We model the spatio-temporal variations of the shape of objects in a video sequence using a unique SVD-like decomposition. The decomposition is used to compute shape features, whi...
Our goal is to automatically segment and recognize basic human actions, such as stand, walk and wave hands, from a sequence of joint positions or pose angles. Such recognition is d...
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 ...
This paper presents a new behavior classification system for analyzing human movements directly from video sequences. First of all, we propose a triangulation-based method to tran...
The ability to detect a persons unconstrained hand in a natural video sequence has applications in sign language, gesture recognition and HCI. This paper presents a novel, unsuper...