Call for Papers Camera-ready Submission Committees Workshop Program Registration Travel and Accommodation

PDF VERSION (english and french)

A video projector and a computer are available for the speakers to use. Before oral sessions, every speaker should copy his presentation on this computer.

Un vidéo projecteur et un ordinateur PC sont mis à disposition des orateurs pour la présentation de leur exposé dans l'amphitheâthre du LABRI. Avant les sessions orales, chaque orateur aura pris le soin pour copier sa présentation sur cet ordinateur commun.

Monday 25 June 2007

08:00 Registration is open

08:45-09:00: Opening

09:00-10:00: SESSION D1amIN: MUSCLE Invited Talk

Bj�rn ��r J�nsson, Hervig Lejsek (Reykjav�k University, Iceland), Laurent Amsaleg (IRISA/CNRS, France): The eff2 project: towards efficient and effective support for large-scale high-dimensional indexing.

Chair: Patrick Bouthemy (IRISA/INRIA, France)

10:00-12:30 SESSION D1amSS1: MUSCLE Special Session

Chair: Patrick Bouthemy, Ivan Laptev (IRISA/INRIA, France)

10:00-10:20: An assessment of alternative strategies for constructing EMD-based kernel functions for use in an SVM for image classification. Anton Zamolotskikh , Padraig Cunningham.

10:20-10:40: The analysis of saliency processes and its application to grouping cues design. Roman Golubchyck, Michael Lindenbaum.

10:40-11:00: Dynamic texture recognition using optical flow features and temporal periodicity. Sandor Fazekas, Dmitry Chetverikov.

11:00-11:30: Coffee

11:30-11:50: Representation and recognition of agent interactions using marking analysis in generalized stochastic Petri nets. Artyom Borzin, Ehud Rivlin, Michael Rudzsky.

11:50-12:10: Integration of structural and semantic models for multimedia metadata management. Suzanne Little, Massimo Martinelli, Ovidio Salvetti, Ugur Gudukbay, Ozgur Ulusoy, Gael de Chalendar, Gregory Grefenstette.

12:10-12:30: Opportunistic sensing and learning in sensor networks.

Romain Tavenard, Onkar Ambekar, Eric Pauwels, Max Waaijers.

12:30-14:00: Lunch

14:00-15:40: SESSION D1pmOR1: Oral Session 1

Chair: R�gine Andr�-Obrecht (IRIT, France)

14:00-14:20: Large-scale study of chord estimation algorithms based on chroma representation and HMM. Helene Papadopoulos, Geoffroy Peeters.

14:20-14:40: Polyphonic music retrieval by local edition of quotiented sequences. Pierre Hanna, Pascal Ferraro.

14:40-15:00: Robust multi-feature segmentation and indexing for natural sound Environments. Gordon Wichern, Harvey Thornburg, Brandon Mechtley, Alex Fink, Kai Tu, Andreas Spanias.

15:00-15:20: Fast hierarchical multimodal structuring of time slots. Jean-Philippe Poli, J�r�my Philippeau, Julien Pinquier, Jean Carrive.

15:20-15:40: Classifying computer generated charts. V. Shiv Naga Prasad, Behjat Siddiquie, Jennifer Golbeck, Larry Davis.

15:40-16:00 Coffee

16:00-17:30: SESSION D1pmSS2: CHORUS Panel

Panel presentation and discussion.

Chair: Nozha Boujemaa (INRIA, France).


Tuesday 26 June

09:00-10:00: SESSION D2amIN: Invited Talk

Jean Carrive, (INA, France): Document description for audiovisual archiving, corpora, technologies and uses.

Chair: Ebroul Izquierdo (QMUL, England).

10:00-12:30: SESSION D2amSS3: COST292-KSpace Special Session

Chair: Ebroul Izquierdo (QMUL, England).

10:00-10:20: Robust video retrieval with luminance field trace indexing and geometry matching. Li Gao, Zhu Li, Aggelos K. Katsaggelos.
10:20-10:40: Adaptive salient block based image retrieval in multi-feature space.

Qianni Zhang, Ebroul Izquierdo

10:40-11:00: Inexpensive fusion methods for enhancing feature detection. Peter Wilkins, Tomasz Adamek, Noel E. O�Connor, Alan F. Smeaton.

11:00-11:30: Coffee

11:30-11:50: Content-driven adaptation of on-line video. Jesus Bescos, Jos� M. Martinez, Luis Herranz, Fabricio Tiburzi.

11:50-12:10: The ARGOS campaing: evaluation of video analysis tools. Philippe Joly, Jenny Benois-Pineau, Ewa Kijak, Georges Qu�not.

12:10-12:30: Overview of JPSearch: a standard for image search and retrieval. Fr�d�ric Dufaux, Michael Ansorge, Touradj Ebrahimi

12:30-14:00: Lunch

14:00-15:00: SESSION D2pmOR2: Oral Session 2

Chair: Ferran Marqu�s (UPC, Spain)

14:00-14:20 : A heuristic for the retrieval of objects in low resolution video. Fanny Chevalier, Maylis Delest, Jean-Philippe Domenger.

14:20-14:40 : A statistical framework for video skimming based on logical story units and motion activity. Sergio Benini, Pierangelo Migliorati, Riccardo Leonardi, University of Brescia.

14:40-15:00 : Region-based hierarchical representation for object detection. Veronica Vilaplana, Ferran Marqu�s.

15:00-15:30 Coffee

15:30-17:30: SESSION D2pmPO1: Poster Session 1

Chair: Eric Pauwels (CWI, The Netherlands)

- Continuous wavelet-like transform based music similarity features for intelligent music navigation. Aliaksandr Paradzinets, Oleg Kotov, Hadi Harb, Liming Chen. Multimodal semantic-associative collateral labelling and indexing of still images. Meng Zhu, Atta Badii.

- Visual taxonomy for professional image retrieval and automated annotation of images. Tuuli Nurminen.

- Evaluation of relative focus map based image indexing. Levente Kovacs, Tamas Sziranyi.

- Using spatial and compressed features for multi-spectral image retrieval. Rafik Bensalma, Mohamed-Chaker Larabi.

- Region-of-interest tracking based on keypoint trajectories on a group of pictures. Vincent Garcia, Eric Debreuve, Michel Barlaud.

- Multimedia scenario extraction and content indexing for e-learning. Thomas Martin, Alain Boucher, Jean-Marc Ogier, Mathias Rossignol, Eric Castelli.

- Soccer video annotation using ontologies extended with visual prototypes. Marco Bertini, Alberto Del Bimbo, Carlo Torniai.

- Speaker segmentation of interviews using integrated video and audio change detectors. Mathieu Lagrange, Luis Gustavo Martins, Luis F. Teixeira, George Tzanetakis.

19:30 � late: Conference Dinner

Car departure from LABRI at 18:30

Wednesday 27 June

09:00-10:00 SESSION D3amIN3: Invited Talk

F. Pachet, P. Roy (SONY, France): Exploring billions of audio features.

Chair: Eric Pauwels (CWI, The Netherlands)

10:00-12:40 SESSION D3amOR3: Oral session 3

Chair: Bernard Merialdo (Eurecom, France)

10:00-10:20: Scalable image retrieval with optimal configuration for p2p network database. Jiann-Jone Chen, Chia-Jung Hu, Chun-Ron Su.

10:20-10:40: Indexing satellite images with features computed from man-made structures on the earth's surface. Avik Bhattacharya, Michel Roux, Henri Maitre, Ian Jermyn, Xavier Descombes, Josiane Zerubia.

10:40-11:00: Evaluating performance of automatic image annotation: example case by fusing global image features. Ville Viitaniemi, Jorma Laaksonen.

11:00-11:20: Coffee

11:20-11:40: Evaluation of active learning strategies for video indexing. St�phane Ayache, Georges Qu�not.

11:40-12:00: Enhancing CBIR through feature optimization, combination and selection. Xavier Hilaire, Joemon Jose.

12:00-12:20: A hierarchical trajectory-based representation for video. Camilo C. D�rea, Montse Pard�s, Ferran Marqu�s.

12:20-14:00: Lunch

14:00-14:30: SESSION D3pmIN4: Invited Talk

Olga Yatsiouk (Russian Research Institute of Technical Aesthetics): Directions for multimedia development considering the aspects of art analysis.

Chair: Jenny Benois-Pineau (LABRI, France)

14:40-16:00 SESSION D3pmPO2: Poster session 2

Chair: Jenny Benois-Pineau (LABRI, France)

- Association of audio and video segmentations for automatic person indexing. Elie El Khoury, Ga�l Jaffr�, Julien Pinquier, Christine S�nac.

- Color-based content retrieval of animation movies: a study. Bogdan Ionescu, Patrick Lambert, Didier Coquin, Vasile Buzuloiu.

- Joint position-pitch tracking for 2-channel audio. Marian K�pesi, Franz Pernkopf, Michael Wohlmayr.

- Practical realization of the content-based image retrieval system using sketch and example. Slawomir Mackowiak, Tomasz Jaminski.

- Video Search using a visual dictionary. Emilie Dumont, Bernard Merialdo.

- Query understanding in content-based image retrieval context. Emilie Naud, Khalid Idrissi, Bruno Tellez.

- Simulated testing of an adaptive multimedia information retrieval system. Frank Hopfgartner, Jana Urban, Robert Villa, Joemon Jos�.

- Building an interactive next-generation artist recommender based on automatically derived high-level concepts. Tim Pohle, Peter Knees, Markus Schedl, Gerhard Widmer.

- A study of intra-modal association rules for visual modality representation. Jean Martinet, Shin'ichi Satoh.

16:00-16:10 Closing (+ Coffee)