We propose a variational multigrid method for fast 3D interpretation of image sequences, in which a dense depth map and 3D motion are directly recovered from spatiotemporal change...
The coding efficiency of the H.264/AVC standard enables the transmission of high quality video over bandwidth limited networks. Due to the use of multiple Macroblock (MB) partitio...
demanding algorithm of a video encoder. It is known that about 60% ~ 80% of the total computation time is consumed for motion estimation [1]. The second is its high impact on the v...
J. Lee, Narayanan Vijaykrishnan, Mary Jane Irwin, ...
We present an automatic and efficient method to extract spatio-temporal human volumes from video, which combines top-down model-based and bottom-up appearancebased approaches. Fr...
We have developed a computer vision system, including both facial feature extraction and recognition, that automatically discriminates among subtly different facial expressions. E...
James Jenn-Jier Lien, Takeo Kanade, Jeffrey F. Coh...