Conference program

A general outline of the conference program is shown below. The full version of the program can be found directly below the abbreviated version.

Abbreviated Program

May 6, 2009

9:1510:15Keynote Presentation: Andrew Zisserman
10:3012:10Oral Session 1: Face and Gestures
13:3015:35Special Session 1: People, Pixels, Peers; Interactive Content in Social Networks
15:5017:30Oral Session 2: Motion Analysis

May 7, 2009

9:0010:00 Keynote Presentation: Fernando Pereira, Video Compression: Still Evolution or Time for Revolution?
10:0010:15 Coffee
10:1512:20 Special Session 2: Automated Information Extraction in Media Production (AIEMPro09)
12:2013:40 Lunch
13:4015:40 Poster Session and Coffee
15:4017:45 Oral Session 3: Content-based Retrieval
19:00... Social Event

May 8, 2009

9:0010:15 Oral Session 4: 3D Analysis
10:1510:30 Coffee
10:3012:10 Special Session 3: Affective Interaction in Natural Environments
12:1013:20 Lunch
13:2015:00 Special Session 4: Event, Behaviour Video Analysis for Interactive Multimedia Services
15:0015:20 Coffee
15:2017:25 Oral Session 5: Applications

Full Program

May 6, 2009

9:00 - 9:15


9:15 - 10:15

Keynote presentation: Andrew Zisserman, Human Pose Estimation and Retrieval in Videos

Andrew Zisserman

Determining the pose and activities of humans is one of the central problems of image and video analysis. The visual problem is challenging because humans are articulated animals, wear loose and varying clothing, self-occlude themselves, and stand against difficult and confusing backgrounds. Nevertheless, the area has seen great progress over the last decade due to advances in modelling and in the efficiency of algorithms.

We describe here recent progress in determining human 2D upper body pose in TV videos and films. The pose specifies the spatial layout of head, torso, upper and lower arms and hands. A standard approach to this problem is to learn a pictorial structure model and fit it to the video frames. We will describe two variations on this approach which differ in their level of supervision and the strength of the applied model. The first model requires explicit supervision, but is then able to track human pose through hour long videos. The second model is weaker (it is tree structured and there is no occlusion modelling), but requires no supervision.

We show results of these models on various TV videos and feature films, and applications of the estimated pose to (i) learning the gestures of sign language, and (ii) to pose based video retrieval.

This is joint work with Patrick Buehler, Mark Everingham, Vitto Ferrari, Daniel Huttenlocher and Manuel Marin-Jimenez

10:15 - 10:30


10:30 - 12:10

Oral Session 1: Face and Gestures

  • Iordanis Mpiperis, Sotiris Malassiotis and Michael Strintzis

    Bilinear Decomposition of 3-D Face Images: An Application to Facial Expression Recognition
  • Manuel J. Marín-Jiménez, Nicolás Pérez de la Blanca, Maria Angeles Mendoza, Manuel Lucena and Jose Manuel Fuertes.

    Learning Action Descriptors for Recognition
  • Veronica Vilaplana and David Varas

    Face tracking using a region-based mean-shift algorithm with adaptive object and background models
  • Feifei Huo, Emile Hendriks, Pavel Paclik and A.H.J. Oomes

    Markerless Human Motion Capture and Pose Recognition
Back to top

12:10 - 13:30


13:30 - 15:35

Special session 1: People, Pixels, Peers; Interactive Content in Social Networks


  • Martha Larson, Delft University of Technology, Netherlands
  • Kai Clüver, Technische Universität Berlin, Germany
  • Naeem Ramzan, Queen Mary, University of London, United Kingdom
  • Frederic Dufaux, Ecole Polytechnique Fédérale de Lausanne, Switzerland

Session Papers

  • Stevan Rudinac, Martha Larson and Alan Hanjalic

    Exploiting Visual Reranking to Improve Pseudo-Relevance Feedback for Spoken-Content-Based Video Retrieval
  • zhijie zhao, Joern Ostermann and Hexin Chen

    Multiple Description Scalable Coding for Video Streaming
  • Pascal Kelm, Sebastian Schmiedeke and Thomas Sikora

    Feature-based Video Key Frame Extraction for Low Quality Video Sequences
  • Stephane Marchand-Maillet, Eniko Szekely and Eric Bruno

    Optimizing Strategies for the Exploration of Social Networks and Associated Data Collections
  • Giuseppe Passino, Ioannis Patras and Ebroul Izquierdo

    Context Awareness in Graph-based Image Semantic Segmentation via Visual Word Distributions
Back to top

15:35 - 15:50


15:50 - 17:30

Oral session 2: Motion Analysis

  • Stergios Poularakis, Alexia Briassouli and Ioannis Kompatsiaris

    Full Action Instances for Motion Analysis
  • Luca Superiori and Markus Rupp

    Detection of Pan and Zoom in Soccer Sequences Based on H.264/AVC Motion Information
  • Yue-Meng Chen, Ivan Bajic and Parvaneh Saeedi

    Coarse-to-fine Moving Region Segmentation in Compressed Video
  • Martin Haller, Andreas Krutz and Thomas Sikora

    Evaluation of pixel- and motion vector-based Global Motion Estimation for camera motion characterization
Back to top

19:00 - 21:00


May 7, 2009

9:00 - 10:00

Keynote presentation: Fernando Pereira, Video Compression: Still Evolution or Time for Revolution?

Video compression has been steadily evolving in the past 20 years with significant developments in the technology, major compression gains, impressive deployment of services and applications, and an amazing overall impact on our society. Until recently, the 'video compression adventure' has been providing around 50% compression gains every 5 years which led to the set of video coding standards nowadays available. This set of standards resulted from a rather smooth technological evolution, with the same predictive coding architecture being successively enriched with new tools to provide higher compression factors, typically also at the cost of a higher encoding complexity.

However, something seems to have changed recently since, after the development of the very successful H.264/AVC standard, further compression gains have been short and more difficult to reach than usual. This fact led many video coding research experts to announce the end of the predictive video coding saga as known from the past two decades.

In this context, this talk will precisely discuss the future of video compression considering the emerging industry needs, notably in terms of 3D video and ultra high resolutions, promising technological novelties, and recent standardization initiatives. With MPEG and VCEG, the two main video coding standardization players running to announce new initiatives - High-Efficiency Video Coding (HVC) from MPEG and Next Generation Video Coding (NGVC) from VCEG - it is time to carefully analyze the possible ways to go forward in video compression and answer the big question: Is it still possible to extend the predictive video coding saga to get further significant compression gains or is it finally time for a revolution in terms of video coding concepts, architectures and tools ?


Fernando Pereira

Fernando Pereira is currently with the Electrical and Computers Engineering Department of Instituto Superior Técnico (IST) and with Instituto de Telecomunicaçõ, both in Lisbon, Portugal. He is responsible for the participation of IST in many national and international research projects. He acts often as project evaluator and auditor for various organizations. He is an Area Editor of the Signal Processing: Image Communication Journal, a member of the Editorial Board of the Signal Processing Magazine, and is or has been an Associate Editor of IEEE Transactions of Circuits and Systems for Video Technology, IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, and IEEE Signal Processing Magazine. He is a member of the IEEE Signal Processing Society Technical Committees on Image, Video and Multidimensional Signal Processing, and Multimedia Signal Processing, and of the IEEE Circuits and Systems Society Technical Committees on Visual Signal Processing and Communications, and Multimedia Systems and Applications. He was an IEEE Distinguished Lecturer in 2005 and an IEEE Fellow in 2008. He has been a member of the Scientific and Program Committees of many international conferences and has contributed more than 200 papers. He has been participating in the work of ISO/MPEG for many years, notably as the head of the Portuguese delegation, Chairman of the MPEG Requirements Group, and chairing many Ad Hoc Groups related to the MPEG-4 and MPEG-7 standards. His areas of interest are video analysis, processing, coding and description, and interactive multimedia services.

10:00 - 10:15


10:15 - 12:20

Special session 2: Automated Information Extraction in Media Production (AIEMPro09)

Session Organizers

  • Alberto Messina, Centre for Research and Technological Innovation, RAI Radiotelevisione Italiana, Italy
  • Jean-Pierre Evain, European Broadcasting Union, Switzerland
  • Robbie De Sutter, VRT-medialab, Belgium

Session Papers

  • Werner Bailer and Georg Thallinger

    Summarizing Raw Video Material Using Hidden Markov Models
  • Antonio d'Acierno, Antonio Picariello and Vincenzo Moscato

    Building Summaries from WEB Information Sources
  • Erik Mannens, Raphael Troncy, Karel Braeckman, Davy Van Deursen, Wim Van Lancker, Robbie De Sutter and Rik Van de Walle

    Automatic Metadata Enrichment in News Production
  • Maurizio Montagnuolo, Marco Ferri and Alberto Messina

    Context-Aware Graph-Based Content Representation for Semantic Navigation in Multimedia News Archives
  • Roberto Basili, Diego De Cao and Riccardo Petitti

    Automatic Multimedia Annotation through Kernel Combinations
Back to top

12:20 - 13:40


13:40 - 15:40

Coffee and Poster Session

  • Anna Carreras, Maria Teresa Andrade, Tim Masterton, Hemantha Kodikara Arachchi, Vitor Barbosa, Safak Dogan, Jaime Delgado and Ahmet Kondoz

    Contextual Information in Virtual Collaboration System beyond Current Standards
  • Krishna Chandramouli and Ebroul Izquierdo

    Multi-Class Relevance Feedback for Collaborative Image Retrieval
  • Gokce Nur, Hemantha Kodikara Arachchi, Safak Dogan and Ahmet M. Kondoz

    Evaluation of Quality Scalability Layer Selection for Bit Rate Adaptation of Scalable Video Content
  • Fernando López, Jose M. Martinez and Narciso García

    Automatic adaptation decision making using an image to video adaptation tool in the MPEG-21 framework
  • Maryse Stoufs, Adrian Munteanu, Joeri Barbarien, Jan Cornelis and Peter Schelkens

    Optimized Scalable Multiple-Description Coding and FEC-based Joint Source-Channel Coding: A Performance Comparison
  • Mengxin Song, Xinyu Chen and Ping Guo

    A Fusion Method for Multispectral and Panchromatic Images Based on HSI and Contourlet Transformation
  • Fan Chen and Christophe De Vleeschouwer

    Autonomous Production of Basketball Videos from Multi-sensored Data with Personalized Viewpoints
  • Maria Angeles Mendoza, Nicolas Perez de la Blanca and Manuel J. Marín-Jiménez.

    PoHMM-based Human Action Recognition
  • Peter Lambert, Pedro Debevere, Stefaan Moens, Jean-François Macq and Rik Van de Walle.

    Optimizing IPTV video delivery using SVC spatial scalability
  • Nikos Deligiannis, Adrian Munteanu, Tom Clerckx, Jan Cornelis and Peter Schelkens

    Correlation Channel Estimation in Pixel-Domain Distributed Video Coding
  • Jeffrey Boyd

    Motion-Swarm Widgets for Video Interaction
  • Yu Zhou, Melvyn Smith, Lyndon Smith and Rob Warr

    Segmentation of Clinical Lesion Images Using Graphical Model
  • Keyu Tan and Alan Pearmain

    A low complexity and efficient slice grouping method for H.264/AVC in error prone environment
  • Yifan Zhou, Jenny Benois-Pineau and Henri Nicolas

    Multi-resolution Tracking of a Non-rigid Target with Particle Filters for Low and Variable Frame-rate Videos
  • Xia Mao, YuLi Xue, Zheng Li, Kang Huang and ShanWei Lv

    Robust Facial Expression Recognition Based on RPCA and AdaBoost
  • Ashish Doshi and Adrian Bors

    Anisotropic Fluid Solver for Robust Optical Flow Smoothing
  • Eleftherios Chrysochos, Eleni Varsaki, Vassilis Fotopoulos and Athanassios Skodras

    High Capacity Reversible Data Hiding using Overlapping Difference Expansion
  • Mohammad Izadi and Parvaneh Saeedi

    Height Estimation for Buildings in Monocular Satellite/Airborne Images based on Fuzzy Reasoning and Genetic Algorithm
  • Chris Poppe, Sarah De Bruyne, Peter Lambert and Rik Van de Walle

    Effect of H.264/AVC Compression on Object Detection for Video
  • Vitor Barbosa and Maria Teresa Andrade

    MULTICAO: A Semantic Approach to Context-aware Adaptation Decision Taking
  • David Santos and Paulo Correia

    Car Recognition Based on Back Lights and Rear View Features
  • Yangyu Tao, Lin Liang and Yingqing Xu

    Robust Satellite Image Analysis Using Probabilistic Learning based Graph Optimization
  • José Ignacio Gómez Espínola, Manuel Jesús Marín Jiménez and Nicolás Pérez de la Blanca Capilla.

    Probabilistic Graphical Models for Human Motion Tracking
  • I Gede Pasek Suta Wijaya, Keiichi Uchimura and Zhencheng Hu

    Why the Alternative PCA Provides Better Performance for Face Recognition
  • Antonio Rama, Francesc Tarres and Aureli Soria-Frisch

    Cascade Scheme Face Detection using a Non-linear Classifier
  • Yingdong Ma, Stewart Worrall and Ahmet Kondoz

    Depth Assisted Visual Tracking
  • Georgios Th. Papadopoulos, Carsten Saathoff, Marcin Grzegorzek, Vasileios Mezaris, Ioannis Kompatsiaris, Steffen Staab and Michael G. Strintzis

    Comparative Evaluation of Spatial Context Techniques for Semantic Image Analysis
  • Farhan Riaz, Mário Dinis-Ribeiro and Miguel Coimbra.

    Semantic Relevance of Current Image Segmentation Algorithms
  • Stijn Vandamme, Johannes Deleu, Tim Wauters, Brecht Vermeulen and Filip De Turck

    CROEQS: Contemporaneous Role Ontology-based Expanded Query Search - Analysis of the Result Set Size
  • Marina Georgia Arvanitidou, Alexander Glantz, Andreas krutz, Thomas Sikora, Marta Mrak and Ahmet Kondoz

    Global Motion Estimation Using Variable Block Sizes and its Application to Object Segmentation
  • Yanpeng Cao and John McDonald

    Self-organisation of Images from A Moving Camera
  • Gael Manson and Sid-Ahmed Berrani

    Repetition Density-Based Approach For TV Program Extraction
  • Gaurav Gupta, Alexandra Psarrou and Anastassia Angelopoulou

    Generic Colour Image Segmentation Via Multi-stage Region Merging
  • Martin Köppel, Dimitar Doshkov and Patrick Ndjiki-Nya

    Fully Automatic Inpainting Method for Complex Image Content
  • Mario Cordeiro and Cristina Ribeiro

    Reuse of Video Annotations Based on Low-Level Descriptor Similarity
  • Xiaodong Cai, Falah Ali and Elias Stipidis

    Background Modeling for Detecting Move-then-stop Arbitrary-long Time Video Objects
  • Seunghan Han, Andreas Hutter and Walter Stechele

    Toward Contextual Forensic Retrieval for Visual Surveillance: Challenges and an Architectural Approach
  • Qian Lin, Tong Zhang, Mei Chen, Yining Deng and Brian Atkins

    Video analysis for browsing and printing
Back to top

15:40 - 17:45

Oral session 3: Content-based Retrieval

  • Rachid Benmokhtar and Benoit Huet

    Ontological Reranking Approach for Hybrid Concept Similarity-based Video Shots Indexation
  • Spiros Nikolopoulos, Elisavet Chatzilari, Eirini Giannakidou and Ioannis Kompatsiaris

    Towards Fully Un-supervised Methods for Generating Object Detection Classifiers using Social Data
  • Eliana Rossi, Sergio Benini, Riccardo Leonardi, Boris Mansencal and Jenny Benois-Pineau

    Clustering of scene repeats for essential rushes preview
  • Luca Piras and Giorgio Giacinto

    Neighborhood-Based Feature Weighting for Relevance Feedback in Content-Based Retrieval
  • Sander Koelstra and Ioannis Patras

    The FAST-3D spatio-temporal interest region detector
Back to top

19:00 - ...

Social Event

May 8, 2009

9:00 - 10:15

Oral session 4: 3D Analysis

  • Qizhen He, Jun Feng and Horace Ip

    3D Object Retrieval based on Visual Keywords using Relative Angle Context Distribution
  • Gloria Haro and Montse Pardàs.

    3D shape from multi-camera view by error projection minimization
  • Peter Vajda, Frederic Dufaux, Thien Ha Minh and Touradj Ebrahimi

    Graph-Based Approach for 3D Object Duplicate Detection
Back to top

10:15 - 10:30


10:30 - 12:10

Special session 3: Affective Interaction in Natural Environments; Real-time affect analysis and interpretation in everyday settings

Session Organizers

  • Ginevra Castellano
  • Kostas Karpouzis
  • Christopher Peters
  • Jean-Claude Martin

Session Papers

  • Ginevra Castellano and Peter W. McOwan

    Analysis of Affective Cues in Human-Robot Interaction: a Multi-Level Approach
  • Jean-Claude Martin

    Posture Annotation for Studying Affective Interaction in Multimodal Corpora
  • Christopher Peters, Stylianos Asteriadis and Genaro Rebolledo-Mendez

    Modelling User Attention for Human-Agent Interaction
  • George Caridakis, Kostas Karpouzis, Nasos Drosopoulos and Stefanos Kollias

    Adaptive gesture recognition in Human Computer Interaction
Back to top

12:10 - 13:20


13:20 - 15:00

Special session 4: Event, Behaviour Video Analysis for Interactive Multimedia Services

Session Organizers

  • Nikolaos Doulamis, National Technical University of Athens, Greece
  • Paul Moore, ATOS Origin
  • Charalampos Patrikakis, National Technical University of Athens, Greece
  • Nikolaos Chr. Papaoulakis, National Technical University of Athens, Greece

Session Papers

  • Stefan Poslad, Aristodemos Pnevmatikakis, Mario Nunes, Elena Garrido Ostermann, Paul Chippendale, Peter Brightwell, Charalampos Patrikakis

    Directing Your Own Live and Interactive Sports Channel
  • Nikos Katsarakis and Aristodemos Pnevmatikakis

    Event Detection in Athletics for Personalized Sports Content Delivery
  • Vassilios Anagnastopoulos, Nikolaos Doulamis and Anastasios Doulamis

    Edge-motion Video Summarization: Economical Video Summarization for Low Powered Devices
  • Nuria Sánchez and José Manuel Menéndez García

    Video Analysis Architecture for Enhancing Pedestrian and Driver Safety in Public Environments
Back to top

15:00 - 15:20


15:20 - 17:25

Oral session 5: Applications

  • Xiaosong Wang and Majid Mirmehdi

    Archive Film Defect Detection based on a Hidden Markov Model
  • Dieter Van Rijsselbergen, Barbara Van De Keer, Maarten Verwaest, Erik Mannens and Rik Van de Walle

    Enabling Universal Media Experiences through Semantic Adaptation in the Creative Drama Production Workflow
  • Shan Jin, Hemant Misra, Thomas Sikora and Joemon Jose

    Automatic Topic Detection Strategy for Information Retrieval in Spoken
  • Benoit Pellan and Cyril Concolato

    Summarization of Scalable Multimedia Documents
  • Timothy Brick, Jeffrey Spies, Barry-John Theobald, Iain Matthews and Steven Boker

    High-Presence, Low-Bandwidth, Apparent 3D Video-conferencing With A Single Camera
Back to top