An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...
In this work, we present a multimodal identity verification system based on the fusion of the face image and the text independent speech data of a person. The system conciliates th...
Jacek Czyz, Samy Bengio, Christine Marcel, Luc Van...
Fusional languages have rich inflection. As a consequence, tagsets capturing their morphological features are necessarily large. A natural way to make a tagset manageable is to us...
The TREC-2001 Web track evaluation experiments at the Justsystem site are described with a focus on the "aboutness" based approach in text retrieval. In the web ad hoc t...
In this paper we present results from the first use of neural networks for real-time control of the high temperature plasma in a tokamak fusion experiment. The tokamak is currentl...