We describe an approach to segmenting foreground regions corresponding to a group of people into individual humans. Given background subtraction and ground plane homography, hierar...
Zhe Lin, Larry S. Davis, David S. Doermann, Daniel...
In this paper, we propose a method for jointly computing optical flow and segmenting video while accounting for mixed pixels (matting). Our method is based on statistical modelin...
C. Lawrence Zitnick, Nebojsa Jojic, Sing Bing Kang
A dynamic layer representation is proposed in this paper for tracking moving objects. Previous work on layered representations has largely concentrated on two-/multiframe batch fo...
In this paper, we propose to focus on the segmentation of vectorial features (e.g. vector fields or color intensity) using region-based active contours. We search for a domain that...
We present a compressed domain scheme that is able to recognize and localize actions in real-time1 . The recognition problem is posed as performing an action video query on a test ...