Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlu...
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...
The management of large databases of hierarchical (e.g., multi-scale or multilevel) image features is a common problem in object recognition. Such structures are often represented ...
—A novel patch-based correspondence model is presented in this paper. Many segment-based correspondence approaches have been proposed in recent years. Untextured pixels and bound...
A statistical representation of three-dimensional shapes is introduced, based on a novel four-dimensional feature. The feature parameterizes the intrinsic geometrical relation of ...