Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
—Reading gaze direction is important in human-robot interactions as it supports, among others, joint attention and non-linguistic interaction. While most previous work focuses on...
People identification has numerous applications, ranging from surveillance/security to robotics. Face and body movement/gait biometrics are the most important tools for this task....
Most recent rendering research has concentrated on two subproblems: modeling the reflection of light from materials, and calculating the direct and indirect illumination from lig...
This paper presents a novel approach for estimating the flow fields of dynamic temporal textures whose motion differs radically from that of rigid bodies. Our approach is based o...
David Edwards, Johnny T. Chang, Lin Shi, Yizhou Yu