We present a method for object categorization in real-world scenes. Following a common consensus in the field, we do not assume that a figure-ground segmentation is available prior...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the dis...
Abstract. In surveillance systems for monitoring people behaviour, it is imporant to build systems that can adapt to the signatures of the people tasks and movements in the environ...
Nam Thanh Nguyen, Svetha Venkatesh, Geoff A. W. We...
Pitch mismatch between training and testing is one of the important factors causing the performance degradation of the speaker recognition system. In this paper, we adopted the mis...