Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions (e.g. happiness and anger). Such prototypic expressions, however, occur infre...
Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. movements...
In this paper we describe a recognition approach based on the notion of primitives. As opposed to recognizing actions based on temporal trajectories or temporal volumes, primitive-...
Preben Fihl, Michael B. Holte, Thomas B. Moeslund,...
This paper proposes a novel algorithm for categorization of action video sequences using unsupervised dual clustering. Given a video database, we extract motion information of act...