Warning: your browser seems to be quite old, or at least old enough that it does not support the minimal standard capabilities of today's browsers, which are used extensively on this site. Please upgrade to a browser that supports web standards, specifically one that supports minimal CSS1 capabilities, such as Netscape 6 or higher, IE 5 or higher, or Opera 5 or higher. Your browsing experience will be much better! Thanks.

The main objectives for this Action are summarized under two main research topics, namely semantic learning and inference on the one hand, and multimodal based retrieval mechanisms on the other hand. These objectives are being achieved according to the work plan of the Action. The work plan consists of an open and flexible framework, comprising seven interrelated and concurrent Working Groups (WG).

• WG 1 - Common testing data and frameworks.


• WG 2 - Image and Video Segmentation, Shot Analysis and Key frame extraction, Efficient extraction of standardized features.


• WG 3 - Reduction of the dimension of the feature space and multimodal feature fusion.


• WG 4 - Automatic paradigms for semantic annotation.


• WG 5 - Semi-automatic paradigms for semantic annotation.


• WG 6 - Applications.


• WG 7 - JPSearch.