This paper offers a logical formalisation of an argument-based account of reasoning about action, taking seriously the abductive nature of this form of reasoning. The particular qu...
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feed...
Hueihan Jhuang, Thomas Serre, Lior Wolf, Tomaso Po...
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...
Recent work in behavioral animation has taken impressive steps towards a virtual human. As for intelligent virtual agents, abbreviated "IVAs", the behaviors displayed in ...
Abstract This paper focuses on human behavior recognition where the main problem is to bridge the semantic gap between the analogue observations of the real world and the symbolic ...