In this paper, a new Mixture model of Dynamic pedestrian-Agents (MDA) is proposed to learn the collective behavior patterns of pedestrians in crowded scenes. Collective behaviors ...
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...
Abstract. This paper presents a novel approach for image segmentation by introducing competition between neighboring shape models. Our method is motivated by the observation that e...
Pingkun Yan, Weijia Shen, Ashraf A. Kassim, Mubara...
Abstract. Volume segmentation is a relatively slow process and, in certain circumstances, the enormous amount of prior knowledge available is underused. Model-based liver segmentat...
Charles Florin, Nikos Paragios, Gareth Funka-Lea, ...
The ability to detect and differentiate breakpoints during task execution is critical for enabling defer-to-breakpoint policies within interruption management. In this work, we ex...