|
Program
Monday, July 9
8:00 AM - 9:00 AM
Registration
9:00 AM - 10:00 AM
Keynote Presentation
- Information-Based Classification and Retrieval
- Keith van Rijsbergen
- Information has been, and continues to be, an elusive concept; nevertheless many philosophers, mathematicians, logicians, and computer scientists consider that the concept is fundamental. Many attempts have been made, with varying degrees of success, to provide a sensible and intuitively acceptable definition of information. In this lecture I will give a brief survey of different notions of information, including statistical and epistemic ones. If one takes as one’s starting point that for an ontology of objects individuated by a cognitive agent it makes sense to speak of the information contained in one object about another. Then one can argue, as I will, that a properly defined information calculus may constitute a sound basis for the classification and retrieval of multimedia objects.
10:00 AM - 10:20 AM
Coffee Break
10:20 AM - 12:00 PM
Oral Session
- A Content-Based Image Retrieval Scheme Allowing for Robust Automatic Personalization
- Sotirios Chatzis (National Technical University of Athens, Greece); Anastasios D. Doulamis (National Technical University of Athens, Greece); Theodora A. Varvarigou (national Technical University of Athens, Greece, Greece)
- An In-Memory Relevance Feedback Technique for High-Performance Image Retrieval Systems
- Ning Yu (University of Central Florida, USA); Khanh Vu (University of Central Florida, USA); Kien Hua (University of Central Florida, USA)
- Image Retrieval on Large-Scale Image Databases
- Eva Hoerster (Univeristy of Augsburg, Germany); Rainer Lienhart (Univ of Augsberg, Germany); Malcolm Slaney (Yahoo! Research, USA)
- Automatic Image Annotation By An Iterative Approach: Incorporating Keyword Correlations And Region Matching
- Xiangdong Zhou (University of Fudan, P.R. China); Mei Wang (University of Fudan, P.R. China); Qi Zhang (University of North Carolina at Chapel Hill, USA); JunQi Zhang (Fudan University, P.R. China); Baile Shi (Fudan University, P.R. China)
- Interpretability Based Interest Points Detection
- Ahmed Rebai (INRIA, France); Alexis Joly (INRIA, France); Nozha Boujemaa (INRIA, France)
12:00 PM - 1:30 PM
Lunch
1:30 PM - 3:10 PM
Oral Session
- VAST MM: Multimedia Browser for Presentation Video
- Alexander Haubold (Columbia University, USA); John Kender (Columbia U, USA)
- Automated Production of TV Program Trailer using Electronic Program Guide
- Yoshihiko Kawai (NHK, Japan); Hideki Sumiyoshi (Japan Broadcasting Corporation, Japan); Nobuyuki YAGI (NHK Science and Technical Research Laboratories, Japan)
- Video Parsing Based on Head Tracking and Face Recognition
- Pengxu Li (Tsinghua Univerisity, P.R. China); Haizhou Ai (Tsinghua University, P.R. China); Yuan Li (Tsinghua University, P.R. China); Chang Huang (Tsinghua University, P.R. China)
- Web Image Retrieval on ImagEVAL: Evidences on visualness and textualness concept dependency in fusion model
- Sabrina Tollari (Université du Sud Toulon-Var / LSIS, France); Hervé Glotin (Université du Sud Toulon-Var / LSIS, France)
- Online Video Recommendation Based on Multimodal Fusion and Relevance Feedback
- Bo Yang (Tsinghua University, P.R. China); Tao Mei (Microsoft Research Asia, P.R. China); Xian-Sheng Hua (Microsoft Research Asia, P.R. China); Linjun Yang (Microsoft Research Asia, P.R. China); Shi-Qiang Yang (Tsinghua University, P.R. China); Mingjing Li (Microsoft Research Asia, P.R. China)
3:10 PM - 3:25 PM
Coffee Break
3:10 PM - 4:40 PM
Demos
- SemanticVox: A multilingual video search engine
- Bertrand Delezoide (CEA, France); Herve Le Borgne (CEA, France)
- Shaping 3D Multimedia Environments: The Media Square
- Michael Dittenbach (E-Commerce Competence Center - EC3, Austria); Helmut Berger (E-Commerce Competence Center - EC3, Austria); Ronald Gensweider (E-Commerce Competence Center - EC3, Austria); Andreas Pesenhofer (E-Commerce Competence Center - EC3, Austria); Andreas Rauber (Vienna University of Technology, Austria); Thomas Lidy (Vienna University of Technology, Austria); Dieter Merkl (Vienna University of Technology, Austria)
- 3D-Model Search Engine from Photos
- Filali Ansary Tarik (University of Iille, France); Jean-Phillipe Vandeborre (University of Iille, France); Mohamed Daoudi (GET/INT, Telecom Lille1, LIFL (UMR USTL-CNRS 8022), France)
- RETIN: A Smart Interactive Digital Media Retrieval System
- Julien Gony (University of Paris, France); Matthieu Cord (University of Paris, France); Sylvie Philipp-Foliguet (University of Cergy, France); Philippe Gosselin (University of Paris, France); Frederic Precioso (ETIS Laboratory - ENSEA / UMR CNRS 8051, France); Michael Jordan (University of Cergy, France)
- Video and Image Copy Detection Demo
- Julien Law-To (INRIA Rocquencourt, France); Alexis Joly (INRIA, France); Laurent Joyeux (INRIA, France); Nozha Boujemaa (INRIA, France); Olivier Buisson (INA, France); Valerie Gouet (Conservatoire National des Arts et Metiers, France)
- Real-Time Object Tracking with Relevance Feedback
- Ard Oerlemans (Leiden University, The Netherlands); Joachim Rijsdam (Leiden University, The Netherlands); Michael Lew (Leiden University, The Netherlands)
- Flexible Test-bed for Unusual Behavior Detection
- István Petrás (Computer and Automation Research Institute, Hungarian Academy of Sciences, Hungary); Levente Kovács (Computer and Automation Research Institute, Hungarian Academy of Sciences, Hungary); Behcet Toreyin (Bilkent University, Turkey); Csaba Beleznai (ACV, Austria); Zoltan Szlavik (Mta-SZTAKI, Hungary); Ugur Gudukbay (Bilkent University, Turkey); Yigithan Dedeoglu (Bilkent University, Turkey); László Havasi (Peter Pazmany Catholic University, Hungary); Enis Cetin (Bilkent University, Ankara, Turkey); Montse Pardas (Technical University of Catalonia, Spain); Tamas Sziranyi (Computer and Automation Research Institute of the Hungarian Academy of Sciences, Hungary); Cristian Canton (Universitat Politecnica de Catalunya, Spain)
- ACADI Showcase - Automatic Character Indexing in Audiovisual Document
- Frederic Gianni (IRIT, France); Julien Pinquier (Universite Paul Sabatier - IRIT, France); Ewa Kijak (Université Pierre et Marie Curie, France)
- SemRetriev – An Ontology Driven Image Retrieval System
- Adrian Popescu (CEA/LIST-Lic2m, France); Pierre Alain Moellic (CEA, France); Christophe Millet (Commissariat , France)
- A New Intelligent Systems Approach to 3D Animation in Television
- Charles Prado (Globo TV Network, Brazil); Felipe France (Univ. Rio de Janeiro, Brazil); Eduardo Costa (Globo TV Network, Brazil); Luiz Vasconcelos (Globo TV Network, Brazil)
- Demonstration of Assembly Work Using Augmented Reality
- Tapio Salonen (VTT Information Technology, Finland); Juha Saaski (VTT Information Technology, Finland); Mika Hakkarainen (VTT Information Technology, Finland); Theofanis Kannetis (Technical University of Crete, Greece); Manolis Perakakis (Technical University of Crete, Greece); Sanni Siltanen (VTT Information Technology, Finland); Alexandros Potamianos (Technical University of Crete, Greece); Otto Korkalo (VTT Information Technology, Finland); Charles Woodward (VTT Information Technology, Finland)
- IBM Multimodal Interactive Video Threading
- Jelena Tesic (IBM Watson Research Center, USA); Apostol Natsev (IBM T. J. Watson Research Center, USA); Joachim Seidl (IBM Watson Research Center, USA); John Smith (IBM T.J. Watson Research Center, USA)
- Visual Information Retrieval Using Synthesized Imagery
- Bart Thomee (Leiden University, The Netherlands); Mark Huiskes (Centre for Mathematics and Computer Science, The Netherlands); Erwin Bakker (Leiden University, The Netherlands); Michael Lew (Leiden University, The Netherlands)
- Dynamic Texture Detection, Segmentation and Analysis
- Behcet Toreyin (Bilkent University, Turkey); Yigithan Dedeoglu (Bilkent University, Turkey); Enis Çetin (Bilkent University, Turkey); Sándor Fazekas (SZTAKI, Hungary); Dmitry Chetverikov (MTA SZTAKI, Hungary); Tomer Amiaz (Tel Aviv University, Israel); Nahum Kiryati (Tel Aviv University, Israel)
- Demonstration of Image Retrieval Based on Illumination Invariant Textural MRF Features
- Pavel Vácha (Institute of Information Theory and Automation, Czech Republic); Michal Haindl (Institute of Information Theory and Automation, Czech Republic)
- Object Categorisation with Color Interest Points
- Julian Stöttinger, Jaume Amores, Nicu Sebe, Allan Hanbury, Nozha Boujemaa, Theo Gevers
- Movie Summarization and Skimming Demonstrator
- Kostas Rapantzikos, Petros Maragos, Costas Kotropoulos, Patrick Gros, Alexandros Potamianos
- Content Analysis Showcase and Evaluation Web Portal (CASEWP)
- Andreas Rauber, Nicu Sebe, Philippe Joly, Thomas Lidy, Jakob Frank, Cees
Snoek, Thomas Foures, Costas Kotropoulos, Emmanouil Benetos, Bill
Christmas, Arie Yeredor
Posters
- Inducing a Perceptual Relevance Shape Classifier
- Victoria Hodge (University of York, UK, United Kingdom); John Eakins (University of York, UK, United Kingdom); Jim Austin (University of York, UK, United Kingdom)
- A Framework for Multimedia Content Abstraction and its Application to Rushes Exploration
- Werner Bailer (Joanneum Research, Austria); Georg Thallinger (JOANNEUM RESEARCH, Austria)
- Semi-Supervised Learning for Semantic Video Retrieval
- Ralph Ewerth (University of Marburg, Germany); Bernd Freisleben (University of Marburg, Germany)
- Near-Duplicate Keyframe Retrieval with Visual Keywords and Semantic Context
- Xiao Wu (City University of Hong Kong, Hong Kong); Wanlei Zhao (City University of Hong Kong, Hong Kong); Chong-Wah Ngo (City University of Hong Kong, Hong Kong)
- Image annotation : which approach for realistic databases ?
- Nicolas Hervé (INRIA, France); Nozha Boujemaa (INRIA, France)
- Classification of Video Events using 4-dimensional time-compressed Motion Features
- Alexander Haubold (Columbia University, USA); Milind Naphade (IBM T J Watson Research Center, USA)
- A Robust Scene Recognition System for Baseball Broadcast Using Data-Driven Approach
- Ryoichi Ando (Tokyo Institute of Technology, Japan); Koichi Shinoda (Tokyo Institute of Technology, Japan); Sadaoki Furui (Tokyo Institute of Technology, Japan); Takahiro Mochizuki (NHK, Japan)
- Fast and cheap object recognition by linear combination of views
- Jerome Revaud (INSA Lyon, France); Guillaume Lavoué (LIRIS UMR 5205, Insa-Lyon, France); Yasuo Ariki (Kobe University, Japan); Atilla Baskurt (INSA de Lyon, France)
- Ontology-supported Object and Event Extraction with a Genetic Algorithms Approach for Object Classification
- Yakup Yildirim (Middle East technical University, Turkey); Turgay Yilmaz (Middle East Technical University, Turkey); Adnan Yazici (Middle East Technical University, Turkey)
- Using Depth Features to Retrieve Monocular Video Shots
- Ralph Ewerth (University of Marburg, Germany); Martin Schwalb (University of Marburg, Germany); Bernd Freisleben (University of Marburg, Germany)
- Shape based 3D model retrieval without query
- Susumu Endo (Fujitsu Laboratories Ltd., Japan)
- Kernels on bags for multi-object database retrieval
- Philippe Gosselin (University of Paris, France); Matthieu Cord (University of Paris, France); Sylvie Philipp-Foliguet (University of Cergy, France)
- Whitened LDA for Face Recognition
- Nhat Vo (Kyung Hee University, Korea)
- Multi-level local descriptor quantization for Bag-of-Visterms image representation
- Pedro Quelhas (IDIAP Research Institute, Switzerland); Jean-Marc Odobez (IDIAP, Switzerland)
- Semantic Facets: An in-depth Analysis of a Semantic Image Retrieval System
- Jonathon Hare (University of Southampton, United Kingdom); Paul Lewis (University of Southampton, United Kingdom); Peter Enser (University of Brighton, United Kingdom); Christine Sandom (University of Brighton, United Kingdom)
- Soccer players identification based on visual local features
- Lamberto Ballan (University of Florence, Italy); Marco Bertini (Universitŕ di Firenze, Italy); Alberto Del Bimbo (University of Firenze, Italy); Walter Nunziati (University of Florence, Italy)
- The Value of Stories for Speech-Based Video Search
- Bouke Huurnink (University of Amsterdam, The Netherlands); Maarten de Rijke (University of Amsterdam, The Netherlands)
- Comparison of Face Matching Techniques under Pose Variation
- Bart Kroon (Delft University of Technology, The Netherlands); Alan Hanjalic (Delft University of Technology, The Netherlands); Sabri Boughorbel (Philips Research Eindhoven, The Netherlands)
- Canonical Image Selection from the Web
- Yushi Jing (Google, USA); Shumeet Baluja (Carnegie Mellon University, USA); Henry Rowley (Google, USA)
- Behavior monitoring through automatic analysis of video sequences
- Carlo Colombo (Universita' di Firenze, Italy); Dario Comanducci (DSI Florence, Italy); Alberto Del Bimbo (University of Firenze, Italy)
- Spatiotemporal Saliency for event detection and representation in the 3D Wavelet Domain: Potential in human action recognition
- Konstantinos Rapantzikos (National Technical University of Athens, Greece); Yannis Avrithis (National Technical University of Athens, Greece); Stefanos Kollias (NTUA, Greece)
- Enhancing HSV Histograms with Achromatic Points Detection for Video Retrieval
- Costantino Grana (University of Modena and Reggio Emilia, Italy); Roberto Vezzani (University of Modena, Italy); Rita Cucchiara (University of Modena and Reggio Emilia, Italy)
- Semantics Reinforcement and Fusion Learning for Multimedia Streams
- Dhiraj Joshi (The Pennsylvania State University, USA); Milind Naphade (IBM T J Watson Research Center, USA); Apostol Natsev (IBM T. J. Watson Research Center, USA)
- Network-aware identification of video clip fragments
- Jose San Pedro (University of Sheffield, United Kingdom); Sergio Dominguez (Universidad Politecnica de Madrid, Spain)
- TV Broadcast Macro-Segmentation: Metadata-Based vs. Content-Based Approaches
- Sid Ahmed Berrani (Orange Labs - France Telecom, France); Lechat Patrick (Orange Labs - France Telecom, France); Gaël Manson (Orange Labs - France Telecom, France)
- A Reranking Approach for Context-based Concept Fusion in Video Indexing and Retrieval
- Lyndon Kennedy (Columbia University, USA); Shih-Fu Chang (Dept. of E.E. , Columbia Univ., USA)
- Matching Ottoman Words: An Image Retrieval Approach to Historical Document Indexing
- Esra Ataer (Bilkent University, Turkey); Pinar Duygulu (Bilkent University, Turkey)
- Z-grid-based Probabilistic Retrieval for Scaling Up Content-Based Copy Detection
- Sebastian Poullot (CNAM, France); Michel Crucianu (INRIA, France); Olivier Buisson (INA, France)
- Appearance-based video clustering in 2D locality preserving projection subspace
- Li-Qun Xu (British Telecommunications PLC, United Kingdom); Bin Luo (Anhui University, P.R. China)
- A blob detector in color images
- Anlong Ming (Beijing Univ. of Posts and Telecommunications, P.R. China); Huadong Ma (Beijing University of Posts and Telecommunications, P.R. China)
- Video Copy Detection: a Comparative Study
- Julien Law-To (INRIA Rocquencourt, France); LI CHEN (University College London, United Kingdom); Alexis Joly (INRIA, France); Yvan Laptev (IRISA, France); Olivier Buisson (INA, France); Valerie Gouet (Conservatoire National des Arts et Metiers, France); Nozha Boujemaa (INRIA, France); Fred Stentiford (University College London, United Kingdom)
- Device parts retrieval from assembly drawings with SVM based active relevance feedback
- Rujie Liu (Fujitsu Research & Development Co., Ltd, P.R. China)
- Ontology Driven Content Based Image Retrieval
- Adrian Popescu (CEA/LIST-Lic2m, France); Christophe Millet (Commissariat , France); Pierre Alain Moellic (CEA, France)
- Distributing Expressional Faces in 2-D Emotional Space
- Yangzhou Du (Intel China Research Center, P.R. China); Tao Wang (Intel China Research Center, P.R. China); Haizhou Ai (Tsinghua University, P.R. China)
- Representing shape with a spatial pyramid kernel
- Anna Bosch (University of Girona, Spain); Andrew Zisserman (University of Oxford, United Kingdom); Xavier Muńoz (University of Girona, Spain)
- The Use of Temporal, Semantic and Visual Partitioning Model for Efficient Near-Duplicate Keyframe Detection in Large Scale News Corpus
- Yan-Tao Zheng (National University of Singapore, Singapore); Shi-Yong Neo (National University of Singapore, Singapore); Tat-Seng Chua (National University of Singapore, Singapore); Qi Tian (Institute for Infocomm Research, Singapore)
- Multiple Temporal Texture Detection Using Feature Space Mapping
- Ashfaqur Rahman (Monash University, Australia); Manzur Murshed (Monash University, Australia)
- Refining Image Annotation Using Contextual Relations Between Words
- Yong Wang (Queen Mary, Univ. of London, United Kingdom); Shaogang Gong (Queen Mary, Univ. of London, United Kingdom)
- Analysis of Vector Space Model and Spatiotemporal Segmentation for Video Indexing and Retrieval
- Eric Galmar (Institut Eurecom, France); Benoit Huet (Institut Eurecom, France)
- Cast Indexing for Videos by NCuts and Page Ranking
- Yong Gao (Intel China research center, P.R. China); Tao Wang (Intel China Research Center, P.R. China); Yangzhou Du (Intel China Research Center, P.R. China)
- Image Retrieval Measures Based on Illumination Invariant Textural MRF Features
- Pavel Vácha (Institute of Information Theory and Automation, Czech Republic); Michal Haindl (Institute of Information Theory and Automation, Czech Republic)
- A Nearest-Neighbor Approach to Relevance Feedback in Content Based Image Retrieval
- Giorgio Giacinto (University of Cagliari, Italy)
- An Empirical Study of Inter-Concept Similarities in Multimedia Ontologies
- Markus Koskela (Helsinki University of Technology, Finland); Alan Smeaton (Dublin City University, Ireland)
- User-Adaptive Home Video Summarization using Personal Photo Libraries
- Yuichiro Takeuchi (The University of Tokyo, Japan); Masanori Sugimoto (The University of Tokyo, Japan)
- 3D Model Representation Using Adaptive Volumetric Extended Gaussian Image
- Jiqi Zhang (City University of Hong Kong, Hong Kong); Ding wen Wang (Wuhan University, P.R. China); Hau San Wong (City University of Hong Kong, Hong Kong)
- Merging Storyboard Strategies and Automatic Retrieval for Improving Interactive Video Search
- Michael Christel (Carnegie Mellon University, USA); Rong Yan (IBM TJ Watson Research Center, USA)
- Towards Optimal Bag-of-Features for Object Categorization and Semantic Video Retrieval
- Yu-Gang Jiang (City University of Hong Kong, Hong Kong); Chong-Wah Ngo (City University of Hong Kong, Hong Kong); Jun Yang (Carnegie Mellon University, USA)
- Texture Retrieval based on a Non-parametric Measure for Multivariate Distributions
- Vasileios Pothos (University of Patras, Greece); Christos Theoharatos (University of Patras, Greece); George Economou (University of Patras, Greece); Apostolos Ifantis (Technological Institute of Patras, Greece)
- Associating Characters with Events in Films
- Andrew Salway (Burton Bradstock Research Labs, United Kingdom); Bart Lehane (Dublin City University, Ireland); Noel O'Connor (Dublin City University, Ireland)
4:40 PM - 6:00 PM
Special Session on Trademark Image Retrieval
- Practice and Challenges in Trademark Image Retrieval
- Jan Schietse (AKTOR Knowledge Technology, Belgium); John Eakins (University of York, UK, United Kingdom); Remco C. Veltkamp (Utrecht University, The Netherlands)
- Layout Indexing of Trademark Images
- Reinier van Leuken (Utrecht University, The Netherlands); Fatih Demirci (Utrecht University, The Netherlands); Victoria Hodge (University of York, UK, United Kingdom); Jim Austin (University of York, UK, United Kingdom); Remco C. Veltkamp (Utrecht University, The Netherlands)
- Probabilistic Matching and Resemblance Evaluation of Shapes in Trademark Images
- Helmut Alt (Freie Universitat Berlin, Germany); Ludmila Scharf (Freie Universität Berlin, Germany); Sven Scholz (Freie Univerität Berlin, Germany)
- Searching for Logo and Trademark Images on the Web
- Euripides Petrakis (Technical University of Crete (TUC), Greece); Epimenides Voutsakis (Technical University of Crete (TUC), Greece); Evangelos Milios (Dalhousie University, Canada)
6:00 PM - 7:30 PM
Reception
| |