Many emerging applications require tracking targets in video. Most existing visual tracking methods do not work well when the target is motion-blurred (especially due to fast moti...
Shengyang Dai, Ming Yang, Ying Wu, Aggelos K. Kats...
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstru...
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
When an image is viewed at varying resolutions, it is known to create discrete perceptual jumps or transitions amid the continuous intensity changes. In this paper, we study a per...