Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
In this paper we propose a novel message-passing algorithm, the so-called Action-GDL, as an extension to the Generalized Distributive Law algorithm (GDL) [1] to efficiently solve...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...
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...
Although human action recognition has been the subject of much research in the past, the issue of viewpoint invariance has received scarce attention. In this paper, we present an ...