State-of-the-art stereo vision algorithms utilize color changes as important cues for object boundaries. Most methods impose heuristic restrictions or priors on disparities, for e...
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
We present a practical framework for detecting and modeling 3D static occlusions for wide-baseline, multi-camera scenarios where the number of cameras is small. The framework cons...
An interactive human segmentation approach is described. Given regions of interest provided by users, the approach iteratively estimates segmentation via a generalized EM algorith...
Zhe Lin, Larry S. Davis, David S. Doermann, Daniel...
There is general consensus that context can be a rich source of information about an object's identity, location and scale. However, the issue of how to formalize contextual ...