Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
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...
Abstract. This paper addresses the problem of automatically segmenting bone structures in low resolution clinical MRI datasets. The novel aspect of the proposed method is the combi...
We present a new approach to deformable image registration suitable for articulated images such as hand-drawn cartoon characters and human postures. For such type of data state-of...
The appearance manifold [WTL 06] is an efficient approach for modeling and editing time-variant appearance of materials from the BRDF data captured at single time instance. Howeve...
Su Xue, Jiaping Wang, Xin Tong, Qionghai Dai, Bain...