Abstract— This paper proposes a sparsity driven shape registration method for occluded facial feature localization. Most current shape registration methods search landmark locati...
Abstract--Reconstruction algorithms for fluorescence tomography have to address two crucial issues : (i) the ill-posedness of the reconstruction problem, (ii) the large scale of nu...
We optimize over the set of corrected laplacians (CL) associated with a weighted graph to improve the average case normalized cut (NCut) of a graph. Unlike edge-relaxation SDPs, o...
Extracting a computer model of a real scene from a sequence of views, is one of the most challenging and fundamental problems in computer vision. Stereo vision algorithms allow us...
Visual attributes expose human-defined semantics to object recognition models, but existing work largely restricts their influence to mid-level cues during classifier training....