This paper describes a novel application of Statistical Learning Theory (SLT) for motion prediction. SLT provides analytical VC-generalization bounds for model selection; these bo...
Harry Wechsler, Zoran Duric, Fayin Li, Vladimir Ch...
3D human motion capture by real-time monocular vision without using markers can be achieved by registering a 3D articulated model on a video. Registration consists in iteratively o...
Abstract. Intensity based registration methods, such as the mutual information (MI), do not commonly consider the spatial geometric information and the initial correspondences are ...
Our goal is to fit the multiple instances (or structures) of a generic model existing in data. Here we propose a novel model selection scheme to estimate the number of genuine str...
In this paper, we address the problem of estimating mesoscale dynamics of atmospheric layers from satellite image sequences. Relying on a physically sound vertical decomposition of...