The encoding of shape information is a distinguishing feature of MPEG-4. In error prone communication networks, it is important and efficient to conceal shape errors spatially, so...
Guido M. Schuster, Xiaohuan Li, Aggelos K. Katsagg...
We aim to improve the accuracy of handwritten Chinese character recognition using two advanced techniques: discriminative feature extraction (DFE) and discriminative learning quad...
In this paper, we propose a new context-sensitive Bayesian learning algorithm. By modeling the distributions of data locations by a mixture of Gaussians, the new algorithm can uti...
Optimization algorithms for large margin multiclass recognizers are often too costly to handle ambitious problems with structured outputs and exponential numbers of classes. Optim...
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
Michael Karlen, Jason Weston, Ayse Erkan, Ronan Co...