We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized corre...
Given a video sequence, obtaining accurate layer segmentation and alpha matting is very important for various applications. However, when a non-textured or smooth area is present ...
We simultaneously approach two tasks of nonlinear discriminant analysis and kernel selection problem by proposing a unified criterion, Fisher+Kernel Criterion. In addition, an eff...
Shu Yang, Shuicheng Yan, Dong Xu, Xiaoou Tang, Cha...
Segmentation involves separating an object from the background. In this work, we propose a novel segmentation method combining image information with prior shape knowledge, within...
Samuel Dambreville, Yogesh Rathi, Allen Tannenbaum
Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made ...