An approach of a semantic annotation and thematisation of AV documents

In this work, we propose an approach of thematisation of audiovisual (AV) documents for a research according to topics evoked in each document. The first step of our approach is to define the descriptive metadata allowing a bibliographical description of the whole documents. The second step is divided into three stages: the first one is a temporal segmentation, the second one is space segmentation and the last is a semantic thematized description. Topics are modeled by classes of annotations such as (person, event, site and activity, etc.) and their instances (such as an event political, sporting, and cultural, etc.). In order to illustrate our work of semantic annotation we used platform ADVENE. This one will create semantic annotations by video and thereafter generating hypervideos for an active reading. This platform thus makes practices of thematized reading it possible. After this experiment, we will see to which extent and by which means our solution of thematisation, will give a better search of heterogeneous audiovisual documents.