A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a ...
— Most recent approaches to monocular non-rigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well-textured. The alternative ...
—We introduce a simple image descriptor referred to as the image signature. We show, within the theoretical framework of sparse signal mixing, that this quantity spatially approx...
—We describe an approach for segmenting a moving image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appea...
Binary descriptors are becoming increasingly popular as a means to compare feature points very fast and while requiring comparatively small amounts of memory. The typical approach...