Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of...
We present a template-based approach to detecting human silhouettes in a specific walking pose. Our templates consist of short sequences of 2D silhouettes obtained from motion cap...
Many large-scale biometric systems operate in the identification mode and include multimodal information. While biometric fusion is a well-studied problem, most of the fusion schem...
Traditional binary hypothesis testing relies on the precise knowledge of the probability density of an observed random vector conditioned on each hypothesis. However, for many app...
Discriminative approaches to human pose inference involve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping ha...