—Most of the development of pose recognition focused on a single person. However, many applications of computer vision essentially require the estimation of multiple people. Henc...
Our goal is to circumvent one of the roadblocks to using existing approaches for single-view recognition for achieving multi-view recognition, namely, the need for sufficient trai...
Detecting an object part relies on two sources of information - the appearance of the part itself, and the context supplied by surrounding parts. In this paper we consider problem...
Leonid Karlinsky, Michael Dinerstein, Daniel Harar...
Deformable model tracking is a powerful methodology that allows us to track the evolution of high-dimensional parameter vectors from uncalibrated monocular video sequences. The co...
Christian Vogler, Siome Goldenstein, Jorge Stolfi,...
While the problem of tracking 3D human motion has been widely studied, most approaches have assumed that the person is isolated and not interacting with the environment. Environme...