Video-based recognition and prediction of a temporally extended activity can benefit from a detailed description of high-level expectations about the activity. Stochastic grammars...
Contours have been established in the biological and computer vision literature as a compact yet descriptive representation of object shape. While individual contours provide stru...
3D surface matching is fundamental for shape registration, deformable 3D non-rigid tracking, recognition and classification. In this paper we describe a novel approach for generati...
Wei Zeng, Yun Zeng, Yang Wang, Xiaotian Yin, Xianf...
Current two-dimensional image based face recognition systems encounter difficulties with large facial appearance variations due to the pose, illumination and expression changes. ...
In this paper, we present a novel approach to robust skeleton extraction. We use undirected graphs to model connectivity of the skeleton points. The graph topology remains unchang...