Illuminant estimation from shadows typically relies on accurate segmentation of the shadows and knowledge of exact 3D geometry, while shadow estimation is difficult in the presen...
Integration over a domain, such as a Euclidean space or a Riemannian manifold, is a fundamental problem across scientific fields. Many times, the underlying domain is only acces...
It’s common experience for human vision to perceive full 3D shape and scene from a single 2D image with the occluded parts “filled-in” by prior visual knowledge. In this pa...
In this paper, we present a general data clustering algorithm which is based on the asymmetric pairwise measure of Markov random walk hitting time on directed graphs. Unlike tradi...
Recent research has shown that surprisingly rich models of human behavior can be learned from GPS (positional) data. However, most research to date has concentrated on modeling si...