The objective of this paper is to parse object trajectories in surveillance video against occlusion, interruption, and background clutter. We present a spatio-temporal graph (ST-G...
This paper aims at improving perceptual quality of encoded video sequences, and proposes a new perceptual bit allocation scheme for H.264. Firstly, a new motion complexity measure...
We describe a general algorithm for identifying an arbitrary pose of an articulated subject with low density feature points. The algorithm aims to establish a one-to-one correspon...
Abstract. The work described in this abstract presents a roadmap towards the creation and specification of a virtual humanoid capable of performing expressive gestures in real tim...
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pr...