We present a markerless motion capture approach that reconstructs the skeletal motion and detailed time-varying surface geometry of two closely interacting people from multi-view ...
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
We present a novel theory for characterizing defocus blurs in multi-perspective cameras such as catadioptric mirrors. Our approach studies how multi-perspective ray geometry trans...
We are interested in the problem of automatic tracking and identification of players in broadcast sport videos shot with a moving camera from a medium distance. While there are m...
Wei-Lwun Lu, Jo-Anne Ting, Kevin Murphy, Jim Littl...
We present a novel approach to representing and recognizing composite video events. A composite event is specified by a scenario, which is based on primitive events and their tem...