Abstract— We present a novel algorithm to perform continuous collision detection(CCD) between non-rigid, deformable models using local advancement. Given the initial and final c...
In this paper, we describe an approach to segmenting news video based on the perceived shift in content using features spanning multiple modalities. We investigate a number of mul...
Gert-Jan Poulisse, Marie-Francine Moens, Tomas Dek...
The recent availability of large corpora for training N-gram language models has shown the utility of models of higher order than just trigrams. In this paper, we investigate meth...
Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
Automatic recognition of Dialog-act (DA) is one of the most important processes in understanding spontaneous dialog. Most existing studies have been working on how to use various ...