martin 58MCGUFFIN, Michael J . 80MCGUINNESS, Kevin 173MEDDEB, Marwa 109MEDINA ARMAS, Christian 143MEHRI DEHNAVI, Alireza 136MEHRI, Alireza 136, 150MEI, Jiang 81MEI, Xiang 91, 171MEIGNEN, Sylvain 203MELLONI, Ambra 130MEMMESHEIMER, Raphael 55MENDES, Caroline 131MENG, Fang 49MENG, Jingjing 51MENG, Jingyu 154MENG, Lingfei 182MENON, Vineetha 112MENOTTI, David 73MERGET, Daniel 87, 145MERHOF, Dorit 143MERIAUDEAU, Fabrice 66METZLER, Chris 95METZLER, Christopher 148MEUNIER, Jean 69MEZARIS, Vasileios 53, 162MHIRI, Rawia 55MIAO, Jie 176MIAO, Jun 81, 104MIAO, Zhenjiang 105MIGUEL, Marcelo 163MILANI, Simone 140, 142MINAEE, Shervin 126MINEMATSU, Tsubasa 140MING, Anlong 125MIQUELES, Eduardo 63MIR, Junaid 54MIRMAHBOUB, Behzad 194MIRONICA, Ionut 160MISHRA, Akshaya 62, 159, 166,
167MITCHELL, Kenny 181MIYAGI, Yusuke 148MIYATA, Takamichi 97, 98MOESLUND, Thomas B . 191MOHAMMADZADEH, Ali 196MOKHAYYERI, Faniya 193MOKRAOUI, Anissa 127MOLINA, Rafael 148MONGA, Vishal 59MONNO, Yusuke 56MONTAZZOLLI SILVA, Sergio 158MONTENEGRO, Anselmo 84MOON, Todd 153MORADI, Saber 166
MORALES, Sandra 202MORAN BURGOS, Francisco 55MORÉ, Luis G . 152MOREAUD, Maxime 60MOREL, Jean-Michel 138, 149MORÈRE, Olivier 53MORERIO, Pietro 139MORGAN, Lucy 136MORGAN, Stuart 174MORI, Greg 193MORIN, André 65, 100, 112MORIN, Luce 114MORITA, Ryosuke 132MOSCHINI, Ugo 93MOSHE, Yair 145MOSTAPHA, Mahmoud 154, 203MOTTA, Danilo 200MOULIN, Pierre 88, 130MOUMENE, Mohammed Elamine
195MOURA, Jose 80MOURYA, Rahul 98, 115MOUSAVI, Hossein 104MOUSSET, Stéphane 55MRAK, Marta 164MU, Jian 71MU, Nan 52MUDDAMSETTY, Satya 66MUELLER, Karsten 70MUKHERJEE, Debargha 135MUKHERJEE, Dipti Prasad 157MUKHERJEE, Prerana 52MUKHERJEE, Sankha Subhra
69, 158MUÑOZ-BARRUTIA, Arrate 118MUNTEANU, Adrian 113, 177MURE, Simon 204MURILLO MONTES DE OCA,
Ambar 184, 197MURINO, Vittorio 94, 104MV, Rohith 197MWANGI, Gerald 48, 180
NNABI, Moin 104NACCARI, Matteo 164NAEMURA, Takeshi 191NAGAHARA, Hajime 140NAJARIAN, Kayvan 98, 151NAJMAN, Laurent 204NALLAMOTHU, Brahmajee 151NAM IK, Cho 59NAM, Dongkyung 69NANJUNDA IYER, Kiran 123NANJUNDASWAMY, Tejaswi 177,
199NARANJO, Valery 202NASCIMENTO, Jacinto 94, 115NASE, Radu T . 74NASREDDINE, Kamal 91NASRINPOUR, Hamid 146
NASROLLAHI, Kamal 191NATARAJ, Lakshmanan 66NAVA, Rodrigo 203NAVAB, Nassir 187NAVARRO, Laurent 202NEES, Matthias 81NEFF, Ralph 159NEJATI, Mansour 98NERI, Alessandro 182NETTO, Sergio 192NEUHOFF, David 66, 131, 139NEWSON, Alasdair 106NEWSTADT, Gregory 187NG, Carol 187NGAN, King Ngi 109, 162NGO, Tran-thanh 199NGO, Tuan Anh 170NGUYEN CANH, Thuong 82NGUYEN, Chuong 85NGUYEN, Kien 139NGUYEN, Tuan 122NI, Ding 183NI, Jia 125NICHOLSON, Bryce 140NICOLAI, Bart 63NICOLAS, Henri 192, 193NIEN, Hung 116NIKOLAIDIS, Nikolaos 95, 125NIKOU, Christophoros 64, 107NING, Guanghan 127NITZKEN, Matt 154NONATO, Luis Gustavo 200NOUMEIR, Rita 146NOURI, Anass 51NOURINE, Rachid 195NOVOZÁMSKÝ, Adam 80, 161NOYEL, Guillaume 138NTALIANIS, Klimis 87
OO'CONNOR, E, Noel . 173ODATE, Ryosuke 128OGAWA, Takahiro 87, 93, 201OGUZ, Oguzhan 118, 119, 172OH, Changjae 85, 178OH, Heeseok 197OH, Tae-Hyun 186OHASHI, Kazuki 113OKAJIMA, Hiroshi 56OKTAY, Ayse 201OKUDA, Masahiro 56, 107, 171OKUTOMI, Masatoshi 56, 149,
186OLIVO-MARIN, Jean-Christophe
119OLSEN, Søren 174OLSSON, Roger 182ONG, Ee Ping 137ONO, Satoshi 190ONO, Shunsuke 97, 169ONUKI, Masaki 169
226 | ICIP 2015 – Index of Authors and Session Chairs
ORAMAS M ., José 67, 68ORTEGA, Antonio 78ORTIZ-DE-SOLÓRZANO, Carlos
118OSTERMANN, Jörn 55, 126, 189OSTERMANN, Ralf 133OTTERSTEN, Bjorn 91OTTEVAERE, Heidi 113OUERTANI, Fatma 202OUSEPH, Rosemary 192OVEISI, Farid 81, 82OVEISI, Shahrzad 81, 82OZAN, Ezgi Can 51
PPABST, Simon 96PADOS, Dimitris 186PAENG, Kyunghyung 180PAGET, Mathias 169PAGLIARI, Carla 108, 163PAIM, Guilherme 108PAL, Dipan 68PALAZZO, Simone 120PAMBRUN, Jean-Francois 146PAN, Chunhong 84, 97, 123,
139, 191PAN, Hong 174PAN, Lili 72PAN, Xu 59PAN, Zhenkuan 97PANAHPOUR TEHERANI, Mehrdad
113PANAHPOUR TEHRANI, Mehrdad
113, 148PANDA, Rameswar 157PANDREMMENOU, Katerina 144PANG, Fengqian 187PANG, Jiahao 170PANG, Meng 57PANG, Qingyu 73PANTIC, Maja 90PAPACHRISTOU, Konstantinos 53PAPADIMITRIOU, Katerina 64PAPADOPOULOS, Miltiadis Alexios
165PAPPAS, Odysseas 70PAPPAS, Thrasyvoulos N . 36, 37,
116, 200PAPUSHOY, Alex 79PARIS, Sylvain 116PARK, Frederick 95PARK, Fredrick 191PARK, Jong-il 55PARK, Jungsik 55PARK, Paul K . J . 166PARK, Sungheon 64PARK, Taewoong 85PARRA, Albert 133PASHA, Saleem 128PASQUAL, Ajith 161PATEL, Sidhdharthkumar 76
PATEL, Vishal M . 75, 87, 88, 111, 123, 129
PATIL, Pranita 178PATRAS, Ioannis 53PATRAUCEAN, Viorica 186PATRONA, Foteini 125PAUL, Padma Polash 195PAULUS, Dietrich 55PEDEBOY, Jean-Pierre 77PEDERSEN, Marius 62PEI, Soo-Chang 56, 144, 195PEIXOTO, Eduardo 54, 79PELEG, Nimrod 145PELEG, Shmuel 125, 140PENG, Anjie 131PENG, Kuan-Chuan 194PENG, Peipei 133PENG, Qunnie 98PENG, Tingying 187PENG, Xiaojiang 156PENG, Xiyuan 129PENG, Yan-Tsung 99PÉREZ RUA, Juan Manuel 69PEREZ, Marcelo 163PÉREZ, Patrick 69PERINA, Alessandro 94, 104PERRIER, Valerie 137PERRIN, Anne-Flore 126PESCATORE, Jérémie 135PESQUET-POPESCU, Béatrice 109PESQUET, Jean-Christophe 64,
75, 108PETERS, Ethan 161PETTERSSON, Martin 107PETUTSCHNIGG, Alexander 88PHAM, Luong VAN 184PHAM, Mai Quyen 75PHAN, Minh Son 159PHAN, Raphael C .-W . 184PHILIPPE, Pierrick 126PHILIPS, Wilfried 128, 149PIAO, Yongri 60PICCINI, Davide 146, 169PIECK, Martin A . R . 175PIERAZZO, Nicola 149PIETIKAINEN, Matti 131PINHEIRO, Miguel Amável 80PINTO-ROA, Diego 152PIOTTO, Nicola 55, 113PIRAMUTHU, Robinson 175PITAS, Ioannis 53, 79, 95, 125,
157PLATANIOTIS, Konstantinos N .
82, 119PO, Lai-man 137POLOK, Lukas 96POPOVIC, Vladan 161PORTEJOIE, Pierre 204PORTER, Richard 82PORTILLA, Javier 70PORTO, Marcelo 108
POTAMIANOS, Alexandros 158POTTER, Lee 63POUJOL, J . 168POULARAKIS, Stergios 147POURIAN, Niloufar 87POURREZA-SHAHRI, Reza 76POWERS, Michael A . 129PRASAD, Saurabh 112PRATES, Raphael 94PRECIOSO, Frederic 52PRETORIUS, Hendrik 106PTUCHA, Raymond 67PUECH, William 76, 77, 184PUJOL, Sonia 150PURWAR, Anirudh 123PUSTELNIK, Nelly 61PUTHENPUTHUSSERY, Ajit 183,
188
QQI, Chun 64QI, Feng 58QI, Hairong 68, 84, 179, 199QI, Lin 203QI, Wenfa 131QI, Wenyuan 106QI, Xianbiao 172QIAO, Liyan 129QIAO, Tong 162QIAO, Yu 189QIN, Boyang 96QIN, Hong 132QING, Chunmei 69QING, Laiyun 81, 104QINGHUA, Hu 133QIQI, Hou 89QIU, Guoping 56QIU, Qiang 111, 158QU, Hongjia 60QU, Xiaochao 121QU, Xiwen 128QUANSEN, Sun 204
RRABBANI, Hossein 136, 150RABBANI, Majid 64RADHA, Hayder 135, 151RADHAKRISHNAN, Venkatesh
Babu 52, 140RAHIM, Mehdi 202RAHIMI, Amir M . 66RAIS, Martin 149RAJAGOPAL, Anoop 190RAJAGOPALAN, A .N . 91RAJALAKSHMI, P 63RAJAN, Deepu 66RAKHSHANFAR, Meisam 144RAMADASAN, Datta 55RAMAKRISHNAN, Kalpathi 190RAMAMOHANARAO, Kotagiri 168
ICIP 2015 – Index of Authors and Session Chairs | 227
RAMOS-LLORDÉN, Gabriel 63, 118
RAMPAL, Karan 69RAMPONI, Giovanni 94RAN, Lingyan 173RAN, Yang 175RATNAYAKE, Kumara 67RÄTSCH, Matthias 139RAUTERBERG, Matthias 139RAVI, Hareesh 162RAVISHANKAR, Saiprasad 196REDONDI, Alessandro 138REGAZZONI, Carlo 139, 193REHG, James M . 105REHM, Patrick 54REINHART, Gunther 129REITER, Daniel 81REMAGNINO, Paolo 101REN, Haoyu 70REN, Jinchang 101REN, Tongwei 52RESO, Matthias 189RETRAINT, Florent 162REVEL, Arnaud 52REY-MAESTRE, Nerea 198REY-OTERO, Ives 138REYNAUD, Roger 167REZAEE KAVIANI, Hoda 85REZNIK, Yuriy 159RHEIN, Stephen 110RIAHI, Dorra 84RIBEIRO, Thiago 131RICCIO, Daniele 199RICH, Adam 63RICHTER, Thomas 160RIGOLL, Gerhard 87, 145RIOU, L . 168RISTER, Blaine 81RITHWIK, Kollipara 149RITTNER, Letícia 61, 132RO, Won Woo 168, 175RO, Yong Man 103, 105, 152,
178, 201ROBERTSON, Neil 69, 106, 156,
158ROBLES-KELLY, Antonio 76ROCHA, Anderson 130RODGER, Iain 106RODRIGUES, Nuno 108RODRIGUEZ LUPARELLO, Raoul
64RODRIGUEZ, Antonio L . 111RODRIGUEZ, Paul 182ROE, Paul 191ROMASCANO, David 136ROMERO, Eduardo 187RONG, Jiangpeng 91, 171ROOSTA, Iman 186ROSE, Kenneth 48, 101, 153, 155,
177, 199ROSENHAHN, Bodo 189
ROSITO JUNG, Claudio 158ROSTAMZADEH, Negar 160ROTA, Paolo 105ROTHE, Rasmus 96, 115ROTUREAU, Brice 119ROUMY, Aline 108ROUSSEAU, Francois 185ROUSSEAU, Sylvain 71, 72ROY-CHOWDHURY, Amit 53, 157ROY, Sébastien 69ROZENHOLC, Yves 200ROZZA, Alessandro 105RUAN, Xiang 49RUBEN, Nathan 153, 164RUEDA, Hoover 179RUUTH, Steven 174RYU, Hyunsurk 166RYU, Seungchul 85
SSA, Pankaj 53SAAD, Elhusain 138SAAFIN, Wael 148SABATER, Neus 98SABLATNIG, Robert 185SAEED, Anwar 158SAFAR, Simon 173SAGHAFI, Behrouz 104SAHBI, Hichem 172SAIC, Stansilav 161SAID, Amir 78SAID, Salem 197SAINZ DE CEA, Maria V . 194SAITO, Hideo 55SAITO, Toyohiro 113SAJID, Hasan 106SAKAI, Shuji 75SAKAI, Shun 122SAKURAI, Kazuyuki 69SALAMA, Gouda 53SALVADOR, Amaia 140SALZENSTEIN, Fabien 73SAMAVI, Shadrokh 98, 151, 186,
194SAMUELSSON, Jonatan 107SANCHEZ DE LA FUENTE, Yago
92SANCHEZ, Victor 108SANCHEZ, Yago 92SANDERSON, Conrad 193, 194SANFOURCHE, Martial 50SANGI, Mehrdad 58SANKARANARAYANAN, Aswin
C . 129SANKARANARAYANAN, Swami
111SANTARCANGELO, Joseph 50SANTIAGO, Diêgo 139SANTOS, Andrey Bicalho 73SANTOS, João 108SAO, Anil 137
SAPIRO, Guillermo 106, 111, 158, 203
SAPONARO, Philip 110SAPPA, Angel 179SARRAFZADEH, Omid 136SARTI, Augusto 171SATHYANARAYANA, Suchitra 148SATHYANARAYANA, Supriya 148SATO, Tomokazu 185SATO, Yoichi 85SATZODA, Ravi Kumar 148SAUCAN, Emil 49SAULQUIN, Bertrand 74SAUSSARD, Romain 167SAVAKIS, Andreas 91, 161SAVVIDES, Marios 68, 89, 102,
103, 137, 196SAXENA, Ankur 165, 177SCHAATHUN, Hans Georg 76SCHARFENBERGER, Christian
62, 166SCHAUERTE, Boris 62SCHELKENS, Peter 113, 177,
190, 196SCHIERL, Thomas 92SCHMITTER, Daniel 146, 169SCHNURRER, Wolfgang 160SCHOLEFIELD, Adam 113, 133SCHRAML, Rudolf 88SCHRETTER, Colas 177SCHROEDER, Damien 54SCHUTTER, Kyle 116, 197SCHWARTZ, Arik 145SCHWARTZ, William Robson
73, 94SCHWARZ, Gottfried 199SCHWARZ, Sebastian 164SCHWARZE, Tobias 181SCLAROFF, Stan 83SCOTNEY, Bryan 58SEBE, Nicu 105, 160SEDLAR, Jiri 80SEELAMANTULA, Chandra Sekhar
149SEETHARAMAN, Gunasekaran 91SEGALL, Andrew 135SEGERS, Hilde 63SEIB, Viktor 55SEIDL, Markus 110SEILER, Jürgen 65, 89, 135, 160SEO, Byung-Kuk 55SEO, Ja-Won 99, 180SEO, Jeong-Jik 105SETHI, Amit 64SETHI, Ricky 105SHABBIR, Aqsa 86SHAFIEE, Mohammad Javad 99,
166, 172SHAH, Archit 52SHAHID, Muhammad 144SHAN, Shiguang 173
228 | ICIP 2015 – Index of Authors and Session Chairs
SHANBEHZADEH, Jamshid 191, 196
SHANG, Xiwu 53SHAO, Feng 145SHAO, Haoyang 52SHAO, Tong 177SHAPOVALOVA, Nataliya 193SHARMA, Gaurav 88, 179SHARMA, Monika 131, 184SHATKAY, Hagit 116, 197SHEHATA, Mohamed 139, 192SHEIKH FARIDUL, Hasan 77SHEN, Bin 59SHEN, Linlin 88SHEN, Xukun 67SHEN, Yuxiang 98SHENG, Hao 73, 160SHENG, Victor S . 120, 140SHENOY, Renuka 153SHEOPURI, Anshul 165SHI, Jingang 64SHI, Limin 97SHI, Pengfei 51, 66, 83, 84, 176,
178, 189SHI, Qingxuan 122SHI, Wuzhen 117SHI, Xiaoshuang 114SHI, Yinghuan 71SHI, Yonggang 187SHIBATA, Takashi 186SHIH, Min-chi 153SHIMADA, Atsushi 140SHIN, Chang-Woo 166SHIRAI, Keiichiro 107, 132, 169SHIRANI, Shahram 85, 186SHOU, Zheng 192SI, Jianlou 67SIBALDO, Maria 68SICK, Volker 116SIDIBE, Desire 66SIDIKE, Paheding 73SIEGEL, Mel 74, 188SIJBERS, Jan 63, 106, 118SILVA, Eduardo 163SILVA, Luciano 129, 131SIM, Jae-Young 149, 179SIMMONS, Jeffrey 63, 187SIMOND, Florian 162SINGH, Karanhaar 102SINHA, Shashank 151SIRINUKULWATTANA, Tharatch
103SIU, Wan-Chi 70, 127SIVA, Parthipan 62, 166SIVASWAMY, Jayanthi 106SJÖBERG, Rickard 107SJÖSTRÖM, Mårten 182SKUPIN, Robert 92SLABAUGH, Greg 111SMOLIC, Aljoša 76, 126SNEDDON, Justin 96
SOARES, Neelkamal 61, 129SOHAIB, Ahmed 76SOHEL, Ferdous 142SOHN, Kwanghoon 85, 128, 178,
187SOHN, Sungryull 92SOLIMAN, Ahmed 154, 168, 192SOMANATH, Gowri 116, 197SON, Jongin 187SONG, Chao 106SONG, Chao-Bing 170SONG, Gihun 158SONG, Hwangjun 161SONG, Yang 136SONG, Yifan 133SORENSEN, Scott 110SORGI, Lorenzo 110, 133SORKINE-HORNUNG, Alexander
181SOROUSHMEHR, S .M .Reza 98,
151, 194SOUKUP, Daniel 130SOULARD, Raphael 62SOUSA, Davy Oliveira Barros 161SOUSA, Joao P . 142SOUZA, Roberto 61, 132SPAMPINATO, Concetto 120SPINOULAS, Leonidas 116SPRECHMANN, Pablo 106SREEHARI, Suhas 63SRIDHARAN, Sridha 105, 139,
174SRIVATSA, R .,Sai 52SROUBEK, Filip 80, 97ST-CHARLES, Pierre-Luc 67STEFANOSKI, Nikolce 76STEINBACH, Eckehard 54, 107STEPHEN, Julia M . 150STERGIOPULOS, Nikolaos 203STERNBERG, Gregory 159STEVEN VANCE, Steven 179STIEFELHAGEN, Rainer 62STOIAN, Andrei 124STOLC, Svorad 130SU, Chang 151SU, Fei 94, 133, 157SU, Po-Hsun 56SU, Song-Zhi 176SU, Xiaohong 74SU, Zhixun 72SUBEDAR, Mahesh 164SUBR, Kartic 181SUBRAMANIAN, Ramanathan 190SUH, Yunjae 166SUN, Bo 185SUN, Chao 114SUN, Gang 141SUN, Limin 94SUN, Meijun 101SUN, Ming-Ting 171SUN, Quansen 74, 188
SUN, Tanfeng 190SUN, Weichen 94SUN, Weidong 73, 117SUN, Xiaoshuai 132, 181SUN, Xiaoxia 141SUN, Xin 124SUN, Xun 169SUN, Yu-Chen 54SUN, Zhenan 111SUNG, Minyong 168SUO, Jidong 74SUOMINEN, Olli 160SUR, Frédéric 97SÜSSTRUNK, Sabine 162SUWA, Masaki 166SUZUKI, Taizo 202SVEC, Jan G . 80SYED, Tabish 106SZE, Vivienne 107
TTA, Vinh-Thong 130TAALIMI, Ali 84TADIC, Vladislav 82TAGLIASACCHI, Marco 130, 138TAHA, Ahmed 125TAHBOUB, Khalid 83TAI, Yen-chou 127TAI, Yu-Wing 117TAJINE, Mohamed 159TAKAGI, Hironobu 67TAKAHASHI, Keita 113, 148TAKETOMI, Takafumi 171TAKIGUCHI, Tetsuya 188TALAGALA, Dumidu S . 54TALATHI, Sachin 167TALBOT, Hugues 64TALEBI, Ardeshir 136TALENS-NOGUERA, Juan V . 143,
144TAM, Roger 118TAMAKI, Toru 110TAMBO, Asongu 153TAN, Kai 74TAN, Tieniu 76, 111TAN, Wai-Tian 165TAN, Yap-Peng 51TAN, Zhangyun 60TAN, Zheng-Hua 102, 121TANAKA, Masayuki 56, 149, 172,
186TANAKA, Yuichi 132, 168, 169TANDEO, Pierre 186TANG, Hao 152TANG, Lisa 118TANG, Sheng 50TANG, Xianglong 58, 120TANG, Yandong 153TANIGUCHI, Rin-ichiro 140TANISIK, Gokhan 83TAO, Dacheng 77
ICIP 2015 – Index of Authors and Session Chairs | 229
TAO, Dapeng 157TAO, Li 151TAO, Xiaoming 50TAO, Zhiqiang 49TARABALKA, Yuliya 49TAREL, Jean-Philippe 169TARIQ, Amara 50TARPINE, Ryan 116, 197TAUBIN, Gabriel 200TAUBMAN, David 89TAVARES, Luis 61TAY, Peter 58TEENINGA, Paul 93TEFAS, Anastasios 53, 79, 95,
125, 156, 157TEIXEIRA, Rene 158TEMEL, Dogancan 146TEOH, Eam Khwang 72TEPPER, Mariano 106TEREBES, Romulus 65TEW, Yiqi 184THAI, Thanh Hai 162THAMBIPILLAI, Srikanthan 148THANOU, Dorina 78THASKANI, Sandhya 200THIÉBAUT, Éric 98THIRAN, Jean-Philippe 50, 136THOMAZ, Lucas 192THOME, Nicolas 50, 174THOMPSON, Benjamin 58THOREAU, Dominique 175, 177TIAN, Dong 103TIAN, Jing 162TIAN, Lu 152, 180TIAN, Qi 83, 172TIAN, Tai-Peng 165TIAN, Xiao 156TIAN, Yingli 151TIAN, Yonghong 117TICKOO, Omesh 167TIEFENBACHER, Philipp 87, 145TIENIU, Tan 93TILLO, Tammam 126TIMOFTE, Radu 96, 115, 170TIWARI, Kamlesh 50TIZHOOSH, Hamid R . 148, 164TOLEDO, Ricardo 179TONI, Laura 93TORKI, Marwan 125TOROPOV, Evgeny 80TORTORICI, Claudio 102TOSIC, Ivana 170, 181TOWSEY, Michael 191TRABOULSEE, Anthony 118TRAGER, Scott 93TRAINI, Daniela 136TRAN, Dung 149TRAN, Duyet 149TRAN, Trac 149TRÉMEAU, Alain 57TRUDEAU, Luc 176
TSAI, Chia-Liang 56TSAI, Chia-Yin 129TSAI, Dong-Chen 170, 183TSAI, Min-Hsuan 125TSAI, Ming-Chia 130TSAI, Ming-Han 190TSAI, Ting-Hui 71TSANG, Ing Jyh 139TSANG, Ing Ren 68, 139TSANG, Sik-Ho 127TSAPANOS, Nikolaos 95TSAPATSOULIS, Nicolas 86, 87TSCHUMPERLE, David 200TSENG, Chen-Yu 156TSUDA, Seiya 119TU, Peter 165, 193TU, Wei-Chih 56TUBARO, Stefano 129, 130, 138,
171TUNCEL, Dönüs 118TURK, Matthew 180TURKAN, Mehmet 34, 175TURUWHENUA, Jason 58TUYTELAARS, Tinne 68TZIMIROPOULOS, Georgios 90
UUCHIMURA, Keiichi 56UCHIYAMA, Hideaki 140UEMOTO, Jyunpei 75UHL, Andreas 88, 173, 185UIJLINGS, Jasper 160ULLAH, Habib 156ULLAH, Mohib 156ULRICH, Marco 129UMAKANTHAN, Sabanadesan 105UNSER, Michael 40, 41, 146, 169,
202, 203UNTERWEGER, Andreas 185URATSUKA, Seiho 75
VVACA-CASTANO, Gonzalo 142VACCARI, Andrea 104VAGHARSHAKYAN, Suren 180VALENZISE, Giuseppe 124VAN AUDEKERKE, Johan 118VAN BEEK, Peter 135VAN DAEL, Mattias 63VAN DE WALLE, Rik 184VAN DER SOMMEN, Fons 175VAN EYNDHOVEN, Geert 106VAN GEMERT, Jan 124VAN STEENKISTE, Gwendolyn
118VAN WALLENDAEL, Glenn 184VAN, Luc GOOL 96, 115, 170VANZETTO, G . 168VARDOULIS, Orestis 203VASCONCELOS, Cristina 84VASILIU, Marius 167
VASSEUR, Pascal 55VASU, Subeesh 91VÁZQUEZ NOGUERA, José Luis
152VAZQUEZ, Carlos 202VEER, Dharm 159VEERARAGHAVAN, Ashok 129VEGA, Miguel 148VEILLARD, Antoine 53VELIPASALAR, Senem 139VELMURUGAN, Rajbabu 52VENKATA, Subramanyam 162VENKATAKRISHNAN, S . V . 63VENTURA, Carles 173VENUGOPALAN, Shreyas 137VERBOVEN, Pieter 63VERDOJA, Francesco 78VERDOOLAEGE, Geert 86VERHOYE, Marleen 118VETRO, Anthony 103, 105VETTERLI, Martin 113, 133VIDAL, Esteban 55VIEYRES, Pierre 150VILAPLANA, Verónica 173VISWANATHAN, Kartik 114VITEK, Jerrold 203VO, Phong 172VOLZ, Daniel 81VONIKAKIS, Vassilios 190VYDROVA, Jitka 80
WWAINE, Ted 96WALKER, Paul Michael 201WAN, Pengfei 177WAN, Shuai 153, 165WANDELL, Brian 112WANG, Biao 121WANG, Bin 132WANG, Bo 86WANG, Botao 126WANG, Chong 162WANG, Chongjing 192WANG, Dadong 107WANG, Dan 173WANG, Di 72WANG, Dongsheng 109WANG, Fang 138WANG, Fasheng 110WANG, Gang 51WANG, Guozhong 53WANG, Haitao 69, 169, 178WANG, Hao 71WANG, Hongtao 94WANG, Hongzhen 139WANG, Jianyu 162WANG, Jiheng 146WANG, Jing 72WANG, Jinjun 151WANG, Jinqiao 105, 134WANG, Jinzhuo 83, 194
230 | ICIP 2015 – Index of Authors and Session Chairs
WANG, Juan 147WANG, Jue 96WANG, Jun 81WANG, Kai 167WANG, Kaiye 125WANG, Lei 157WANG, Li-lian 155WANG, Liang 115, 125, 132, 156WANG, Lingfeng 84, 123, 139,
191WANG, Mengdi 117WANG, Mengmeng 163WANG, Miaohui 109WANG, Nianbing 102WANG, Qi 175WANG, Qiang 123WANG, Qilong 194WANG, Qingqing 143WANG, Qingyun 151WANG, Qingzheng 132WANG, Qiu 116WANG, Qiusi 87WANG, Ronggang 54, 83, 87,
117, 194WANG, Sheng-Jyh 156WANG, Shengjin 174WANG, Shiqi 135, 146, 164WANG, Shuai 153WANG, Shuang 182WANG, Song 141, 172WANG, Wei 76, 125, 132, 179WANG, Weibao 145WANG, Weining 169WANG, Weiqiang 71, 112, 122,
128WANG, Wenmin 54, 83, 87, 117,
188, 193, 194WANG, Xiang 84WANG, Xiaotao 123WANG, Xin 159WANG, Xing 149WANG, Xiying 51, 69, 169, 178WANG, Yanming 68WANG, Yao 109, 126, 145, 176WANG, Yilin 190WANG, Ying 123WANG, Yitong 83WANG, Yiyang 72WANG, Yong 192WANG, Yu 156WANG, Yu-Chiang Frank 130, 142WANG, Yuan-Gen 77WANG, Yue 60, 70, 72, 155WANG, Yuhang 134WANG, Zhe 83WANG, Zhen 75WANG, Zhenfan 188WANG, Zheng 101WANG, Zhou 109, 146, 163, 164,
186WARD, John Paul 202
WARD, Rabab 63, 64, 65WARNELL, Garrett 75WATANABE, Makoto 97WATASUE, Taro 90WAZAEFI, Yanal 202WEBER, Henrique 90, 191WEBSTER, Dereck 140WEI, Chia-Po 130WEI, Dennis 187WEI, Xiaoyao 151WEI, Xingxing 49WEN, Bihan 196WEN, Hui 94WEN, Huiying 118WEN, Mei 73WEN, Yandong 114WEN, Ying 143WENDT, Herwig 61WENG, Lubin 139WERGHI, Naoufel 102WERMAN, Michael 48, 125WERNICK, Miles 106WESTPHAL, Cedric 159WIAUX, Yves 136WIEGAND, Thomas 70WILDFEUER, Herb 165WILKIN, Paul 101WILKINSON, Jeffrey 165WILKINSON, Michael H .F . 93, 132WILLIAMS, David 93WINKLER, Joab 117WINKLER, Stefan 75, 86, 122,
124, 190WOHLBERG, Brendt 182WOLF, Christian 141WONG, Alexander 62, 99, 124,
166, 172WONG, Chau-Wai 130WONG, Damon Wing Kee 137WONG, Edward 71WONG, Finn 152WONG, Koksheik 184WOO, Jooyeon 166WOODFORD, Brendon 193WOODHAM, Robert J . 119WORKMAN, Scott 79, 171WÖRTWEIN, Torsten 62WU, Chyuan-Tyng 143WU, Dapeng 99WU, Eddy Chi-Hao 166WU, Enhua 141WU, Gangshan 52WU, Haiyuan 142WU, Hanwei 120WU, Hao 70WU, Hong Ren 165WU, Jian 120WU, Jiqing 170WU, Jonathan 90, 104WU, Min 130WU, Pingping 69, 90
WU, Po Chen 196WU, Qin 102WU, Qingbo 146WU, Rui 58WU, Ruiwen 102WU, Shandong 192WU, Shiqian 204WU, Shu 115WU, Songsong 141WU, Tieru 98WU, Tung-Yu 156WU, Xiao-Jun 196WU, Xiaojun 163WU, Xiaolin 57, 98, 185WU, Xiaoyu 185WU, Yiqun 114
XXIA, Gui-Song 60XIA, James J . 152XIA, Menghan 187XIA, Shu-Tao 170XIA, Zengtao 112XIAN, Min 52, 136XIAN, Yang 151XIANG, Dan 49XIANG, Sen 180XIANG, Shiming 97, 123XIANG, Xuezhi 133XIAO, Bai 74XIAO, Jiangjian 73XIAO, Jimin 126XIAO, Jing 175XIAO, Jun 175XIAO, Le 110XIAO, Yang 141, 175, 188XIAOLIANG, Xu 81XIAOQIANG, Li 132XIAOZHOU, Zhou 204XIE, Jie 191XIE, Kai 66XIE, Lingxi 172XIE, Mei 72XIE, Qunyi 59XIE, Xiaohua 86, 98XIE, Xiaokang 141, 188XIE, Xu 83XIN, Jun 99XIN, Xiaomeng 191XING, Junliang 84, 121XING, Luyan 60XING, Xiaofen 69XING, Yi 169XIONG, Hongkai 126, 180XIONG, Wei 60, 70, 155XIONG, Zhang 73, 160XIONG, Zixiang 110XU, Bin 103XU, Fanjiang 200XU, Fei 52, 136XU, Haixia 94
ICIP 2015 – Index of Authors and Session Chairs | 231
XU, Haiyong 145XU, Ke 190XU, Kuanhong 142XU, Long 51XU, Mingwei 141XU, Nan 129, 147XU, Ning 128XU, Richard Yi Da 196XU, Tianyi 92XU, Wanru 105XU, Wanxin 129XU, Weiliang 180XU, Xiang 187XU, Xiangmin 69, 169, 176XU, Xikai 76XU, Xin 52XU, Xingzhong 59XU, Xiuxiu 102XU, Xun 101XU, Xuyuan 137XU, Yangyang 107XU, Yanwu 137XU, Yaowu 169XU, Yatong 142XU, Yong 88XU, Zengmin 192XU, Zi-Xin 160XUE, Haoyang 83, 84XUE, Jian 85XUE, ji*ze 98XUE, Kang 51, 178XUE, Yuanyi 176XUN, Baofeng 125
YYAMADA, Yoshifumi 64YAMAGISHI, Masao 107YAMASAKI, Toshihiko 122YAMAsh*tA, Takayoshi 90, 172YAMAUCHI, Yuji 90, 172YAN, Canxiang 173YAN, Hao 113YAN, Ye 110, 127YAN, Zengqiang 110YAN, Zhisheng 159YANG, En-Hui 55, 176YANG, Feng 60YANG, Fuzheng 165YANG, Guanglei 137YANG, Guanyu 154YANG, Haitao 177YANG, Hongxue 102YANG, Jian 66, 92YANG, Jie 51, 66, 83, 84, 97, 176,
178, 189YANG, Jingyu 141YANG, Jun 56, 202YANG, Junying 175YANG, Lifeng 133YANG, Lin 114YANG, Lingxiao 86
YANG, Meng 114YANG, Ming-Hsuan 71, 173YANG, Mu 171YANG, Sen 91, 171YANG, Wanqi 71YANG, Wenhan 136, 151YANG, Xiaokang 71YANG, Ying 181YANG, Yongyi 106, 147, 194YANG, You 160, 180YANG, Yu-Bin 104YANG, Yueming 193YANG, Yujiu 114YANG, Yunsheng 153YAO, Hongxun 124, 132, 181YAO, Jian 91, 187YAO, Yi 123YASAKA, Shungo 64YASSINE, Inas 201YAYILGAN, Sule Yildirim 201YAZDIAN-DEHKORDI, Mahdi 72YE, Chen 120YE, Dong Hye 106, 134YE, Liang 175YE, Peng 144YE, Qixiang 198YE, Zhipeng 58, 120YEGANEH, Hojatollah 109YEH, Chan-Tai 71YEH, Hao-Wei 156YEH, Yi-Ren 142YI, Wu 204YIHONG, Gong 89YIN, Fang 88YIN, Guangxue 77YIN, Jihao 128YIN, Ling 57YIN, Qiyue 115YING, Peng 85YING, Xianghua 91, 171YOKOYA, Naokazu 185YOO, Chang D . 83, 195YOO, Seunghwan 135YOON, Soo Sung 178YORULMAZ, Onur 118YOSHIHASHI, Ryota 191YOUNAN, Nicolas H . 199YOUNG, Paul 136YOUNG, Sean 89YU, Chuan 180YU, Honghai 130YU, Jing 73, 117YU, Jinze 85YU, Lejun 185YU, Li 110, 126, 180YU, Mei 145YU, Quanhe 107YU, Ting 165YU, Wei 107YU, Xianyu 109YU, Yongjian 96
YU, Zhiding 114YUAN, Chun 120YUAN, Fang 137YUAN, Jiangbo 122YUAN, Jinwei 138YUAN, Junsong 51, 85YUAN, Liming 94YUAN, Lin 77YUAN, Xu 81YUAN, Yuan 89, 170, 177, 193YUAN, Zheng 99YUE, Bo 182YUE, Jiaju 133YUE, Jiguang 68YUEN, Chau 159YUHUI, Zheng 204YUN, Kimin 57, 104YUN, Yixiao 176
ZZACCARIN, André 46, 47ZACHEVSKY, Ido 60ZATT, Bruno 108ZAVALA BOJORQUEZ, Jorge
Arturo 201ZEEVI, Yehoshua Y . 49, 60ZEHNGUT, Niv 68ZELEK, John 99ZENG, Bing 114ZENG, Fanxiang 96ZENG, Hui 130, 131, 137ZENG, Jin 170ZENG, Kai 146, 164ZENG, Rui 154ZENG, Weimin 99ZENG, Wenjun 130ZENG, Yi 58ZENG, Yi-Chong 77ZEPPELZAUER, Matthias 110ZERUBIA, Josiane 49, 80ZHA, Hongbin 91, 171ZHA, Shengxin 200ZHAI, Menghua 171ZHAI, Yuanhao 66, 131ZHANG, Caiming 112ZHANG, Changqing 49ZHANG, Chongyang 71ZHANG, Chunyuan 73ZHANG, Dong 101ZHANG, Fan 136, 145, 159, 163,
165ZHANG, Guangming 152ZHANG, Hejia 81ZHANG, Heng 87ZHANG, Hong 52, 177ZHANG, Hong-Bin 127ZHANG, Honggang 67ZHANG, Hongwei 142ZHANG, Hui 200ZHANG, Ji-Ping 170ZHANG, Jian 58, 97, 183
232 | ICIP 2015 – Index of Authors and Session Chairs
ZHANG, Jinfang 200ZHANG, Jing 140, 181ZHANG, Jinglan 191ZHANG, Jun 182ZHANG, Junge 122ZHANG, Lei 133, 137, 194ZHANG, Liangpei 60ZHANG, Lifang 89ZHANG, Lihe 71ZHANG, Lingfeng 141ZHANG, Lu 181ZHANG, Maojun 149ZHANG, Mengdan 84ZHANG, Miao 60ZHANG, Mingli 112ZHANG, Qiang 49ZHANG, Shanghang 80ZHANG, Shen 87ZHANG, Shengping 124ZHANG, Shizhou 151ZHANG, Shu 53ZHANG, Shuai 118ZHANG, Shuo 160ZHANG, Tao 51ZHANG, Tong 165, 166, 167ZHANG, Wei 143, 144ZHANG, Xiao-Ping 50, 105, 143ZHANG, Xiaoyan 152ZHANG, Xinggong 93ZHANG, Xinxin 117ZHANG, Xiujun 179ZHANG, Xuewu 69, 90ZHANG, Yanan 121ZHANG, Yang 76ZHANG, Yanhao 124ZHANG, Yanning 173ZHANG, Ye 111ZHANG, Yi 151ZHANG, Yichi 162ZHANG, Yichun 49ZHANG, Yingtao 52, 136ZHANG, Yongbing 97, 183ZHANG, Yongdong 50, 182ZHANG, Yu 163, 167ZHANG, Yujia 122, 188ZHANG, Yulun 183ZHANG, Yun 115ZHANG, Yuqi 132ZHANG, Zhaoli 75ZHANG, Zheng 88, 102ZHANG, Zhengdong 107ZHANG, Zhi 125ZHANG, Zhiguo 118ZHANG, Zhongfei 87ZHANG, Zizhuo 50ZHAO, Bo 116ZHAO, Debin 57, 58, 82, 117ZHAO, Fangda 110ZHAO, Genping 102ZHAO, Hanguang 122ZHAO, Huaici 153
ZHAO, Jiu-Yang 104ZHAO, Jiying 56, 57ZHAO, Lei 133ZHAO, Lu 94ZHAO, Nan 156ZHAO, Pengpeng 120ZHAO, Qingjie 191ZHAO, Sicheng 132, 181ZHAO, Wei 58, 120ZHAO, Wenteng 61ZHAO, Xiangyun 99ZHAO, Xin 54ZHAO, Xu 70, 157, 192ZHAO, Xueyi 87ZHAO, Yongqiang 98ZHAO, Zhicheng 133ZHAO, Zhong 89ZHAO, Zhong-Qiu 124ZHEN, Mingmin 188ZHEN, Xiantong 132, 133ZHENG, Amin 89, 170, 177ZHENG, Jianhua 107ZHENG, Jinghong 99, 204ZHENG, Lihong 157ZHENG, Peng 124ZHENG, Wenming 92ZHENG, Xiaozhen 107ZHENG, Ying 132ZHENQIU, Shu 74, 179ZHONG, Baojiang 49ZHONG, Guangyu 72ZHONG, Shengwei 111ZHONG, Zhichao 181ZHONG, Zhun 141ZHOU, Chao 93ZHOU, Fugen 170ZHOU, Jie 114, 180ZHOU, Mingcai 69, 169ZHOU, Mingquan 200ZHOU, Qi 102ZHOU, Tao 66ZHOU, Tianfei 121ZHOU, Wei 109ZHOU, Wengang 83ZHOU, Xiaobo 152ZHOU, Xiaoyan 92ZHOU, Xu 170ZHOU, Yi 74, 176ZHOU, Youjie 141ZHOU, Yu 88, 125ZHOU, Yuxuan 102ZHOU, Zhi 72ZHU, Ce 126ZHU, Dianwen 148ZHU, Feiyun 123ZHU, Gengliang 160ZHU, Guopu 77ZHU, Haigang 198ZHU, Hongmei 128ZHU, Hongqing 59ZHU, Jiehua 89
ZHU, Mengyu 141, 188ZHU, Xiaobin 49ZHU, Yaping 174ZHU, Zijian 204ZHUO, Li 181ZIBETTI, Marcelo V . W . 62, 63ZICKLER, Todd 152ZINE, Abdelmalek 92ZINGER, Svitlana 175ZIOU, Djemel 173, 195ZITA, Ales 80ZITOVA, Barbara 80, 97ZLATINTSI, Athanasia 158ZOU, Junni 180ZOU, Qin 172, 189ZOU, Yi 70, 192ZOU, Yuexian 114ZUO, Chenglin 149ZUO, Yifan 174ZUPANCIC, Ivan 54, 79ZURADA, Jacek M . 203
ICIP 2015 – List of Reviewers | 233
AABBAS, Hazem; Ain Shams UniversityABDELMUNIM, Hossam; Ain Shams UniversityABHAYARATNE, Guruge; The University of SheffieldABIANTUN, Ramzi; Carnegie Mellon UniversityACHIM, Alin; University of BristolACTON, Scott; University of VirginiaADJEROH, Donald; West Virginia UniversityAFLAKI, Payman; NokiaAGUIAR, Pedro; Institute for Systems and Robotics
/ ISTAHLBERG, Jörgen; Linköping UniversityAHN, Sewoong; Yonsei UniversityAHUJA, Nilesh; IntelAIZAWA, Kiyoharu; The University of TokyoAKAR, Gozde Bozdagi; METUAKGUL, Ceyhun Burak; Bogazici UniversityAKSEL, Alla; Northrop GrummanAKSOY, Yagiz; Disney ResearchALATTAR, Adnan; DigimarcALBU, Felix; Valahia University of TargovisteALDAHDOOH, Ahmed; Nantes UniversityALLEBACH, Jan; Purdue UniversityALLEYSSON, David; University Pierre Mendes-
France, GrenobleALONSO-FERNANDEZ, Fernando; Halmstad
UniversityALREGIB, Ghassan; Georgia TechALVAREZ, Carlos; Universitat Politècnica de
CatalunyaAMANATIADIS, Angelos; Democritus University of
ThraceAMAT-ROLDAN, Ivan; YmagingAMER, Maria Aishy; Concordia UniversityANDREADIS, Ioannis; Democritus University of
ThraceANDREOPOULOS, Yiannis; University College
LondonANGELINI, Elsa; Columbia UniversityANGELOPOULOU, Elli; University of Erlangen-
NurembergANGULO, Jesus; MINES ParisTechARDABILIAN, Mohsen; École Centrale de LyonARGENTI, Fabrizio; University of FlorenceARGONES RÚA, Enrique; GradiantARGYROPOULOS, Savvas; StreamOwlARNFRED, Jonas; University of Illinois at Urbana-
ChampaignARNOLD, John; UNSWASADI, Majid; Sina Software Company
INDEX OF REVIEWERS
ASBACH, Mark; Pixolus GmbHASCENSO, Joao; Instituto Superior Tecnico - Instituto
de TelecomunicacoesASHISH, Jagmohan; IBM ResearchASSUNCAO, Pedro; Instituto de Telecomunicacoes
/ IPLeiriaATES, Hasan; Isik UniversityATMOSUKARTO, Indriyati; Singapore Institute of
Technology (SIT)ATREY, Pradeep; State University of New York,
AlbanyAULI-LLINAS, Francesc; Universitat Autonoma de
BarcelonaAUSTVOLL, Ivar; University of StavangerAUTRUSSEAU, Florent; IRCCyN, University of NantesAVANAKI, Ali; Barco HealthcareAVGERINAKIS, Konstantinos; Centre for Research
and Technology Hellas - Information Technologies Institute
AVRITHIS, Yannis; NTUAAYDIN, Tunc; Disney Research ZürichAYMAN, Abaza; West Virginia High Technology
Consortium FoundationAYSAL, Tuncer; Cornell University
BBABAGUCHI, Noboru; Osaka UniversityBABICH, Fulvio; University of TriesteBACCAGLINI, Enrico; Istituto Superiore Mario BoellaBAGCI, Ulas; University of Central FloridaBAILEY, Donald; Massey UniversityBAJIC, Ivan; Simon Fraser UniversityBALADO, Félix; University College DublinBALLESTER, Coloma; University Pompeu FabraBANDOH, Yukihiro; NTT-ATBANNARI, Abderrazak; Arabian Gulf UniversityBARKOWSKY, Marcus; University of NantesBARNER, Kenneth; University of DelawareBARNES, Chris; Georgia Institute of TechnologyBAS, Erhan; General ElectricBAS, Patrick; Ecole Centrale de LilleBASANEZ, Luis; Universitat Politecnica de CatalunyaBASKURT, Atilla; LIRIS CNRSBATOOL, Nazre; Inria Sophia AntipolisBATTIATO, Sebastiano; University of CataniaBATUR, Umit; Texas InstrumentsBAUCKHAGE, Christian; Fraunhofer IAISBAUDRY, Severine; Technicolor R&D FranceBEBIS, George; University of NevadaBECKER-LAKUS, Axel; ChipPath Design Systems
234 | ICIP 2015 – List of Reviewers
BEGHDADI, Azeddine; L2TI, Université Paris 13, Sorbonne Paris Cité
BELLON, Olga; Universidade Federal do ParanáBEN AMOR, Boulbaba; Télécom Lille/CRIStAL
(France)BEN HAMZA, Abdessamad; Concordia UniversityBENAZZA-BENYAHIA, Amel; Sup’ComBENOIS-PINEAU, Jenny; University of Bordeaux/
LABRIBENOIT, Alexandre; LISTIC - Université of SavoieBERBERIDIS, Kostas; University of PatrasBERKNER, Kathrin; Ricoh Innovations Inc.BERNAL, Edgar; XeroxBERNARD, Olivier; CREATISBERNARDINI, Riccardo; Universita di UdineBERRETTI, Stefano; University of FlorenceBERTHOUMIEU, Yannick; Bordeaux INP - Laboratoire
IMS UMR 5218BERTOLINO, Pascal; Université Grenoble AlpesBESCÓS, Jesús; Universidad Autónoma de MadridBESTAGINI, Paolo; Politecnico di MilanoBEVILACQUA, Marco; IMT Institute for Advanced
Studies LuccaBHAGAVATULA, Vijayakumar; Carnegie Mellon
UniversityBHASKARAN, Vasudev; Qualcomm Inc.BHOWMIK, Deepayan; Heriot-Watt UniversityBHUTTA, Adeel; Kent State University @ StarkBIANCHI, Tiziano; Politecnico di TorinoBICHOT, Charles-Edmond; École Centrale de LyonBIGGAR, Michael; University of MelbourneBILCU, Radu Ciprian; MicrosoftBIOUCAS-DIAS, Jose; Instituto Superior TécnicoBLANC-FERAUD, Laure; CNRSBLASI, Saverio; Queen Mary University of LondonBLOCH, Isabelle; Telecom ParisTech - CNRS LTCIBLOOM, Jeffrey; SiriusXM Satellite RadioBLUMENSATH, Thomas; University of SouthamptonBOATO, Giulia; University of TrentoBOBIN, Jerome; CEABOEHME, Rainer; University of MünsterBOLES, Wageeh; QUTBOLON, Philippe; Université Savoie Mont-BlancBORA, Prabin; IIT GuwahatiBORACCHI, Giacomo; Politecnico di MilanoBORGEAT, Louis; National Research Council CanadaBORGNAT, Pierre; CNRS, ENS LyonBORKAR, Amol; IntelBORS, Adrian; University of YorkBOUDRAA, Abdel-Ouahab; École NavaleBOUGACHA, Salma; INRIABOUGANIS, Christos; Imperial College LondonBOUGLEUX, Sebastien; Université de Caen Basse-
NormandieBOUGUILA, Nizar; Concordia UniversityBOULGOURIS, Nikolaos; Brunel University London,
UK
BOURLAI, Thirimachos; WVUBOURSIER, Yannick; Aix Marseille UniversityBOUSLIMI, Dalel; Institut Mines - Telecom; Telecom
Bretagne; Unite INSERM 1101 LatimBOUTHEMY, Patrick; InriaBOUWMANS, Thierry; Université La RochelleBOVIK, Alan; University of TexasBOVOLO, Francesca; University of TrentoBRADLEY, Andrew; The University of Queensland BRANKOV, Jovan; Illinois Institute of TechnologyBRÉDIF, Mathieu; IGNBRENDT, Wohlberg; Los Alamos National LaboratoryBRESSON, Xavier; EPFLBREUSS, Michael; BTU Cottbus-SenftenbergBRIASSOULI, Alexia; Information and Technologies
Institute - Centre for Research and Technology Hellas
BRINGER, Julien; MorphoBRITES, Catarina; IST-ITBROWET, Arnaud; Université catholique de LouvainBRUN, Luc; ENSICAENBRUNA, Arcangelo Ranieri; STMicroelectronicsBUENO, Gloria; Universidad de Castilla-La ManchaBUI, The Duy; Vietnam National University, HanoiBUTALA, Mark; Jet Propulsion LaboratoryBYSTROM, Maja; Bevara TechnologiesBYUN, Jiyun; Mayachitra Inc.
CCABALLERO, Cesar; Basque Center on Cognition,
Brain and LanguageCABRERA, Sergio; University of Texas El PasoCAI, Jianfei; Nanyang Technological UniversityCAI, Junjie; UTSACAI, Xun; Massachusetts Institute of TechnologyCALDELLI, Roberto; CNITCALIC, Janko; University of SurreyCAMPISI, Patrizio; Università degli Studi Roma TreCAMPLANI, Massimo; University of BristolCAPLIER, Alice; GIPSA-labCAPPELLARI, Lorenzo; Nidek Technologies SrlCAPRA, Alessandro; STMicroelectronicsCARRILLO, Rafael; EPFLCASTELLANI, Umberto; University of VeronaCATHCART, Michael; Georgia Tech Research InstituteCAYRE, François; Gipsa-Lab, INP GrenobleCELEBI, M . Emre; Louisiana State University in
ShreveportCELENK, Mehmet; Ohio UniversityÇETIN, Mujdat; Sabanci UniversityCHA, Zhang; Microsoft ResearchCHAARI, Lotfi; IRITCHABANNE, Hervé; MorphoCHABERT, Marie; University of ToulouseCHAN, Chee Seng; University of MalayaCHAN, Stanley; Purdue UniversityYH, Chan; The Hong Kong Polytechnic University
ICIP 2015 – List of Reviewers | 235
CHANDLER, Damon; Oklahoma State UniversityCHANG, Shiyu; University of Illinois at Urbana-
ChampaignCHAPIRO, Alexandre; Disney ResearchCHARRIER, Christophe; Université de CaenCHATEAU, Thierry; Blaise Pascal UniversityCHAUDHURY, Kunal; Indian Institute of ScienceCHAUFFERT, Nicolas; CEA NeuroSpinCHAUMONT, Marc; LIRMMCHELLAPPA, Rama; University of MarylandCHEN, Chen; University of Texas at DallasCHEN, Cunjian; Michigan State UniversityCHEN, Fan; Japan Advanced Institute of Science and
TechnologyCHEN, Homer; National Taiwan UniversityCHEN, Hwann-Tzong; National Tsing Hua UniversityCHEN, Jian-Ru; Chien Hsin University of Science and
TechnologyCHEN, Jie; Peking UniversityCHEN, Jin; Lehigh UniversityCHEN, Liming; École Centrale de LyonCHEN, Tsuhan; Cornell UniversityCHEN, Xianjie; University of California, Los AngelesCHEN, Yan; University of Maryland, College ParkCHEN, Yong-Sheng; National Chiao Tung UniversityCHENG, Lu; Purdue UniversityCHENG, Samuel; University of OklahomaCHENG, Wen-Huang; Academia SinicaCHENG, Wentao; NTUCHERIET, Mohamed; École de Technologie
SupérieureCHETVERIKOV, Dmitry; MTA SZTAKICHEUNG, Gene; National Institute of InformaticsCHEUNG, Ngai-Man; Singapore University of
Technology & DesignCHEUNG, Sen-Ching Samson; University of KentuckyCHIA, Liang-Tien; Nanyang Technological UniversityCHIA-WEN, Lin; National Tsing Hua UniversityCHIOU-TING, Hsu; National Tsing Hua UniversityCHO, Nam Ik; Seoul National UniversityCHOU, Philip; Microsoft ResearchCHOUDHURY, Anustup; Sharp Labs of AmericaCHU, Henry; University of Louisiana at LafayetteCHU, Wei-Ta; National Chung Cheng UniversityCHUBACH, Olena; RWTH Aachen UniversityCHUNG, Albert C . S .; The Hong Kong University of
Science and TechnologyCHUONG, Nguyen; University of OklahomaCHUPEAU, Bertrand; Technicolor R&D FranceCICIRELLI, GRAZIA; National Research Council of
ItalyCIUC, mihai; University Politehnica of BucharestCIUCIU, Philippe; CEACIVANLAR, Mehmet; Ozyegin UniversityÇLA, Cevahir; ASELSAN Inc.CLARYSSE, Patrick; CREATIS CNRS UMR 5220,
Inserm U1044
CLAUSI, David; University of WaterlooCOGRANNE, Rémi; Troyes University of TechnologyCOHEN, Robert; Mitsubishi Electric Research
LaboratoriesCOLANTONIO, Sara; CNRCOLTUC, Dinu; Valahia University of TargovisteCOMESAÑA-ALFARO, Pedro; University of VigoCONNAH, David; University of BradfordCONSTANTINE, Kotropoulos; Aristotle University of
ThessalonikiCORD, Matthieu; LIP6, UPMCCORMIER, Stéphane; URCACORNELIS, Jan; Vrije Universiteit Brussel (VUB)CORREIA, Paulo; Instituto Superior TécnicoCORRIGAN, David; Trinity College DublinCOUDOUX, François-Xavier; IEMN DOAE UVHCCOULOMBE, Stéphane; École de technologie
supérieureCREUSERE, Charles; New Mexico State UniversityCRISTANI, Marco; University of VeronaCUI, Peng; Tsinghua UniversityCUI, Suxia; Prairie View A&M UniversityCUNNINGHAM, Robert; MIT Lincoln Laboratoryc*ntOOR, Naresh; Intelligent Automation Inc.CYGANEK, Boguslaw; Krakow University of Science
and TechnologyD’ORAZIO, Tiziana; CNR
DDAI, Wei; Hong Kong University of Science and
TechnologyDAMERA-VENKATA, Niranjan; Hewlett-Packard
LaboratoriesDAOUDI, Mohamed; Institut Mines-Télécom/Telecom
LilleDAS, Samarjit; Bosch Research, CMUDAUWELS, Justin; Nanyang Technological UniversityDE co*ck, Jan; Ghent University - iMindsDE NATALE, Francesco ; University of Trento DE QUEIROZ, Ricardo; Universidade de Brasilia -
University of WashingtonDE ROSA, Alessia; University of FlorenceDE SIMONE, Francesca; Telecom Paris TechDE WITH, Peter H .N .; Eindhoven Universitiy of
TechnologyDE WITTE, Valérie; University of AntwerpDEBAYLE, Johan; MINES Saint-EtienneDEBREUVE, Eric; Laboratoire I3S / CNRS / University
Nice Sophia AntipolisDEFEE, Irek; Tampere University of TechnologyDEL-BLANCO, Carlos R .; Universidad Politecnica de
MadridDELACHARTRE, Philippe; INSA LyonDELEDALLE, Charles-Alban; IMB - CNRS, Université
BordeauxDELIGIANNIS, Nikos; University College LondonDELLANDREA, Emmanuel; École Centrale de Lyon -
LIRIS Lab
236 | ICIP 2015 – List of Reviewers
DELLEPIANE, Silvana; Università degli Studi di Genova
DELOUILLE, Veronique; Royal Observatory of Belgium
DELP, Edward; Purdue UniversityDELPHA, Claude; Université Paris SudDEMITRI, Nevine; Technische Universität DarmstadtDERAVI, Farzin; University of KentDERRODE, Stéphane; Ecole Centrale, Lyon, FranceDESCOMBES, Xavier; INRIADEVRIM, Unay; Bahcesehir UniversityDIAGO, Luis; Interlocus IncDIANAT, Sohail; Rochester Institute of TechnologyDIAS, Andre; BBC R&DDIAZ-DE-MARIA, Fernando; Universidad Carlos III
de MadridDIMICCOLI, Marielma; Universitat Autònoma de
BarcelonaDING, Yi; University of WashingtonDITTMANN, Jana; Otto-von-Guericke-Universität
Magdeburg DJERMOUNE, El Hadi; CRAN, Université de Lorraine,
CNRSDOBIGEON, Nicolas; University of ToulouseDOMANSKI, Marek; Poznan University of TechnologyDOMÍNGUEZ-CONDE, Gabriel; Universidade de VigoDONG, Jane; California State University, Los AngelesDONIDA LABATI, Ruggero; Università degli Studi di
MilanoDOOMS, Ann; Vrije Universiteit BrusselDORETTO, Gianfranco; West Virginia UniversityDÖRKSEN, Helene; inIT DRAGOTTI, Pier Luigi; Imperial College LondonDRAHANSKY, Martin; Brno University of Technology,
Faculty of Information TechnologyDUAN, LINGYU; Institute of Digital Media, School of
EE & CS, Peking UniversityDUARTE, Marco; University of Massachusetts
AmherstDUBOIS, Eric; University of OttawaDUBOIS, Julien; University of BourgogneDUBUISSON, Séverine; ISIR - UPMC Sorbonne
UniversitésDUCLA SOARES, Luis; ISCTE-IUL/ITDUFAUX, Frederic; TELECOM ParisTechDUFOUR, Alexandre; Institut PasteurDUPÉ, François-Xavier; Aix-Marseille Université
EECHEGARAY, Sebastian; Stanford UniversityEGLIN, Véronique; LIRISEISERT, Peter; Fraunhofer HHI / Humboldt University
BerlinEKLUND, Anders; Linköping UniversityEKMEKCIOGLU, Erhan; Loughborough University in
LondonEL-BAZ, Ayman; University of LouisvilleEL-MALEH, Khaled; Qualcomm
EL-MELEGY, Moumen; Assiut UniversityELEFTHERIADIS, Alexandros; Vidyo, Inc.ELEYAN, Alaa; Mevlana UniversityELVIR, Causevic; Black Stone IPENGAN, Kjersti; University of StavangerENGELKE, Ulrich; CSIROERKIN, Zeki; TU DelftESCUDERO-VIÑOLO, Marcos; VPU-Lab EPS UAMEVANS, Alun; Universitat Pompeu FabraEVANS, Brian; The University of Texas at Austin
FFABLET, Ronan; Institut Mines-Télécom/Télécom
BretagneFADILI, Jalal; CNRS-ENSICAEN-U. CaenFAHMY, Gamal; Australian College in KuwaitFAN, Jian; HP LabsFAN, Yi; FANG, Lu; USTCFANG, Yuming; Nanyang Technological University,
SingaporeFARAG, Aly; University of LouisvilleFARIA, Sérgio; Instituto de TelecomunicacoesFARIAS, Mylene; University of BrasiliaFARINELLA, Giovanni Maria; University of CataniaFARRE, Miquel; Disney ResearchFARUP, Ivar; Gjøvik University CollageFELDMAN, Sergey; Data Cowboys, LLCFELDMANN, Ingo; Fraunhofer HHIFERNANDEZ DOMINGUEZ, Gustavo; AIT Austrian
Institute of TechnologyFERNANDEZ-MALOIGNE, Christine; University of
PoitiersFESSLER, Jeff; University of MichiganFIEGUTH, Paul; University of WaterlooFIGUEIREDO, Mario; Instituto Superior TécnicoFILIP, Sroubek; Czech Academy of SciencesFILLATRE, Lionel; University Nice Sophia AntipolisFISCHER, Thomas; Washington State UniversityFLORENCIO, Dinei; Microsoft ResearchFLORES-MANGAS, Fernando; University of TorontoFLYNN, Patrick; University of Notre DameFOFI, David; Université de BourgogneFOI, Alessandro; Tampere University of TechnologyFONTAINE, Caroline; CNRS Telecom BretagneFORCHHAMMER, Søren; DTU FotonikFORESTI, Gian Luca; University of UdineFOUGEROLLE, Yohan; Université de BourgogneFOWLER, James; Mississippi State UniversityFRADET, Matthieu; TechnicolorFRATER, Michael; UNSW AustraliaFRIBOULET, Denis; CreatisFUJII, Toshiaki; Nagoya UniversityFURON, Teddy; Inria
GGADIA, Davide; University of MilanGAO, Sheng; institute for Infocomm Research
ICIP 2015 – List of Reviewers | 237
GARCIA, Alvaro; Universidad Autonoma de MadridGARCIA, Christophe; INSA de LyonGARCÍA, Narciso; Universidad Politécnica de MadridGASULL, Antoni; UPCGATTA, Carlo; Computer Vision CenterGEREK, Omer Nezih; Anadolu UniversityGERONIMO, David; Catchoom TechnologiesGIJSENIJ, Arjan; AkzoNobelGIOIA, Patrick; Orange LabsGIRO-I-NIETO, Xavier; Technical University of
Catalonia (UPC)GIUSTO, Daniel; University of CagliariGOH, Jonathan; Institute for Infocomm Research,
Agency for Science, Technology and Research (A*STAR)
GOMES, Herman; UFCGGOMES, Jose Gabriel; UFRJGONZALEZ, Fabio; National University of ColombiaGONZÁLEZ BALLESTER, Miguel Ángel; ICREA /
Universitat Pompeu FabraGORMISH, Michael; Ricoh Innovation, Corp.GOTCHEV, Atanas; Tampere University of TechnologyGRAMFORT, Alexandre; Telecom ParisTech, CNRS
LTCIGRAMMALIDIS, Nikos; Centre for Research and
Technology HellasGRANGETTO, Marco; University of TurinGRAVA, Cristian; University of OradeaGRAZIOSI, Danillo; Ostendo Technologies Inc.GRECOS, Christos; ConsultantGRENIER, Thomas; Université de LYONGU, Irene Y .H .; Chalmers University of TechnologyGUAN, Ling; Ryerson UniversityGUANG, Deng; La Trobe UniversityGUARAGNELLA, Cataldo; Politecnico di BariGUDUKBAY, Ugur; Bilkent UniversityGUILLEMOT, Christine; INRIAGUIMARAES, Silvio; PUC MinasGULDOGAN, Esin; NokiaGUMUSTEKIN, Sevket; Izmir Institute of TechnologyGUNTURK, Bahadir; Louisiana State UniversityGUO, Guodong; WVUGUO, Jing-Ming; National Taiwan University of
Science and TechnologyGUO, Yandong; MicrosoftGUO, Zhenhua; Tsinghua UniversityGUPTA, Anubha; IIIT DelhiGUPTA, Sumana; IIT-Kanpur
HHALDAR, Justin; University of Southern CaliforniaHAMIDOUCHE, Wassim; IETR Lab INSA de RennesHAMZAOUI, Raouf; De Montfort UniversityHAN, Jingning; Google IncHANG, Hsueh-Ming; National Chiao-Tung UniversityHANSEN, Lars Kai; Technical University of DenmarkHARTUNG, Frank; FH Aachen
HASAN, Yassin; Assiut UniversityHAVLICEK, Joseph; University of OklahomaHE, Dake; BlackBerryHELLE, Philipp; Fraunhofer Heinrich Hertz InstituteHEO, Suwoong; Yonsei UniversityHERLIN, Isabelle; INRIAHEU, Jun-Hee; SK TelecomHEWAGE, Chaminda; Kingston UniversityHILL, Paul; University of BristolHILSMANN, Anna; Fraunhofer HHIHIRAKAWA, Keigo; University of DaytonHO, Yo-Sung; Gwangju Institute of Science and
TechnologyHOFBAUER, Heinz; University of SalzburgHONG, Richang; Hefei University of TechnologyHOU, Chenping; HU, Wei; Hong Kong University of Science and
TechnologyHU, Yu Hen; Univ of Wisconsin - MadisonHU, Yue; Harbin Institute of TechnologyHUANG, Ching-chun; National Chung Cheng
UniversityHUANG, Chun-Rong; National Chung Hsing
UniversityHUANG, Qinghua; South China University of
TechnologyHUANG, Weimin; Institute for Infocomm ResearchHUANG, Xiaojie; GEHUNG, Edson Mintsu; Universidade de BrasiliaHUTTER, Andreas; Siemens AGHWANG, Wen-Liang; Academia SinicaHWANG, Wonjun; Korea Advanced Institute of
Technology
IIKEHARA, Masaaki; Keio UniversityIMRE, Evren; University of SurreyINAZUMI, Yasuhiro; University of ToyamaIOSIFIDIS, Alexandros; Tampere University of
TechnologyISKANDER, D . Robert; Wroclaw University of
TechnologyIWAHASHI, Masahiro; Nagaoka University of
Technology
JJABER, Mustafa; Nant Vision Inc.JACQUES, Laurent; UCL BelgiumJANG, Euee Seon; Hanyang UniversityJASON, Fritts; Saint Louis UniversityJEON, Byeungwoo; Sungkyunkwan UniversityJI, Rongrong; School of Information Science and
Engineering, Xiamen UniversityJIANDE, Sun; Shandong UniversityJIANG, Xudong; Nanyang Technological UniversityJIANG, Yuebing; Real Communications Inc.JIANSHENG, Chen; Tsinghua UniversityJILLELA, Raghavender; Digital Signal Corporation
238 | ICIP 2015 – List of Reviewers
JIN, Guoxin; Northwestern UniversityJIN, Pengchong; Purdue UniversityJINJIAN, Wu; Xidian UniversityJINQIAO, Wang; National Lab of Pattern Recognition,
Institute of Automation, Chinese of Sciences JIWEN, Lu; ADSCJONIC, Slavica; CNRSJUNEJO, Imran; University of Central Florida
KK .C ., Amit Kumar; Université catholique de LouvainKALE, Amit; Siemens KALMAN, Palagyi; University of SzegedKANEMURA, Atsunori; AISTKANKANHALLI, Mohan; National University of
SingaporeKARL, Clem; Boston UniversityKATKOVNIK, Vladimir; Tampere University of
TechnologyKATTO, Jiro; Waseda UniversityKATZENBEISSER, Stefan; TU DarmstadtKAUP, Andre; Friedrich-Alexander University
Erlangen-Nürnberg (FAU)KAWULOK, Michal; Silesian University of TechnologyKAYABOL, Koray; Gebze Institute of TechnologyKE, Gu; Shanghai Jiao Tong UniversityKEIMEL, Christian; TUMKEHTARNAVAZ, Nasser; University of Texas at DallasKELLER, Yosi; Bar-Ilan UniversityKEREKES, John; Rochester Institute of TechnologyKEROFSKY, Louis; InterDigital CommunicationsKERVRANN, Charles; InriaKHALIL, Mahmoud; Ain Shams UniversityKHAN, Ekram; Aligarh Muslim UniversityKHANSARI, Mohammad; University of TehranKHWAJA, Ahmed; Ryerson UniversityKIEFFER, Michel; L2S, CNRS-CentraleSupelec-Univ
Paris-SudKIM, Chang-Su; Korea UniversityKIM, Hansung; University of SurreyKIM, Woojae; Yonsei UniversityKIMIA, Benjamin; Brown UniversityKIRCHNER, Matthias; University of BinghamtonKISACANIN, Branislav; InterphaseKNAUS, Claude; GoogleKOK, Chi wah; Canaan Semiconductor LimitedKOKARAM, Anil; GoogleKOLLIAS, Stefanos; NTUAKOMPATSIARIS, Ioannis; CERTH-ITIKONDI, Lisimachos; University of IoanninaKONG, Adams; Nanyang Technological UniversityKONG, Xiangwei; Dalian University of TechnologyKOPPARAPU, Sunil Kumar; TCS Innovation LabsKOSCHAN, Andreas; University of TennesseeKOUAME, Denis; University of Toulouse III - Paul
SabatierKOUNALAKIS, Tsampikos; Brunel University London
KOVACS, Levente; MTA SZTAKIKOWALSKI, Matthieu; Univ Paris-SudKRIM, Hamid; NCSUKRUTZ, Andreas; quavideo.deKUIJPER, Arjan; Fraunhofer IGDKUMAR, Ajay; The Hong Kong Polytechnic UniversityKUO, C .-C . Jay; University of Southern CaliforniaKURCEREN, Ragip; NokiaKURIBAYASHI, Minoru; Kobe UniversityKURUGOLLU, Fatih; Queen’s UniversityKURUOGLU, Ercan Engin; CNRKWON, Young-Bin; Chung-Ang UniversityKYBIC, Jan; Czech Technical University in Prague
LLABIT, Claude; INRIALADRET, Patricia; Gipsa-labLAFRUIT, Gauthier; Université Libre de BruxellesLAGENDIJK, Reginald; Delft University of TechnologyLAM, Edmund; The University of Hong KongLAM, Tuyet-Trang; Intel CorporationLAMBERT, Patrick; University of SAVOIE, LISTICLARABI, Chaker; Université de PoitiersLARTIZIEN, Carole; CREATIS, CNRS UMR5220,
INSERM U1044, INSA Lyon, Université de LyonLAZZERETTI, Riccardo; University of SienaLE BOUQUIN JEANNÈS, Régine; Université de
Rennes 1LE CALLET, Patrick; IRCCyN UMR CNRS 6597LE GUELVOUIT, Gaëtan; B<>COMLE MEUR, Olivier; University of Rennes 1LEBOWSKY, Fritz; STMicroelectronicsLEDESMA-CARBAYO, Maria J; Universidad
Politécnica de MadridLEE, HeungKyu; KAISTLEE, Jack Y . B .; The Chinese University of Hong KongLEE, Jong-Seok; Yonsei UniversityLEEDHAM, Graham; Nanyang Technological
UniversityLEFEBVRE, Frédédric; TechnicolorLEFEVRE, Sebastien; LEOU, Jin-Jang ; National Chung Cheng UniversityLEOW, Wee Kheng; National University of SingaporeLEVINE, Martin; McGill UniversityLI, Chang-Tsun; University of WarwickLI, Jiangtao; FacebookLI, Liyuan; Institute for Infocomm ResearchLI, Peng; LI, Shujun; University of SurreyLI, Wen; LI, Xin; LI, Yingbo; ENS ParisLI, Zhu; LI-WEI, Kang; National Yunlin University of Science
and TechnologyLIANG, Chia-Kai; Lytro IncLIANG, Jie; Simon Fraser University
ICIP 2015 – List of Reviewers | 239
LIAO, Rui; Siemens CorporationLIEBGOTT, Herve; LIEBLING, Michael; Idiap Research InstituteLIN, Shih-Chun; LIN, Wei-Yang; National Chung Cheng UniversityLIN, Yen-Yu; Academia SinicaLITTLE, Max; MITLIU, Hantao; Delft University of TechnologyLIU, Jundong; Ohio UniversityLIU, Tyng-Luh; Institute of Information Science,
Academia SinicaLIU, Tzu-Yu; UC BerkeleyLIU, Xiaobai; UCLALLAMOCCA, Daniel; Oakland UniversityLOHWEG, Volker; Ostwestfalen-Lippe University of
Applied SciencesLÓPEZ, Antonio; Universidad de GranadaLOPRESTI, Daniel; Lehigh UniversityLOTUFO, Roberto; University of Campinas - UnicampLOUI, Alexander; Kodak Alaris Inc.LU, Chun-Shien; Institute of Information Science,
Academia SinicaLU, Fang; University of Science and Technology of
ChinaLU, Shao-Ping; Vrije Universiteit BrusselLU, Tefan; Technical University of Cluj-NapocaLU, Wei; KLA-Tencor CorporationLU, Yue; Harvard UniversityLUCAS, Laurent; University of Reims Champagne-
ArdenneLUGHOFER, Edwin; Johannes Kepler University of
LinzLUKAC, Rastislav; Foveon Inc. / Sigma Corp.LUN, Daniel; The Hong Kong Polytechnic UniversityLUO, Ying; University of KentuckyLUTHON, Franck; Univeristy of Pau
MMA, Kai-Kuang; Nanyang Technological UniversityMACCHIAVELLO, Bruno; Universidade de BrasiliaMAGGIONI, Matteo; Tampere University of
TechnologyMAGLI, Enrico; Politecnico di TorinoMAGNOR, Marcus; TU BraunschweigMAHOOR, Mohammad; University of DenverMAIORANA, Emanuele; University of Roma TreMAITRE, Henri; Telecom ParisTechMAJUMDAR, Angshul; IIITDMANCAS, Matei; University of Mons MANDIC, Lidija; University of Zagreb Faculty of
Graphic ArtsMANJUNATH, B .S .; UC Santa BarbaraMANOJ, PRAKHYA SAI; MANYA, Afonso; Instituto Superior Tecnico,
University of Lisbon, PortugalMAO, Hongda; Alivecor IncMARCENARO, Lucio; University of GenoaMARCIALIS, Gian Luca; University of Cagliari
MARIOFANNA, Milanova; UALRMARPE, Detlev; Fraunhofer HHIMARTIN-FERNANDEZ, Marcos; Valladolid UniversityMARTINEZ, Geovanni; University of Costa Rica -
IPCV-LABMARTINEZ, Jose M .; Universidad Autónoma de
MadridMARTÍNEZ, José Luis; University of Castilla-La
ManchaMARZILIANO, Pina; Nanyang Technological
UniversityMASMOUDI, Atef; University of Sfax, TunisiaMATHEW, Reji; University of New South WalesMATTAVELLI, Marco; EPFLMATUSZEWSKI, Bogdan; University of Central
LancashireMAUGEY, Thomas; INRIAMAYBANK, Stephen; Birkbeck CollegeMAZURCZYK, Wojciech; Warsaw University of
TechnologyMCDUFF, Daniel; AffectivaMEERWALD, Peter; University of SalzburgMEMON, Nasir; New York University MENEGAZ, Gloria; University of VeronaMENON, Vineetha; Mississippi State UniversityMESSINA, Giuseppe; ST MicroelectronicsMEZARIS, Vasileios; Information Technologies
Institute / CERTHMIAO, Liu; Massachusetts Institute of TechnologyMICHEL, Olivier; GIPSA-LabMICHELONI, Christian; Università degli Studi di
UdineMIGUET, Serge; Université Lumière Lyon 2MILANFAR, Peyman; Google ResearchMILANI, Simone; University of PadovaMILED, Wided; insatMILLANE, Rick; University of CanterburyMILLER, Robert; Applied Communication SciencesMIN, Dongbo; Advance Digital Science CenterMIYATA, Takamichi; Chiba institute of TechnologyMOHAMMAD-DJAFARI, Ali; CNRSMOHAMMED, Al-Mualla; Khalifa UniversityMOIRON, Sandro; VMwareMOKRAOUI, Anissa; Université Paris 13 Sorbonne
Paris CitéMOLINA, Rafael; University of GranadaMONGA, Vishal; Pennsylvania State UniversityMONTEMAYOR, Antonio S .; Universidad Rey Juan
CarlosMOREAUD, Maxime; IFP Énergies nouvellesMOREL, Olivier; Burgundy UniversityMORROS, Josep Ramon; technical University of
Catalinia (UPC)MOTTA, Giovanni; Google Inc.MOUSTAFA, Mohamed; American University in CairoMRAK, Marta; BBC R&DMUELLER-SCHNEIDERS, Stefan; FEV GmbHMUKHERJEE, Dipti Prasad; Indian Statistical Institute
240 | ICIP 2015 – List of Reviewers
MUKHOPADHYAY, Jayanta; IIT KharagpurMULVANEY, David; Loughborough UniversityMUNTEANU, Adrian; Vrije Universiteit BrusselMURAMATSU, Shogo; Niigata UniversityMURRAY, Victor; Universidad de Ingenieria y
Tecnologia - UTECMURTAZA, Taj; LUMS School of Science &
Engineering
NNACCARI, Matteo; BBCNAFORNITA, Corina; Politehnica University TimisoaraNAGAR, Abhishek; SamsungNAGATY, Khaled; The British University in EgyptNAJMAN, Laurent; Université Paris-Est / ESIEE ParisNAKASHIZUKA, Makoto; Chiba Institute of
TechnologyNAMAN, Aous; The University of New South WalesNAMAZI, Nader; The Catholic University of AmericaNARANJO, Valery; Universitat Politecnica de ValenciaNARWARIA, Manish; University of NantesNASIRIRAVANAKI, Mohammadreza; Wayne State
UniversityNATTKEMPER, Tim; Bielefeld UniversityNATU, Ambarish; Patheya SolutionsNAUTSCH, Harald; Linköping UniversityNELSON, James; University College LondonNEUHOFF, David; University of MichiganNEVES, Antonio; University of AveiroNGAN, King Ngi; The Chinese University of Hong
KongNGUYEN, Thanh; University of Wollongong (UoW)NGUYEN, Thinh; Oregon State UniversityNI, Karl; Lawrence Livermore LaboratoryNICOLAS, Henri; University of BordeauxNICOLAS, Marina; ST MicroelectronicsNICOLAS, Tsapatsoulis; Cyprus University of
TechnologyNIEMANN, Heinrich; University Erlangen-NurembergNIETO, Marcos; Vicomtech-IK4NIKOLAIDIS, Nikos; Aristotle University of
ThessalonikiNIKOLAOS, Mitianoudis; Democritus University of
ThraceNIKOU, Christophoros; University of IoanninaNISHIKAWA, KIyoshi; IEICENITTA, Naoko; Osaka UniversityNIWAS, Issac; NTUNOLAND, Katy; BBC Research and DevelopmentNÜKHET, Özbek; Ege UniversityNUNES, Paulo; ISCTE-IUL / Instituto de
TelecomunicaçõesNYUL, Laszlo; University of Szeged
OOGNJEN, Arandjelovic; Deakin UniversityO’GORMAN, Lawrence, Bell Labs
OHM, Jens-Rainer; RWTH Aachen UniversityOKUDA, Masahiro; The University of KitakyushuOLIVEIRA, Henrique; Instituto de TelecomunicaçõesOLIVER, Cossairt; Northwestern UniversityONG, Ee Ping; Institute for Infocomm ResearchORIA, Vincent; NJITORTEGA, Antonio; USCORWELL, James; Kingston UniversityOSTERMANN, Jörn; Leibniz Universität HannoverOTHMAN, Asem; Michigan State University
PPALIOURAS, Vassilis; University of PatrasPALUS, Henryk; Silesian University of TechnologyPANAGIOTAKIS, Costas; Technological Educational
Institute of CretePANG, Jiahao; Hong Kong University of Science and
TechnologyPANTRIGO, Juan; Universidad Rey Juan CarlosPAPADOPOULO, Theodore; INRIAPAPADOPOULOS, Georgios CERTHPAPADOPOULOS, Miltiadis Alexios; University of
BristolPAPPAS, THRASYVOULOS N .; Northwestern
UniversityPARISOT, Pascaline; Université catholique de LouvainPARK, Hyunwoo; Yonsei UniversityPARK, Jaehwa; Chung-Ang UniversityPARK, Rae-Hong; Sogang UniversityPARKKINEN, Jussi; University of Eastern FinlandPASQUINI,Cecilia; University of TrentoPASSAT, Nicolas; Université de Reims Champagne-
ArdennePATEUX, Stéphane; OrangePATIL, Shashikant ; SVKMs NMIMS Mumbai IndiaPAULUS, Dietrich; University Koblenz-LandauPAYAN, Frédéric ; Laboratoire I3S - Université de
Nice Sophia AntipolisPEARLMAN, William; Rensselaer Polytechnic
InstitutePEDERSEN, Marius; Gjøvik University CollegePEDRINI, Helio; University of CampinasPEDRO, Martins; CISUC - University of CoimbraPEINADO, Antonio M .; Universidad de GranadaPENG, WEN-HSIAO; National Chiao Tung UniveresityPEREDA-BAÑOS, Alexandre; Barcelona MediaPEREIRA, Fernando; IST-ITPERREIRA DA SILVA, Matthieu; Université de NantesPEREZ-FREIRE, Luis; GradiantPÉREZ-GONZÁLEZ, Fernando; University of VigoPERRY, Stuart; Canon Information Systems Research
AustraliaPESQUET-POPESCU, Béatrice; Télécom ParisTechPESQUET, Jean-Christophe; Université Paris-EstPETIA, Radeva; University of BarcelonaPETROVSKA DELACRETAZ, Dijana; Mines Télécom /
Télécom SudParis
ICIP 2015 – List of Reviewers | 241
PEVNY, Tomas; Czech Technical University in PraguePEYRIN, Francoise; CREATIS, INSERM, CNRS, INSA
LyonPHAM, Nam Trung; Institute for Infocomm Research,
SingaporePHAN, Anh-Huy; Brain Science InstitutePHILIPS, Wilfried; Ghent UniversityPICKERING, Mark; UNSW CanberraPINHEIRO, Antonio; Universidade da BeiraPINHO, Armando; University of AveiroPINOLI, Jean-Charles; École Nationale Supérieure
des MinesPITAS, Ioannis; Aristotle University of ThessalonikiPIURI, Vincenzo; University of MilanPIVA, Alessandro; University of FlorencePIZURICA, Aleksandra; Ghent UniversityPO, Lai Man; City University of Hong KongPOGGI, Giovanni; Università Federico II di NapoliPORAT, Moshe; TechnionPOURAZAD, Mahsa; UBCPRABHAKARAN, Balakrishnan; University of Texas
at DallasPRASAD, Saurabh; University of HoustonPRATI, Andrea; University IUAV of VenicePRECIOSO, Frederic; University Nice Sophia AntipolisPRINCE, Jerry; Johns Hopkins UniversityPROCHAZKA, Ales; Institute of Chemical technologyPUECH, William; University of MontpellierPUGLISI, Giovanni; University of CagliariPULLI, Kari; LightPUSTELNIK, Nelly; Laboratoire de Physique de
l’École Normale Supérieure de LyonPYUN, Kyungsuk Peter; Samsung Electronics
QQI, Guo-Jun; UCFQIAN, Gang; ObjectVideo Inc.QIAN, Kemao; NTUQIESHI, Zhang; QUELUZ, Maria Paula; Instituto Superior TécnicoQUINN, Anthony; Trinity College DublinQUIVIRA, Fernando; Northeastern University
RRABBANI, Majid; Eastman Kodak companyRABIEE, Hamid R .; Sharif University of TechnologyRADUCANU, Bogdan; Computer Vision CenterRAI K, Yashas; IVC, University of NantesRAJASEKHAR, Deepthi; RAMASWAMY, Sharadh; Google IncRAMPONI, Giovanni; University of TriesteRAMZAN, Naeem; University of West of ScotlandRAOUZAIOU, Amaryllis; National Technical University
of AthensRAPAKA, Krishna; Qualcomm Technologies Inc.RAPANTZIKOS, Kostas; National Technical University
of Athens
RAPESTA, Bartrina; Universitat Autonoma de Barcelona
RATTANI, Ajita; Michigan State UniversityRAULET, Mickael; ATEMEREBECCA, Willett; University of WisconsinREDI, Judith; Delft University of TechnologyREEVES, Stanley; Auburn UniversityREGAZZONI, Carlo; University of GenoaREIBMAN, Amy; Purdue UniversityREN, Kui; SUNY at BuffaloREN, Tongwei; Nanjing UniversityRENARD, Felix; CNRSRENÒ, Vito; Politecnico di BariRIBEIRO, Eraldo; Florida Institute of Technology RIBES, Alejandro; EDF R&DRICCIO, Daniele; University of Napoli Federico IIRICHIARDI, Jonas; University of GenevaRICHTER, Thomas; University of StuttgartRICORDEL, Vincent; IRCCyNRIESS, Christian; University of Erlangen-NurembergRINALDO, Roberto; Università di UdineRO, Yong Man; KAISTROBERT, Antoine; Technicolor R&D FranceROBERT, Safranek; ColorEyeQ Inc.RODET, Thomas; ENS CachanRODRIGUEZ, Arturo; Video Solutions, Cisco
Systems, IncRODRIGUEZ, Paul; PUCPRODRIGUEZ PARDO, Carlos; University of RochesterROHDE, Gustavo; Carnegie Mellon UniversityROLON, Julio; Instituto Politecnico NacionalROMERO, Eduardo; Universidad Nacional de
ColombiaRONG, Yaocheng; TsinghuaRONNEBERGER, Olaf; University of FreiburgROSE, Kenneth; University of California, Santa
BarbaraROUGON, Nicolas; Institut Mines-Telecom / Telecom
SudParisROUMY, Aline; INRIAROUSE, David; Johns Hopkins University Applied
Physics LaboratoryROY-CHOWDHURY, Amit; University of California,
RiversideROYSAM, Badri; University of HoustonRUIZ-HIDALGO, Javier; UPCRYEN, Tom; University of StavangerRZESZUTEK, Richard; Bubl Technology Inc.
SSABER, Eli; RITSACK, Harald; Hasso-Plattner-Institute for IT
Systems EngineeringSADOVNIK, Amir; Lafayette CollegeSAID, Asaad; IntelSALGADO, Luis; Universidad Politécnica de MadridSALMON, Joseph; TELECOM Paristech
242 | ICIP 2015 – List of Reviewers
SALTI, Samuele; University of BolognaSANCHES, J . Miguel; Institute for Systems and
RoboticsSANEI, Saeid; Univ of SurreySANKUR, Bulent; Bogazici UniversitySANMIGUEL, Juan C .; University Autonoma of
MadridSAPPA, Angel; Comptuer Vision CenterSARKAR, Anindya; Ventana Medical SystemsSARKIS, Michel; Qualcomm Technologies Inc.SARTI, Augusto; Politecnico di MilanoSATOH, Shin’ichi; National Institute of InformaticsSAVAKIS, Andreas; Rochester Institute of TechnologySAVVIDES, Marios; Carnegie Mellon UniversitySCHAEFER, Gerald; Loughborough UniversitySCHAFFNER, Michael; Disney ResearchSCHALLAUER, Peter; JOANNEUM RESEARCH
Forschungs Ges.m.b.H.SCHARCANSKI, Jacob; UFRGSSCHEIRER, Walter; Harvard UniversitySCHELKENS, Peter; Vrije Universiteit Brussel (VUB)SCHETTINI, Raimondo; University of Milano Bicocca SCHMID, Natalia; West Virginia UniversitySCHNEIDER, Thomas; TU DarmstadtSCHOEFFMANN, Klaus; University of Klagenfurt,
AustriaSCHREER, Oliver; Fraunhofer HHISCHRETTER, Colas; Vrije Universiteit Brussel (VUB)SCHWANDER, Olivier; SupélecSCHWARTZ, William; Federal University of Minas
GeraisSCHWARZ, Sebastian; BBCSEELAMANTULA, Chandra Sekhar; Indian Institute
of ScienceSENCAR, Husrev Taha; TOBB UniversitySENHADJI, Lotfi; Université de Rennes & INSEMSERGIO, Velastin; Universidad de Santiago de ChileSERRA-SAGRISTA, Joan; Universitat Autònoma de
BarcelonaSETHI, Ricky; Fitchburg State UniversitySEZER, Osman; Mobile Processor Innovation LabSHAKER, Matineh; Northeastern UniversitySHARMA, Gaurav; University of RochesterSHEN, Ju; University of DaytonSHI, Guangming; Xidian UniversitySHI, Pengcheng; RITSHI, Yun-Qing; New Jersey Institute of TechnologySHIJIE, Xiao; NTUSHIMIZU, Shinya; NTT CorporationSHIRALI-SHAHREZA, M . Hassan; Amirkabir
University of Technology (Tehran Polytechnic)SHIRANI, Shahram; McMaster UniversitySHYU, Mei-Ling; University of MiamiSIGNORONI, Alberto; University of BresciaSILVEIRA, Margarida; Institute for Systems
and Robotics, Instituto Superior Técnico, Universidade de Lisboa
SINGH, Raghavendra; IBM ResearchSINGH, Richa; IIIT DelhiSIVASWAMY, Jayanthi; IIIT HyderabadSJÖSTRÖM, Mårten; Mid Sweden UniversitySKODRAS, Athanassios; University of PatrasSKRETTING, Karl; University of StavangerSMOLKA, Bogdan; Silesian University of TechnologySNIDARO, Lauro; University of UdineSOLACHIDIS, Vassilios; CERTHSOLANKI, Kaushal; Eyenuk, Inc.SOLER, Pau; Hewlett-PackardSOLTANIAN-ZADEH, Hamid; University of TehranSONG, Byung Cheol; Inha UniversitySORIA-FRISCH, Aureli; Starlab Barcelona S.L.SPAMPINATO, Concetto; University of CataniaSRINIVASA, Gowri; PESIT Bangalore South CampusSTAEMMLER, Martin; University of Applied Sciences
StralsundSTAMM, Matthew; Drexel UniversitySTAMMINGER, Marc; University of Erlangen-
NurembergSTANCO, Filippo; University of CataniaSTANKOVIC, Vladimir; University of StrathclydeSTEFANIDIS, Anthony; George Mason UniversitySTEFANOSKI, Nikolce; Disney Research ZurichSTEINBACH, Eckehard; TU MunichSTEINEBACH, Martin; FraunhoferSTEVENSON, Robert; University of Notre DameSTOKER, David; SRI InternationalSU, Guan-Ming; Dolby LabsSU, Po-Chyi; National Central UniversitySUN, Changming; CSIROSUN, Qibin; Cisco SystemsSUN, Wenxiu; Lenovo Group LimitedSUN, Xiaoyan; Microsoft Research AsiaSURAL, Shamik; IIT KharagpurSUZUKI, Taizo; TaizoSWAMINATHAN, Ashwin; Qualcomm ResearchSWARUP, medasani; Uurmi SystemsSZCZEPANSKI, Marek; Silesian University of
TechnologySZE, Vivienne; Massachusetts Institute of TechnologySZIRANYI, Tamas; MTA SZTAKI
TTABUS, Ioan; Tampere University of TechnologyTAKAHASHI, Keita; Nagoya UniveresityTAKAMURA, Seishi; NTT CorporationTALBOT, Hugues; Université Paris-Est - ESIEETALU, Stefan; Technical University of Cluj-NapocaTAN, Yap-Peng; Nanyang Technological UniversityTANAKA, Yuichi; Tokyo University of Agriculture and
TechnologyTANG, Jinshan; Michigan Technological UniversityTANYA, Ignatenko; Eindhoven University of
TechnologyTARABALKA, Yuliya; Inria
¸ ˇ ¸
ICIP 2015 – List of Reviewers | 243
TASDIZEN, Tolga; University of UtahTASLI, Emrah; Vicarious Perception TechnologiesTAUBMAN, David; University of New South WalesTAY, David; La Trobe UniversityTAY, Peter; Western Carolina UniversityTAYLOR, Clark; Air Force Research LaboratoryTEFAS, Anastasios; Aristotle University of
ThessalonikiTEKALP, Ahmet Murat; Koc UniversityTENEY, Damien; Carnegie Mellon UniversityTHAKUR, Uday; RWTH Aachen UniversityTHALLINGER, Georg; JOANNEUM RESEARCHTHÉVENAZ, Philippe; EPFLTHIESSE, Jean-Marc; ATEMETHILAK, Vimal; ZACSi CorporationTHIRAN, Jean-Philippe; EPFLThom*oS, Nikolaos; University of EssexTIAN, Dong; Mitsubishi Electric Research LabsTIAN, Xinmei; University of Science and Technology
of ChinaTIAN, Yingli; The City College and The Graduate
Center, The City University of New YorkTILLO, Tammam; Xi’an Jiaotong - Liverpool
UniversityTOMINAGA, Shoji; Chiba UniversityTOMIO, Goto; Nagoya Institute of TechnologyTONDI, Benedetta; University of SienaTONG, Zhang; Hewlett PackardTOSIC, Ivana; RicohTOUGNE, Laure; LIRIS - Université Lyon 2TOURAPIS, Alexandros; Apple IncTRAPPE, Wade; WINLAB - RutgersTRÉMEAU, Alain; Laboratoire Hubert Curien, CNRS,
Université Jean MonnetTROCAN, Maria; ISEPTRONCOSO-PASTORIZA, Juan Ramón; University
of VigoTRUSSELL, Joel; NC State UniversityTSAI, Dong-Chen; National Taiwan UniversityTUBARO, Stefano; Politecnico di MilanoTURKAN, MEHMET; TechnicolorTZIRITAS, Georgios; University of Crete
UUCCHEDDU, Francesca; University of FlorenceUHL, Andreas; University of SalzburgUZUNBAS, Mustafa; GE Global Research
VVACAVANT, Antoine; ISIT lab / Université d’AuvergneVALENTE, Stéphane; STMicroelectronicsVALENZISE, Giuseppe; CNRS LTCI - Telecom
ParisTechVALETTE, Sebastien; CREATIS-CNRSVALVENY, Ernest; Computer Vision Center -
Universitat Autònoma de BarcelonaVAN BEEK, Peter; Sharp Labs of America
VAN DE VILLE, Dimitri; EPFL and University of Geneva
VAN WALLENDAEL, Glenn; Ghent University - iMinds - Multimedia Lab
VANCE, Antony; National InstrumentsVANDEWALLE, Patrick; PhilipsVANTARAM, Sreenath Rao; Intel CorpVARNA, Avinash; Intel CorporationVASSEUR, Pascal; Université de RouenVATSA, Mayank; IIIT DelhiVÁZQUEZ-PADÍN, David; University of VigoVEERARAGHAVAN, Ashok; Rice UniversityVELISAVLJEVIC, Vladan; University of BedfordshireVERDOJA, Francesco; Università degli Studi di TorinoVERDOLIVA, Luisa; Università Federico II di NapoliVERTAN, Constantin; Politehnica University of
BucharestVETRO, Anthony; Mitsubishi Electric Research LabsVIELHAUER, Claus; Brandenburg University of
Applied SciencesVILAPLANA, Veronica; Universitat Politecnica de
CatalunyaVILLEGAS, Paulo; Telefonica I+DCOURBOULAY, Vincent; Université de La RochelleVO, Dung; Ho Chi Minh City University of TechnologyVOLOSHYNOVSKIY, Svyatoslav; UniGEVONIKAKIS, Vassilios; Advanced Digital Sciences
CenterVROCHIDIS, Stefanos; Centre for Research and
Technology HellasVURAL, Elif; INRIAVYAS, Urvi; Stanford University
WWALL, Julie; Queen Mary University of LondonWAN, Pengfei; Hong Kong University of Science and
TechnologyWANG, Lei; University of WollongongWANG, Liang; National Laboratory of Pattern
Recognition, Institute of Automation Chinese Academy of Sciences
WANG, Meng; Hefei University of TechnologyWANG, Sheng-Jyh; National Chiao Tung UniversityWANG, Shiqi; University of WaterlooWANG, Yonghui; Prairie View A&M UniversityWANG, Yu-Chiang Frank; Academia SinicaWANG, Zhiyong; University of SydneyWANG, Zhou; University of WaterlooWELLER, Daniel; University of VirginiaWENDT, Herwig; CNRS, University of ToulouseWESTERINK, Peter; IBMWIEN, Mathias; RWTH Aachen UniversityWILKINSON, Michael; University of GroningenWINKEN, Martin; Fraunhofer HHIWINKLER, Stefan; Advanced Digital Sciences
Center (ADSC), University of Illinois at Urbana-Champaign
WOLF, Christian; INSA-Lyon / LIRIS
244 | ICIP 2015 – List of Reviewers
WON, Chee Sun; Dongguk UniversityWONG, Kin Hong; The Chinese University of Hong
KongWONG, Kwan-Yee Kenneth; The University of Hong
KongWOODARD, Damon; University of FloridaWOODS, John; Rensselaer Polytechnic InstituteWORRALL, Stewart; EricssonWU, Wei; South China University of TechnologyWÜRTZ, Rolf P .; Ruhr-UniversityWYATT, Chris; Virginia Tech
XXIANG, Wei; University of Southern QueenslandXIANMING, Liu; Harbin Institute of TechnologyXIAOCHUN, Cao; Tianjin UniversityXIAOJUN, Qi; Utah State UniversityXIAOPENG, Fan; Harbin Institute of TechnologyXIAOQIAN, Wang; XIE, Dan; University of Massachusetts AmherstXINGHUA, Lou; Vicarious FPC Inc.XINXING, Xu; NTUXIONG, Ruiqin; Peking UniversityXU, Changsheng; Chinese Academy of SciencesXU, Min; University of Technology, Sydney
YYAACOUB, Charles; Holy Spirit University of KaslikYAMASAKI, Toshihiko; The University of TokyoYAN, Song; University of Science and Technology
of ChinaYANG, Ge; Carnegie Mellon UniversityYANG, Heng; Queen Mary University of LondonYANG, Huan; NTUYANG, Jie; Carnegie Mellon UniversityYANG, Lei; HPYANG, Ming-Hsuan; University of California at
MercedYANG, Seungjoon; UNISTYANG, Wenxian; Institute for Infocomm Research,
A*STARYANG, Yongyi; Illinois Institute of TehnologyYANNICK, Remion; Université de Reims Champagne
ArdenneYAO, Jianchao; DSO National Labs of SingaporeYE, Jong Chul; KAISTYE, Yan; InterDigital Communications LLCYEA, Sehoon; LG ElectronicsYOON, Soweon; Michigan State University / National
Institute of Standards and TechnologyYOU, Jane; The Hong Kong Polytechnic UniversityYOUNAN, Nicolas; Mississippi State UniversityYU, Ying Kin; Shape XYU, Yongjian; Varian Medical Systems, IncYUEN, Pong C; Hong Kong Baptist UniversityYUNJI, Wang;
ZZABULIS, Xenophon; FORTH-ICSZAFEIRIOU, Stefanos; Imperial College LondonZAIBI, Sonia; Ecole Nationale d’Ing., TunisiaZAIDI, Habib; Geneva University HospitalZAMPOLO, Ronaldo; Federal University of ParaZANUTTIGH, Pietro; University of PadovaZENG, Dan; Shanghai UniversityZENG, Huanqiang; Huaqiao UniversityZERUBIA, Josiane; INRIAZERVAKIS, Michalis; Technical University of CreteZHA, Zheng-Jun; Chinese Academy of SciencesZHAI, Guangtao; Shanghai Jiao Tong UniversityZHANG, Changshui; Tsinghua UniversityZHANG, Dengsheng; Federation University AustraliaZHANG, Dongming; Chinese Academy of SciencesZHANG, Jia; Purdue UniversityZHANG, Jing; Beijing University Of TechnologyZHANG, Lei; The Hong Kong Polytechnic UniversityZHANG, Li; QualcommZHANG, Luming; National University of SingaporeZHANG, Ning; IMAX CorporationZHANG, Shaoting; Rutgers UniversityZHANG, Xin; South China University of TechnologyZHANG, Xinfeng; NTUZHANG, Xujie; QualCommZHANG, Zhilin; Samsung Research AmericaZHAO, H . Vicky; University of AlbertaZHAO, Jian; MicrosoftZHAO, Yao; Beijing Jiaotong UniversityZHENG, Amin; Hong Kong University of Science and
TechnologyZHENG, Liang; Tsinghua UniversityZHENGGUO, Li; Institute for Infocomm ResearchZHENGHUA, Yu; BocomZHONG, Zhang; University of Texas at ArlingtonZHOU, Bo; Qualcomm Technologies Inc.ZHOU, Jiantao; University of MacauZHOU, Liang; Nanjing University of Posts and
TelecommunicationsZHOU, S . Kevin; Siemens Corporate ResearchZHOU, Wengang; University of Science & Technology
of ChinaZHOU, Zhi; Nanyang Technological UniversityZHUANG, Xiaodan; AppleZIMMERMANN, Roger; National University of
SingaporeZNAMENSKIY, Dmitry; Philips ResearchZOIDI, Olga; Aristotle University of ThessalonikiZORAN, Ivanovski; University Ss. Cyril and
Methodius in SkopjeZOU, Ju Jia; University of Western SydneyZWIGGELAAR, Reyer; Aberystwyth University
ICIP 2015 – Meeting Rooms Floor Layout | 245
MEE
TIN
G R
OO
MS
FLO
OR
LAYO
UT
Avenue Honoré-Mercier
HALL
2000
FOYE
R 20
00
200
0D
200
0C
200
0B
200
0A210
1
210
2A 210
2B
20
7
202
204 A
205 A
20
3M
ULTI
MED
IARO
OM
205 B
205 C
200
200 C
A
200 B
210
4A
210
3
201 A 201 B 201 C
2 2105
104
B
206 A
206 B
204 B
CONV
ENTI
ON
HALL
MUL
TIPU
RPOS
EHA
LL
FOYE
R 2
FOYE
R 20
6HO
NORÉ
-M
ERCI
EREN
TRAN
CE
ACCE
SSLO
ADIN
G DO
CKS
LEVE
L 1
DRES
SING
ROOM
ADR
ESSI
NGRO
OM B
KITC
HEN
SATE
LLIT
EKI
TCHE
NSA
TELL
ITE
KITC
HEN
DRES
SING
ROOM
DDR
ESSI
NGRO
OM C
246 | ICIP 2015 – Hotels & Restaurants map
D'Youville
Bun
ge
175
175
440
du C
orps
-de
-Gar
de
Bad
elar
d
St-C
répi
n
Car
réLé
pin
e
Boulevard
Langelier
Rue
des
Sap
eurs
Parc
des
G
ouve
rneu
rs
Po
rt-D
auphin
Parc
de
laFr
anco
phon
ie
des
Aug
ustin
es
Plac
e du
M
arch
é-du
-Vi
eux-
Port
Côte
du
Col-
Côt
e
du Petit-
Plac
e de
l' H
ôtel
-de-
Ville
Pla
ce d
e l’
Ass
embl
ée-
Nat
iona
le
Navigateurs
Qua
rtie
r
Sai
nt-J
ean-
Bap
tiste
Col
line
Parle
men
taire
Port
eSt
-Jea
n
Port
eK
ent
de la
Port
e Pr
esco
tt
Pl. R
oyal
e
Parc
de
l’Am
ériq
ue-
Fran
çais
e
Pla
ce d
uFa
ubou
rg
John
-G
oudi
e
Pl. d
ela
FAO
Parc
Mon
tmor
ency
Esc.
des
Gla
cis
Joly-
de-
De Montcalm
Pl.
de l’
U.-
du-Q
uébe
c
Narcisse
desMenuisiers
Saun
ders
Qua
rtie
r S
aint
-Roc
h
Rue de la Terrasse Dufferin
Port
eSt
-Jea
n
Cit
adel
le
Gar
e d
u P
alai
s
Promenade de la
Pointe-à-Carcy
Pro
men
ade
Pla
ce
Geo
rge-
V
Jard
in
Jean
ne-d
'Arc
Par
c de
s C
ham
ps-d
e-B
atai
lle
Parc
de
l'Art
iller
ie
Plac
e d'
Arm
esPl
ace
d'Ar
mes
Parc
de
l'Esp
lana
de
Parc
des
G
ouve
rneu
rs
Cap
Dia
man
t
Jard
in d
e S
aint
-Roc
hJa
rdin
de
Sai
nt-R
och
Cen
tre
des
con
grè
s
Esc
alie
r d
uC
ap-B
lanc
Parc
de
laFr
anco
phon
ie
Parc
de
l’Am
ériq
ue-
Fran
çais
e
Plac
e de
la G
are
des
Gou
vern
eurs
Pl. R
oyal
e
Ag
ora
Écl
use
(Lo
ck)
Terminal de croisières
Qua
rtie
rP
etit
Cha
mpl
ain
Pla
ce-R
oyal
e
Vie
ux-P
ort
Vie
ux-
Qué
bec
Qua
rtie
r
Sai
nt-J
ean-
Bap
tiste
Port
eK
ent
Plac
e de
Par
is
Plac
eD'
Youv
ille
Parc
du
Cav
alie
r-
du-M
oulin
Pla
ce d
e l’
Ass
embl
ée-
Nat
iona
le
Funi
cula
ireFu
nicu
laire
Plac
e de
l'H
ôtel
-de-
Ville
Port
e St
-Lou
isPo
rte
St-L
ouis
Port
e Pr
esco
ttC
ollin
ePa
rlem
enta
ire
Parc
Mon
tmor
ency
Esc.
des
Gla
cis
Qua
rtie
r S
aint
-Roc
h
Terrasse Dufferin
Quai Chouinard
Quai 92
Bass
in L
ouis
e
CH
AR
ES
TE
ST
SA
INT-
JEA
NS
AIN
T-JE
AN
GR
AN
DE
AL
LÉ
E
ES
T
QUAI SAIN
T-ANDRÉ
SA
INT-
PAU
L
Sous
-le-F
ort
du C
ul-de
-Sac
Barri
cade
de la
Mon
t-C
arm
el
desGrisons
Donn
acon
a
Parloir
desJa
rdins
P.-O. ChauveauRu
eLa
val
Héb
ert
Dau
phi
ne
D'Auteuil
Sai
nte-
Ann
e
Sainte-Ursule
Sai
nt-L
ouis
Elg
in
McM
ahon
St-Stanislas
Ste-Angèle
de
l'Ars
enal
Côte
Gar
neau
Christie
HamelSaint-F
lavien
Ferland
Saint-P
aul
de la Ménagerie
des
Bell
Vaisseaux-du-Roi
Chantier
Bains
Legaré
dela
Gar
e-d
u-P
alai
s
Saint-Nicolas
l'Éperon
Vallière
des
Soeu
rs-
de-la
-Cha
rité
desGlacis
Abr
aham
-Mar
tin
Ont
ario
Ont
ario
Wilf
rid -
Lau
rier
Briand
Galipeault
duFort
des
Pra
iries
Rue
de l’
Estu
aire
Côt
eD
inan
Panet
desCarrières
Sain
t-An
toin
e
des
Urs
ulin
es
Rioux
des Navigateurs
Sous -le
--le
-Cap
Côte de
la Can
oterie
De
Mai
sonn
euve
Turnbull
De Salaberry
Cartier
Rue
Cré
maz
ieE
st
Lock
wel
l
Bur
ton
Scott
Berthelot
De Lorne
desZouaves
Sai
nt-P
atric
k
Sai
nt-G
abrie
lS
aint
-Joa
chim
Sai
nt-R
éal
Côt
eB
adel
ard
Lavi
gueu
r
Sai
nt-O
livie
r
Ric
helie
u
D'A
igui
llon
Claire - Fontaine
J.-J. Bertrand
Saint-Augustin
CôteSainte-Geneviève
O. -Robitaille
Sainte-Marie
Sainte-Claire
Deligny
Sutherland
Philippe-Dorval
Yvon-Guillou
Colbert
Dem
ers
Mgr-Cazeau
MazenodDe
Jérôme
Nazaire- Fortier
DeMagellan
Narcisse- Belleau
desVoltigeurs
Not
re-D
ame-
des
-Ang
es
Sai
nt-F
ranç
ois
Est
V auban
Louis-A.
Sai
nt-A
mab
le
Est
Place
Pl.
Ouest
De Senezergues
de l'Amérique-Française
Bon
-Pas
teur
Sai
nte
- M
argu
erite
De
Sai
nte-
Hél
ène
Fleu
rie De
Sai
nt-
Est
Valli
erXi’a
nde
De
Ber
nièr
es
DeLaChevrotière
du
Signaï
Ste
-Mad
elei
ne
Côte
du
Col-
Dam
bour
gès
Carleton
Pré
vost
De Bua
de
du Petit-
Champlain
Plac
e du
M
arch
é-du
-Vi
eux-
Port
Rue du
Trésor
Rue
Rue
Rue
Avenue
Avenue
Rue de
Avenue
A venue
Ave
nue
Ave
nue
Rue
Rue
Rue
RU
E
Rue
F.-G.-Marchand
Avenue
BO
ULE
VAR
D
des
Rue
Sai
nt-J
osep
hE
st
Rue
Rue
Cha
mpl
ain
St-François
Ouest
Lavio
lette
Saint-Anselme
de
la
Rei
neD
e
LaS
alle
Caron
du
P
rince
- É
dou
ard
du
Cha
lutie
r
RueduParvis
Rue du Pont
Av.Daulac
Letellier
desMenuisiers- LabergeRue
des
Troi
s-M
âts
Sagard
Monseigneur- Gauvreau
de la
des
Voie-d'Eau
Goélands
Martin-Pêcheur
Mar
ée-H
aute
delaDrave
Saint-Dominique
Saint-Roch
Rue
Ara
goE
st
Ave
nue
Sai
nt-J
ean
DE
SA
INT-
VALL
IER
ES
T
McW
illia
m
Fras
er
Saun
ders
Ab
erd
een
de
l'Hôtel-Dieu
Pas
. sou
sle
Cot
eau
Rev
illon
Vic
tor-
Ch.
des
Éc
ossa
is
Rue
du
Mar
ché-
Ber
thel
ot
Pla
ce d
uFa
ubou
rg
Pla
ceJa
cque
s-C
artie
r
Pl.
de l’
U.-
du-Q
uébe
c
Rue de la Terrasse Dufferin
du C
orps
-de
-Gar
de
Av. S
aint
e -
Gen
eviè
ve
De
Bré
beuf
Côte de la Citadelle
du
Ric
helie
u
Côt
e d
e la
Pot
asse
D
e S
aint
-Val
lier
E.
du Palais
Cou
illard
Cha
rlevo
ix
l'Ancien-
de
la
To
urel
le
De
Sai
nte-
Hél
ène
Car
réLé
pin
e
Rue
du
R
oi
R
ue
du
R
oi
de la Chapelle
Rue
Boulevard
Langelier
St-C
répi
n
Chr
isto
phe
- C
olom
b
E
st
RUE DORCHESTER
C
ÔTE
D
'ABR
AHAM
RUE DE LA COURONNE
des
Com
mis
saire
s O
des
Com
mis
saire
s
Est
C
hare
st O
B
d S
t-Jo
sep
h O
S
aint
-Jos
eph
Est
AVENUE HONORÉ - MERCIER
B
OU
LEVA
RD
R
EN
É -
LÉ
VE
SQ
UE
E
ST
Av.
du
Cap
-aux
-Dia
man
ts
Mgr-De
Rem
parts
Po
rt-D
auphin
Rue
des
Sap
eurs
De Montcalm Cours du Général- Cours du Général-
Avenue Taché
George-V
George-V
Taschereau
Côte de
la
M
onta
gne
Notre-Dame
des
T
ravers
iers
du Sault-au-Matelot
Cook
S
aint
e-An
ne
G
rand
s-Ve
nts
des
Randonnée
de la
du
Antonio-Barrette
des
Aug
ustin
es Ren
é-Ja
lber
t
du P
orch
e
Rue
du
Mar
ché-
Finl
ayR
ue d
u D
on-d
e-D
ieu
Rue
Isid
ore-
Thib
aude
auD‘
Artig
ny
des
de la Porte Haldimand
BO
ULE
VAR
D
C
HA
MP
LAIN
B
OU
LEVA
RD
C
HAMPLAIN
MAR
CHÉ
CHA
MPLA
IN
DALHOUSIE
Ave
nue
Côte
De Salaberry
A
venu
e
S
aint
-Den
is
John
-G
oudi
e
Pl. d
ela
FAO
Lotb
iniè
re
Parlementaires
Joly-
de-
Geo
rge
- V
IAv
enue
George - VI
BD J
EAN-LES
AGE
Saint - Pierre
Rue
de
Oct
ave
Côt
e de
l'Escarpe
de la Fabrique
PONT SAMSON
de la
Vie
ille-
Uni
vers
ité
Sainte-Famille
Richard- TurgeonBurke
Horatio- Nelson
Avenue Louis-
Saint-Laurent
Aven
ue Garneau Ouest
Avenue G
arne
au E
st
Saint T
homas
175
440
C
onv
enti
on
sit
e
1.
Qué
bec
City
Con
vent
ion
Cen
tre
H
ote
l lis
t2.
Fa
irmon
t Le
Châ
teau
Fro
nten
ac
3.
Hilt
on Q
uéb
ec
4.
Hôt
el C
hâte
au L
aurie
r Q
uéb
ec
5.
Hôt
el D
elta
Qué
bec
6.
Hôt
el M
anoi
r V
icto
ria
7.
Hôt
el P
alac
e R
oyal
8.
Hôt
el Q
uart
ier
(Bor
. Sai
nte-
Foy)
9.
Le C
onco
rde
M
arrio
tt -
Qué
bec
City
Dow
ntow
n
11.
TRY
P Q
uéb
ec H
ôtel
PU
R
12.
Uni
vers
ité L
aval
res
iden
ces
(B
or. S
aint
e-Fo
y)
R
esta
ura
nt
list
Fa
st F
oo
d $
8 -
$15
13
Caf
é-b
oula
nger
ie P
ailla
rd
14
Che
z A
shto
n
15
Sna
ck B
ar S
t-Je
an
16
Sub
way
Q
uic
k lu
nch
$12
- $
2117
C
osm
os C
afé
18
Jack
Sal
oon
19
L'A
ccen
t
20
Yuzu
Sus
hi
B
usi
nes
s lu
nch
$14
- $
2821
Il
Teat
ro
22
Le H
obb
it
23
Le M
oine
Éch
anso
n
24
Les
Troi
s G
arço
ns
25
Pia
zzet
ta
Tour
ist i
nfor
mat
ion
Tel.:
418
-641
-629
Par
king
Trai
n st
atio
n
Bus
term
inal
(int
erur
ban)
Con
trolle
d A
cces
s H
ighw
ay
Hig
hway
LEG
EN
D
St. L
awre
nce
Rive
r
1 km
= 0
.6 m
i.
5
0 m
= 1
64 ft
.
0 25
050
0m
etre
s
Old
Qué
bec
Map
CÔ
TE
-DE
-BE
AU
PR
ÉA
ND
ÎLE
D'O
RLÉ
AN
S
St.
Char
les R
iver
Estu
ary
21 3 4 5 6 7 8 9 10 11 12
35
1
23 917
4
1814
16
107
2
13624
2119
20
1522 25
11
13 14 15 16 17 18 19 20 21 22 23 24 25
12 8
ICIP
201
5 C
ongr
ess
Q
uéb
ec C
ity C
onve
ntio
n C
entr
e -
Sep
tem
ber
27
to 3
0, 2
015
HO
TELS
& R
ESTA
URA
NTS
MA
P
NOTES