We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, u...
A new class of interconnection networks, the hypernetworks, has been proposed recently. Hypernetworks are characterized by hypergraphs. Compared with point-to-point networks, they...
We derive a new generalization of lowest common ancestors (LCAs) in dags, called the lowest single common ancestor (LSCA). We show how to preprocess a static dag in linear time su...
In the paper we propose a new evolutionary algorithm for induction of univariate regression trees that associate leaves with simple linear regression models. In contrast to typical...
State-of-the-art motion estimation algorithms suffer from three major problems: Poorly textured regions, occlusions and small scale image structures. Based on the Gestalt principle...