We present a Bayesian framework for learning higherorder transition models in video surveillance networks. Such higher-order models describe object movement between cameras in the...
Internet Protocol Television (IPTV) has emerged as a new delivery method for TV. In contrast with native broadcast in traditional cable and satellite TV system, video streams in I...
Multicast conferencing is a rapidly-growing area of Internet use. Audio, video and other media such as shared whiteboard data can be distributed efficiently between groups of confe...
Mourad Amad, Zahir Haddad, Lachemi Khenous, Kamal ...
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...