In this paper we consider the problem of temporal texture modeling and synthesis. A temporal texture (or dynamic texture) is seen as the output of a dynamical system driven by whit...
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...
Abstract. There has been growing interest in developing nonlinear dimensionality reduction algorithms for vision applications. Although progress has been made in recent years, conv...
We present a dynamic near-regular texture (NRT) tracking algorithm nested in a lattice-based Markov-Random-Field (MRF) model of a 3D spatiotemporal space. One basic observation use...
In this paper, we propose a two-level integrated model for accurate face shape alignment. At the low level, the shape is split into a set of line segments which serve as the nodes ...
Filtering based algorithms have become popular in tracking human body pose. Such algorithms can suffer the curse of dimensionality due to the high dimensionality of the pose state ...
Rui Li, Ming-Hsuan Yang, Stan Sclaroff, Tai-Peng T...