Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the rel...
Video game players often learn to map their physical actions (e.g., pressing buttons) onto their on-screen avatars' actions (e.g., wielding swords) in order to play. We explo...
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...