—An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of p...
This paper presents a robust object tracking method via a spatial bias appearance model learned dynamically in video. Motivated by the attention shifting among local regions of a ...
—A new feature based nonrigid image registration method for magnetic resonance (MR) brain images is presented in this paper. Each image voxel is represented by a rotation invaria...
We propose a subspace learning algorithm for face recognition by directly optimizing recognition performance scores. Our approach is motivated by the following observations: 1) Di...
Abstract. In set-based face recognition, each set of face images is often represented as a linear/nonlinear manifold and the Principal Angles (PA) or Kernel PAs are exploited to me...