This is an old revision of the document!


We address several aspects of multimedia information processing and management (see associate publications).

  • Video retrieval
  • Multimedia description and annotation
  • Collection guide
  • Image segmentation
  • Content-based image retrieval

We have developed the GIFT, an open-source package for Content-based image retrieval (CBIR) using the Query-by-Example (QBE) paradigm.

We have extensively worked on CBIR system evaluation, in close relationship with the Benchathlon Network. In this respect, the is a need for the existence of large annotated multimedia collections. This has led us to working on the problem of intelligent multimedia description, both from the knwoledge management and automated annotation viewpoints.

A major part of our research is also dedicated to video information management. We work on several aspects including:

  • Temporal segmentation
  • Event-based indexing
  • Content modelling and indexing
  • Large-scale storage, access and retrieval

We have developed the novel concept of collection guiding to manage multimedia collections with truly accounting for the fact that the collection exists.

research.1246351007.txt.gz · Last modified: 2009/06/30 10:36 by marchand
--

Keywords: machine learning, information geometry, data mining, Big Data, affective information retrieval (recherche d'information), information visualisation, content-based image and video retrieval (CBIR, CBR, CBVR, CBMR, CBMIR), information mining, classification, multimedia and multimodal information management, semantic web, knowledge base (RDF, OWL, XML, metadata, auto-annotation, description), multimodal information fusion