In this paper, we propose a robust and efficient Lagrangian approach, which we call Delaunay Deformable Models, for modeling moving surfaces undergoing large deformations and topo...
1 We propose a novel video-based rendering algorithm with a single moving camera. We reconstruct a dynamic 3D model of the scene with a feature point set that "evolves" o...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...
Contextual information is vital for the robust extraction of semantic information in automated surveillance systems. We have developed a scene independent framework for the detect...
In basketball games, wild-open means that there is an offensive player not well defended by his/her opponents. The occurrence of wild-open usually implies the existence of a succe...