Abstract. This paper addresses the problem of how to learn an appropriate feature representation from video to benefit video-based face recognition. By simultaneously exploiting th...
We propose a fast algorithm, EMD-L1, for computing the Earth Mover's Distance (EMD) between a pair of histograms. Compared to the original formulation, EMD-L1 has a largely si...
In recent years, nonlinear dimensionality reduction (NLDR) techniques have attracted much attention in visual perception and many other areas of science. We propose an efficient al...
Recently, the wide deployment of practical face recognition systems gives rise to the emergence of the inter-modality face recognition problem. In this problem, the face images in ...
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...