—We describe an approach for segmenting a moving image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appea...
We present a new approach to the supervised learning of lateral interactions for the competitive layer model (CLM) dynamic feature binding architecture. The method is based on con...
Spectral graph partitioning provides a powerful approach to image segmentation. We introduce an alternate idea that finds partitions with a small isoperimetric constant, requiring ...
We propose a method based on sparse representation
(SR) to cluster data drawn from multiple low-dimensional
linear or affine subspaces embedded in a high-dimensional
space. Our ...
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...