Annotations of multimedia documents typically have been pursued in two different directions. Either previous approaches have focused on low level descriptors, such as dominant colo...
Stephan Bloehdorn, Kosmas Petridis, Carsten Saatho...
Automatic image annotation is a promising solution to enable semantic image retrieval via keywords. In this paper, we propose a multi-level approach to annotate the semantics of n...
Behavior understanding and semantic interpretation of dynamic visual scenes have attracted a lot of attention in computer vision research community. Although the use of surveillan...
Ahmed Azough, Alexandre Delteil, Fabien De Marchi,...
The work presented in this paper aims at reducing the semantic gap between low level video features and semantic video objects. The proposed method for finding associations betwee...
We address the problem of classifying scenes from feature films into semantic categories and propose a robust framework for this problem. We propose that the Finite State Machines ...