RSS feed

Preliminary program

Wednesday, 23 June 2010

08:30 - 09:00 Registration, opening
09:00 - 10:00 Invited keynote talk Indexing Video Archives Using Latent Link Analysis, Shin'ichi Satoh, NII.
10:00 - 10:30 Coffee Break
10:30 - 12:30 Oral Session 1: Multimedia Learning - Fast shared boosting: application to large-scale visual concept detection, Hervé Le Borgne and Nicolas Honnorat.
- A Fast Algorithm for Music Search by Similarity in Large Databases based on Modified Symetrized Kullback Leibler Divergence, Christophe Charbuillet, Geoffroy Peeters, Stanislav Barton and Valerie Gouet-Brunet.
- Active Learning with Multiple Classifiers for Multimedia Indexing, Bahjat SAFADI and Georges Quénot.
- A kernel-based active learning strategy for content-based image retrieval, Imane Daoudi and Khalid idrissi.
12:30 - 14:00 Lunch Break
14:00 - 15:00 Poster Session - Integration of Spatial Relationship in Visual Language Model for Scene Retrieval, Trong Ton Pham, Philippe Mulhem, Loïc aisonnasse, Eric Gaussier and Ali Ait-Bachir.
- Multi-Video Summarization Based on AV-MMR, Yingbo Li and Bernard Mérialdo.
- Users' Response to Affective Film Content: a Narrative Perspective, Luca Canini, Steve Gilroy, Marc Cavazza, Riccardo Leonardi and Sergio Benini.
- Physics Based 3D Ball Tracking for Tennis Videos, Antoine Poliakov, Denis Marraud, Livier Reithler and Chatain Christophe.
- Squeezing Bag-of-Features for Scalable and Semantic 3D Model Retrieval, Ryutarou Ohbuchi, Masaki Tezuka, Takahiko Furuya and Takashi Oyobe.
- Visual Object Tracking Based on Incremental Kernel PCA, Li Sun and Guizhong Liu.
- Learning from Essential Facial Parts and Local Features for Automatic Facial Expression Recognition, YI JI and Khalid Idrissi.
- A Kernel-Based Strategy for Exploratory Image Collection Search, Jorge Camargo, Juan Caicedo, Anyela Chavarro and Fabio Gonzalez.
15:00 - 15:30 Coffee Break
15:30 - 17:30 Oral Session 2: Multimedia Applications - CRIM's Content-based Audio Copy Detection System for TRECVID-2009, Vshwa Gupta, Gilles Boulianne and Patrick Cardinal.
- Shopping scenarios semantic analysis in videos, Ronan Sicre and Henri Nicolasa.
- Classification of affective semantics in images based on discrete and dimensional models of emotions, Emmanuel Dellandrea, Ningning Liu and Liming Chen.
- Automatic Tag Generation for Photos Using Contextual Information and Description Logics, Joakim Söderberg and Eirini Kakogianni.

Thursday, 24 June 2010

09:00 - 10:00 Invited keynote talk Automatic Construction of Multimedia Summaries, Bernard Mérialdo, Eurecom
10:00 - 10:30 Coffee Break
10:30 - 12:00 Special Session: GDR-ISIS - Semi-Supervised Learning for Location Recognition from Wearable Video, Vladislavs Dovgalecs, Rémi Megret, Hazem Wannous and Yannick Berthoumieu..
- From Descriptor to Boosting: Optimizing the k-NN Classification Rule, Bel Haj Ali Wafa, Piro Paolo, Debreuve Eric and Barlaud Michel.
- Fusion of tf.idf weighted bag of visual features for image classification, Christophe Moulin, Cécile Barat, Christophe Ducottet.
12:00 - 13:30 Lunch Break
13:30 - 15:00 Demonstrations - Image Based Information Access for Mobile Phones, Xi Chen, Markus Koskela, Jouko Hyväkkä.
- MM: modular architecture for multimedia information retrieval, Bertrand Delezoide, Hervé Le Borgne, Romaric Besançon Gaël De Chalendar, Olivier Ferret, Faïza Gara, Patrick Hède, Meriama Laib, Olivier Mesnard, Pierre-Alain Moëllic, Nasredine Semmar.
- VERGE: A Video Interactive Retrieval Engine, Stefanos Vrochidis, Anastasia Moumtzidou, Paul King, Anastasios Dimou, Vasileios Mezaris, Ioannis Kompatsiaris.
- Evaluation of Video Summaries, Yingbo Li, Bernard Merialdo.
- NewsClipping: An Automatic Multimedia News Clipping Application, J.Gregorio Escalada, Helenca Duxans, David Conejero, Albert Asensio, David Salinas.
- INVENIO: An MPEG-7 image indexing platform for content re-use within audio-visual production chains, Titus Zaharia, Alain Vaucelle, Thomas Laquet, Françoise Prêteux.
- OVIDIUS: An on-line video retrieval platform for multi-terminal access, Andrei Bursuc, Titus Zaharia, Bertrand Delezoide, Françoise Prêteux.
- The LIGVID System for Video Retrieval and Concept Annotation, Stéphane Ayache, Georges Quénot, Andy Tseng.
15:00 - 15:30 Coffee Break
15:30 - 17:00 Chorus Panel Content-based multimedia search: what about large scale challenges? Nozha Boujemaa, INRIA
Panelists: Shin'ichi Satoh, Allan Hanbury and Benoît Huet
17:30 - 19:30 Grenoble city tour
20:00 Dinner

Friday, 25 June 2010

09:00 - 11:00 Oral Session 3: Multimedia Representation - A New Spatial Weighting Scheme for Bag-of-Visual-Words, Ismail El sayad, Jean Martinet, Thierry Urruty and Chabane Djeraba.
- Adaptive Hierarchical Density Histogram for Complex Binary Image Retrieval, Panagiotis Sidiropoulos, Stefanos Vrochidis and Ioannis Kompatsiaris.
- Visual Phrases for automatic images annotation, Rami Albatal, Philippe Mulhem and Yves Chiaramella.
- A Multi-Object Particle Filter Tracking with a Dual Consistency Check: Application to Mid-Level Concept Detection in Videos, Yifan Zhou, Boris Mansencal and Jenny Benois-Pineau.
11:00 - 11:30 Coffee Break
11h30 - 12h30 Invited keynote talk Spoken language processing for indexing multimedia documents , Jean-Luc Gauvain, LIMSI
12:30 - 14:00 Lunch Break
14:00 - 16:00 Oral session 4: Human-Centered Multimedia - Talking Faces Indexing in TV-Content, Bendris Meriem, Charlet Delphine and Chollet Gérard.
- Exploiting speaker segmentations for automatic role detection. An application to broadcast news documents, Benjamin Bigot, Isabelle Ferrané and Julien Pinquier.
- Capturing User Behavior in Multimedia Recommenders, Massimiliano Albanese, Antonio d'Acierno, Vincenzo Moscato and Antonio Picariello.
- Interactive person re-identification in TV series, Mika Fischer, Hazum Kemal Ekenel and Rainer Stiefelhagen.
16:00 Closing