Félicien Vallet

I am now a PhD candidate in the Department of Image and Signal Processing - TSI of TELECOM ParisTech and in the Audiovisual Content Description group - DCA of Ina. My advisors are Gaël Richard, Slim Essid (TELECOM ParisTech) and Jean Carrive (Ina).

Created in 1974, Ina is a repository of all French radio and television audiovisual archives. Therefore, with the exponential raising of the volume of numeric data, Ina needs the creation of new and efficient methods for indexation and classification.

My PhD is oriented towards the exploitation of numerous metadata of various forms : audio, video and text. A large part of the work will be the study of the fusion across the diverse modalities in order of detecting high-level concepts. Besides, a reflexion on the selection of the correct attributes for a given task will also be led. A practical approach of such a work would be the building of a robust customer-oriented system for high-level concept detection.

This PhD is involved with many research projects : K-Space, Infom@gic and Quaero in which Ina and TELECOM ParisTech are partners.

Projects

K-Space : K-Space stands for Knowledge Space of Semantic Inference for Automatic Annotation and Retrieval of Multimedia Content. K-Space integrates leading European research teams to create a Network of Excellence in semantic inference for semi-automatic annotation and retrieval of multimedia content. The aim is to narrow the gap between content descriptors that can be computed automatically by current machines and algorithms, and the richness and subjectivity of semantics in high-level human interpretations of audiovisual media : The Semantic Gap.

Partners of the project : Queen Mary University of London (QMUL), Koblenz University (KU), Joanneum Research Forschungsgesellschaft mbH (JRS), Informatics and Telematics Institute (ITI-CERTH), Dublin City University (DCU), Centrum voor Wiskunde en Informatica (CWI), Groupe des Ecoles de Telecommunications (GET), Institut National de l'Audiovisuel (Ina), Institut Eurécom (EURECOM), University of Glasgow (GU), German Research Centre for Artificial Intelligence (DFKI), Technishe Universität Berlin (TUB), Ecole Polytechnique Federale de Lausanne (EPFL), University of Economics, Prague (UEP)

Infom@gic : creating powerful multimedia search, information retrieval and knowledge mining tools... This project brings together more than 20 partners, namely: EADS, XEROX, Bertin technologies, Europlace, Intuilab, Odile Jacob, Pertimm, Temis, Fist, CEA, Ina, CNRS, ONERA, GET/ENST/INT, Paris VI, Vecsys, Paris VIII, Paris IX, Paris XIII, Paris-sud Orsay, Université Marne la Vallée, CNRS/LIMSI, CNRS/LACAN.

Quaero : Quaero is a collaborative research and development program, centered at developing multimedia and multilingual indexing and management tools for professional and general public applications such as the automatic analysis, classification, extraction and exploitation of information. The research aims to facilitate the extraction of information in unlimited quantities of multimedia and multilingual documents, including written texts, speech and music audio files, and images and videos.

Publications

Conference Papers :

- F. Vallet, S. Essid, J. Carrive, G. Richard. "Robust visual features for the multimodal identification of unregistered speakers in TV talk-shows". In Proc. International Conference on Image Processing (ICIP), 2010. ACCEPTED

- S. Bozonnet, F. Vallet, N. Evans, S. Essid, G. Richard, J. Carrive. "A multimodal approach to initialisation for top-down speaker diarization of television shows". In Proc. European Signal Processing Conference (EUSIPCO), 2010. [pdf][poster]

- F. Vallet, S. Essid, J. Carrive, G. Richard. "Descripteurs visuels robustes pour l'identification de locuteurs dans des émissions télévisées de talk-shows". In Proc. Compression et Représentation des Signaux Audiovisuels (CORESA), 2010. ACCEPTED

- Z. Harchaoui, F. Vallet, A. Lung-Yut-Fong, O. Cappé. "A regularized kernel-based approach to unsupervised audio segmentation". In Proc. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2009. [pdf][poster]

- F. Vallet, G. Richard, S. Essid, J. Carrive. "Detecting artist performances in a TV show". In Proc. K-Space PhD Jamboree, Paris, France, July 2008. [pdf][poster]

- P. Wilkins, T. Adamek, D. Byrne, G. Jones, H. Lee, K. McGuiness, N. E. O'Connor, A.F. Smeaton, A. Amin, Z. Obrenovic, R. Benmokhtar, E. Galmar, B. Huet, S. Essid, R. Landais, F. Vallet, G. Th. Papadopoulos, S. Vrochidis, V. Mezaris, I. Kompatsiaris, E. Spyrou, Y. Avrithis, R. Morzinger, P. Schallauer, W. Bailer, T. Piatrik, K. Chandramouli, E. Izquierdo, M. Haller, L. Goldmann, A. Samour, A. Cobet, T. Sikora, P. Praks. "K-Space at TRECVid 2007", October 2007. [pdf]

- F. Vallet, M. McKinney. "Perceptual constraints for automatic vocal detection in music recordings". In Proc. Conference on Interdisciplinary Musicology (CIM), Tallinn, Estonia, August 2007. [pdf]

_{Note concerning IEEE publications: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author'scopyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder (see IEEE copyright policies).}

Contacts

Email : myfirstname.mylastname@telecom-paristech.fr

Ina :

Bureau 1103, 4 avenue de l'Europe, 94366 Bry-sur-Marne, Cedex - FRANCE.

Phone : + 33 1 49 83 26 52

Fax : + 33 1 49 83 25 82

TELECOM ParisTech :

Bureau DA408, 37 rue Dareau, 75014 Paris - FRANCE.

Phone : + 33 1 45 81 72 61

Fax : + 33 1 45 87 71 44

Félicien Vallet's Homepage

LINKS: