In this paper we present a procedure to learn a topological model of Situated Public Displays from data of people traveling between these displays. This model encompasses the dista...
This paper presents a novel approach for tracking humans and objects under severe occlusion. We introduce a new paradigm for multiple hypotheses tracking, observe-and-explain, as ...
Recently, the generative modeling approach to video segmentation has been gaining popularity in the computer vision community. For example, the flexible sprites framework has been...
Color is a powerful attribute that is used to characterize objects for tracking and other surveillance tasks. Since color is dependent on ambient illumination and the imaging equi...
Tracking of humans in videos is important for many applications. A major source of difficulty in performing this task is due to inter-human or scene occlusion. We present an appr...