no code implementations • 28 Sep 2013 • Dong Zhang, Omar Oreifej, Mubarak Shah
In contrast, we propose to extract cross-image features, i. e. features across the pair of images, which, as we demonstrate, is more discriminative to the similarity and the dissimilarity of faces.
no code implementations • CVPR 2013 • Omar Oreifej, Zicheng Liu
In contrast, we describe the depth sequence using a histogram capturing the distribution of the surface normal orientation in the 4D space of time, depth, and spatial coordinates.