No abstract

Abstract. The 'Collaborative Tagging' is gaining popularity on Web 2.0, this new generation of Web which makes user reader/writer. The 'Tagging' is a mean for users to express themselves freely through additions of label called 'Tags' to shared resources. One of the problems encountered in current tagging systems is to define the most appropriate tag for a resource. Tags are typically listed in order of popularity, as del-icio-us. But the popularity of the tag does not always reflect its importance and representativeness for the resource to which it is associated. Starting from the assumptions that the same tag for a resource can take different meanings for different users, and a tag from a knowledgeable user would be more important than a tag from a novice user, we propose an approach for weighting resource's tags based on user profile. For this we define a user model for his integration in the tag weight calculation and a formula for this calculation, based on three factors namely the user, the degree of approximation between his interest centers and the resource field, expertise and personal assessment for tags associated to the resource. A resource descriptor containing the best tags is created.

No abstract

International audienceThe challenge in multimedia information retrieval remains in the indexing process, an active search area. There are three fundamental techniques for indexing multimedia content: using textual information, using low-level information and combining different information extracted from multimedia. Each approach has its advantages and disadvantages as well to improve multimedia retrieval systems. The recent works are oriented towards multimodal approaches. In this paper, we propose an approach that combines the surrounding text with the information extracted from the visual content of multimedia and represented in the same repository in order to allow querying multimedia content based on keywords or concepts. Each word contained in queries or in description of multimedia is disambiguated using the WordNet ontology in order to define its semantic concept. Support Vector Machines (SVMs) are used for image classification in one of the defined semantic concept based on SIFT (scale invariant feature transform) descriptors

No abstract