In this paper, we present a new approach for viewinvariant action recognition using constraints derived from the eigenvalues of planar homographies associated with triplets of bod...
In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
In real world scenes, objects to be classified are usually not visible from every direction, since they are almost always positioned on some kind of opaque plane. When moving a cam...
A new approach to the recognition of temporal behaviors and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference probl...
We propose a new template-based approach for viewinvariant recognition of body poses, based on geometric constraints derived from the motion of body point triplets. In addition to...