It is well known that frame independence assumption is a fundamental limitation of current HMM based speech recognition systems. By treating each speech frame independently, HMMs ...
In this paper, a Random Field Topic (RFT) model is proposed for semantic region analysis from motions of objects in crowded scenes. Different from existing approaches of learning ...
Motion segmentation based on point trajectories can integrate information of a whole video shot to detect and separate moving objects. Commonly, similarities are defined between ...
3D mesh models are now widely available for use in various applications. The demand for automatic model analysis and understanding is ever increasing. Mesh segmentation is an impo...
Yu-Kun Lai, Shi-Min Hu, Ralph R. Martin, Paul L. R...