Sciweavers

Share
ACCV
2010
Springer

Modeling Sense Disambiguation of Human Pose: Recognizing Action at a Distance by Key Poses

8 years 4 months ago
Modeling Sense Disambiguation of Human Pose: Recognizing Action at a Distance by Key Poses
Abstract. We propose a methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses. Human poses often carry a strong visual sense (intended meaning) which describes the related action unambiguously. But identifying the intended meaning of poses is a challenging task because of their variability and such variations in poses lead to visual sense ambiguity. From a large vocabulary of poses (visual words) we prune out ambiguous poses and extract key poses (or key words) using centrality measure of graph connectivity [1]. Under this framework, finding the key poses for a given sense (i.e., action type) amounts to constructing a graph with poses as vertices and then identifying the most "important" vertices in the graph (following centrality theory). The results on four standard activity recognition datasets show the efficacy of our approach when compared to the present state of the art.
Snehasis Mukherjee, Sujoy Kumar Biswas, Dipti Pras
Added 12 May 2011
Updated 12 May 2011
Type Journal
Year 2010
Where ACCV
Authors Snehasis Mukherjee, Sujoy Kumar Biswas, Dipti Prasad Mukherjee
Comments (0)
books