We present a novel human posture recognition method using convex programming based matching schemes. Instead of trying to segment the object from the background, we develop a nove...
This paper presents an automatic Australian sign language (Auslan) recognition system, which tracks multiple target objects (the face and hands) throughout an image sequence and e...
Abstract. We introduce a view–point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on...
This paper presents a new approach for video clip retrieval based on Earth Mover’s Distance (EMD). Instead of imposing one-to-one matching constraint as in [11, 14], our approach...
Shock graphs have emerged as a powerful generic 2-D shape representation. However, most approaches typically assume that the silhouette has been correctly segmented. In this paper,...