The supervised learning paradigm assumes in general that both training and test data are sampled from the same distribution. When this assumption is violated, we are in the setting...
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...
Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by exte...
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires mode...
A template tracking approach to the segmentation of small 3D vessel structures is presented. The main contributions are a general formulation of a vessel template function and a m...