We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natur...
We define multi-scale moments that are estimated locally by analyzing the image through a sliding window at multiple scales. When the analysis window satisfies a two-scale relatio...
Motion information is a powerful cue for visual perception. In the context of video indexing and retrieval, motion content serves as a useful source for compact video representati...
This paper proposes a new technique in wavelet video compression that exploits the spatiotemporal regularity of the video. A sequence of frames is said to be regular along the dire...
Most optical flow estimation techniques have substantial difficulties dealing with flow discontinuities. Methods which simultaneously detect flow boundaries and use the detect...