—Extracting high-quality dynamic foreground layers from a video sequence is a challenging problem due to the coupling of color, motion, and occlusion. Many approaches assume that...
Machine learning methods are often used to classify objects described by hundreds of attributes; in many applications of this kind a great fraction of attributes may be totally irr...
Miron B. Kursa, Aleksander Jankowski, Witold R. Ru...
Many recent works have attempted to improve object recognition by exploiting temporal dynamics, an intrinsic property of video sequences. In this paper, a new spatiotemporal hiera...
— Obtaining models of dynamic 3D objects is an important part of content generation for computer graphics. Numerous methods have been extended from static scenarios to model dyna...
Abstract—For an intelligent multi-camera multi-object surveillance system, object correspondence across time and space is important to many smart visual applications. In this pap...