This paper presents a Named Entity Recognition (NER) method dedicated to process speech transcriptions. The main principle behind this method is to collect in an unsupervised way ...
We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
In many real-world domains, undirected graphical models such as Markov random fields provide a more natural representation of the dependency structure than directed graphical mode...
Sushmita Roy, Terran Lane, Margaret Werner-Washbur...
Standard 3D imaging systems process only a single return at each pixel from an assumed single opaque surface. However, there are situations when the laser return consists of multip...
Sergio Hernandez-Marin, Andrew M. Wallace, Gavin J...
We propose in this paper a new formulation of the equation of the optical flow enabling to compute global and local motions of multi-structure objects (flowers and petals, trees...