We present a new object segmentation method that is based on geodesic active contours with combined shape and appearance priors. It is known that using shape priors can significan...
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level setbased segmentation and tracking. Unlike previous work, we represent sha...
This paper deals with conversion from H.264/AVC (Advanced Video Coding) coded video into the MPEG-2 format. The proposed approach exploits similarities between the coding techniqu...
In this work the problem of automatic decomposition of video into elementary semantic units, known in the literature as scenes, is addressed. Two multi-modal automatic scene segme...
See a PPT file with videos at www.research.microsoft.com/users/jojic/FlexiblesSprites.htm We propose a technique for automatically learning layers of "flexible sprites" ...