Given a dense set of imperfect normals obtained by photometric stereo or shape from shading, this paper presents an optimization algorithm which alternately optimizes until conver...
Several domain specific approaches for sports video management have shown the benefits of integrating low- and high- level video contents in supporting more robust retrieval. Howev...
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...
In this paper we describe a new approach for learning dialog act processing. In this approach we integrate a symbolic semantic segmentation parse,: with a learning dialog act netw...
We present an algorithm for the segmentation of the liver in 2-D computed tomography slice images. The basis for our algorithm is an implicit active shape model. In order to detec...