Taking a sequence of photographs using multiple illumination sources or settings is central to many computer vision and graphics problems. A growing number of recent methods use m...
This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAM)-based approaches have achieved some success, t...
This paper presents a new algorithm for the problem of robust subspace learning (RSL), i.e., the estimation of linear subspace parameters from a set of data points in the presence...
Recovering the three-dimensional (3D) object shape lies as an unresolved and active research topic on the crosssection of computer vision, photogrammetry and bioinformatics. Altho...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...