Learn More
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several parallel streams of action. Our approach integrates temporal, contextual and ordering constraints with output from low-level visual detectors to recognize complex, long-term(More)
The access control provided by a physical lock is based on the assumption that the information content of the corresponding key is private --- that duplication should require either possession of the key or a priori knowledge of how it was cut. However, the ever-increasing capabilities and prevalence of digital imaging technologies present a fundamental(More)
Automatic human motion capture is an important and significant problem in the computer vision community. A successful system may have many applications including inexpensive motion capture and analysis in unconstrained environments, human-computer interfaces, and automatic surveillance systems. This work focuses on an important sub-problem in computer(More)
  • 1