We have designed, implemented, and proved the correctness of a compiler generator that accepts action semantic descriptions of imperative programming languages. The generated comp...
Abstract. In this paper, we propose a framework based on a subsymbolic approach for the support of exploratory activities in a hyperspace. By using it, it is possible to express th...
Mizue Kayama, Toshio Okamoto, Alexandra I. Cristea
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
"Bag of words" models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are mo...