Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
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...
The aim of this work is to devise an effective method for static summarization of home video sequences. Based on the premise that the user watching a summary is interested in peop...
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of...
We present a compressed domain scheme that is able to recognize and localize actions in real-time1 . The recognition problem is posed as performing an action video query on a test ...