Abstract. We propose a methodology for recognizing actions at a distance by watching the human poses and deriving descriptors that capture the motion patterns of the poses. Human p...
Abstract--We present a novel tracking method for effectively tracking objects in structured environments. The tracking method finds applications in security surveillance, traffic m...
Existing scene flow approaches mainly focus on twoframe stereo-pair configurations and reconstruct an imagebased representation of scene flow. Instead, we propose a variational...
Reconstructing realistic 3D hair geometry is challenging due to omnipresent occlusions, complex discontinuities and specular appearance. To address these challenges, we propose a ...
We address the problem of multi-person dataassociation-based tracking (DAT) in semi-crowded environments from a single camera. Existing trackletassociation-based methods using pur...