This paper describes a general methodology for automated recognition of complex human activities. The methodology uses a context-free grammar (CFG) based representation scheme to ...
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...
In this paper we present a stable automatic system for image composition, which can well control the color difference between two images, and produce a seamless composite image wit...
In this work, to render at least 5123 voxel volumes in real-time, we have developed a sort-last parallel volume rendering method for distributed memory multiprocessors. Our sort-l...
Video surveillance systems seek to automatically identify events of interest in a variety of situations. Extracting a moving object from background is the most important step of t...