This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
research [2009/06/24 22:51] marchand |
research [2021/03/23 21:22] (current) marchand |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | {{keywords>information retrieval, content-based image retrieval, CBIR, CBR, CBVR, CBMR, CBMIR, information mining, video retrieval, evaluation, multimedia, affective, affect-based, emotion-based, retrieval, benchathlon, mrml, collection guide, image collection, multimodal fusion, visualisation, research, gift, recherche d'information, geneve, suisse, switzerland, semantic web knowledge base, SWKB, web semantique, RDF, OWL, XML, metadata, auto-annotation, description, classification, multimedia information management, multimodal information retrieval}} | + | {{keywords>information geometry content-based affective emotion information collection image video multimedia retrieval visualisation CBIR CBR CBVR CBMR CBMIR mining evaluation multimodal fusion research, gift recherche semantic SWKB RDF OWL XML metadata auto-annotation description classification large scale}} |
- | 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. | + | (see) {{https://www.groundai.com/project/hypergraph-modeling-and-visualisation-of-complex-co-occurence-networks/|Hypergraph modeling}} |
- | A major part of our research is also dedicated to video information management. We work on several aspects including: | + | {{ :demos:corelhdme.png?800 |Manifold Learning}} |
- | * Temporal segmentation | + | |
- | * Event-based indexing | + | We address several aspects of information processing, learning and mining: |
- | * Content modelling and indexing | + | * Data Mining |
- | * Large-scale storage, access and retrieval | + | * Feature space analysis |
- | We have developed the novel concept of collection guiding to manage multimedia collections with truly accounting for the fact that the collection exists. | + | * Information geometry models for Machine learning |
+ | * Interactive information visualisation | ||
+ | * Information retrieval | ||
+ | |||
+ | For more details, see our [[research:publications|publications]] and [[research:projects|projects]]... | ||
+ | |||
+ | |||
+ | {{ :demos:starshape.png?500 | Information Visualisation}} |