In this paper, we present a method for human action recognition from multi-view image sequences that uses the combined motion and shape flow information with variability considera...
This paper presents a novel representation for human actions which encodes the variations in the shape and motion of the performing actor. When an actor performs an action, at eac...
We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human a...
Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recogn...
A prototype-based approach is introduced for action
recognition. The approach represents an action as a se-
quence of prototypes for efficient and flexible action match-
ing in ...