—Automatic understanding of human behavior is an important and challenging objective in several surveillance applications. One of the main problems of this task consists in accur...
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain. We explore a hybrid model framework for utilizing...
We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to ...
Ben Taskar, Dan Klein, Mike Collins, Daphne Koller...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
We describe a fast and efficient online algorithm for phoneme sequence speech recognition. Our method is using a discriminative training to update the model parameters one utteran...