We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
In this paper we propose a new approach to web visualisation with VRML based on a function-based shape modelling, which unifies different types of mathematical functions in order ...
A composition language based on a formal semantic foundation will facilitate precification of glue abstractions and compositions, and will support reasoning about their behaviour....
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a dispar...
This paper proposes a model-based methodology for recognizing and tracking objects in digital image sequences. Objects are represented by attributed relational graphs (or ARGs), w...
Ana Beatriz V. Graciano, Roberto Marcondes Cesar J...