INRIA

http://www.inria.fr/

INRIA (National Institute for Research in Computer Science and Control) is a French public-sector scientific and technological institute operating under the dual authority of the Ministry of Research and the Ministry of Industry. INRIA's missions are "to undertake basic and applied research, to design experimental systems, to ensure technology and knowledge transfer, to organize international scientific exchanges, to carry out scientific assessments, and to contribute to standardization". The research carried out at INRIA brings together experts from the fields of computer science and applied mathematics covering the following areas: Networks and Systems; Software Engineering and Symbolic Computing; Man-Machine Interaction; Image Processing, Data Management, Knowledge Systems; Simulation and Optimization of Complex Systems.

INRIA gathers in its premises around 3000 persons: 900 INRIA permanent employees (400 researchers, 500 engineers and technicians), 750 post-docs, engineers and visitors, 700 doctoral candidates, 450 Researchers and professors from other organizations and 200 "Expert engineers" (on research contracts). Its budget is roughly 120 Meuro (2003), 25% of which comes from research and development contracts, royalties and sales. Industrial relations are strategic for INRIA: 600 R&D contracts with industry and 50 technology companies have been born of the Institute. Roughly 40% of these contracts are European funded ones. Since 1984, more than 250 European Framework-Programme (FP) projects have been executed.

INRIA is a member of ERCIM EEIG, European Research Consortium for Computer Science and Mathematics. Outside Europe, INRIA also has a significant activity: it has created joint research laboratories (Russia and China), signed cooperation agreements (NSF, India, Brazil, etc.) and promotes intensive scientific exchanges.
Three research groups are involved in the aceMedia consortium :

IMEDIA research group focuses on content-based image retrieval
http://www-rocq.inria.fr/imedia : 1/ Modeling the visual appearance, designing and structuring the description space; 2/ Statistical learning and pattern recognition; 3/ Interactive search and personalization; 4/ Cross-Media indexing and retrieval for us in the semantic range of textual annotation

LEAR : http://www.inrialpes.fr/lear The LEAR research group was created in July 2003. Its main research activities are object recognition and scene interpretation for static images and video sequences. We believe that the addition of learning techniques to computer vision will improve current systems significantly. Even a partial solution to the problem will enable many applications. We are in particular interested in image retrieval and video indexing.

TEXMEX : http://www.irisa.fr/texmex/index.english.htm. This is a new group in Rennes, created in 2002 . The group studies the problem of exploiting efficiently large multimedia databases. The work in the group is organized into three subjects: 1- Indexing and retrieval in very large image bases; 2- Search engine improvement by using linguistic resources; 3- Description of multimedia documents using the different media simultaneously.