In this paper, we address the problem of learning compact, view-independent, realistic 3D models of human actions recorded with multiple cameras, for the purpose of recognizing th...
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...
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
Abstract. We propose a novel and efficient method for generic arbitraryview object class detection and localization. In contrast to existing singleview and multi-view methods using...
Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung, Long Q...
In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D sk...