We present the IBM systems submitted and evaluated within the CLEAR'06 evaluation campaign for the tasks of single person visual 3D tracking (localization) and 2D face trackin...
Recent work has demonstrated that using a carefully designed dictionary instead of a predefined one, can improve the sparsity in jointly representing a class of signals. This has m...
Kevin Rosenblum, Lihi Zelnik-Manor, Yonina C. Elda...
The paper describes an experimental study on the detection of emotion from speech. As computer based characters such as avatars and virtual chat faces become more common, the use ...
Feng Yu, Eric Chang, Ying-Qing Xu, Heung-Yeung Shu...
The sensor network localization, SNL , problem in embedding dimension r, consists of locating the positions of wireless sensors, given only the distances between sensors that are ...
Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...