Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...
The 3D reconstruction of a face from a single frontal image is an ill-posed problem. This is further accentuated when the face image is captured under different poses and/or compl...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
We propose a new algorithm for learning kernels for variants of the Normalized Cuts (NCuts) objective – i.e., given a set of training examples with known partitions, how should ...
Conventional subspace learning-based face recognition aims to attain low recognition errors and assumes same loss from all misclassifications. In many real-world face recognition...