Abstract. We consider a new discriminative learning approach to sequence labeling based on the statistical concept of the Z-score. Given a training set of pairs of hidden-observed ...
We propose a new loss function for discriminative learning of Markov random fields, which is an intermediate loss function between the sequential loss and the pointwise loss. We s...
Abstract--Automatic video annotation is a challenging yet important problem for content-based video indexing and retrieval. In most existing works, annotation is formulated as a mu...
We introduce a discriminative hidden-state approach for the recognition of human gestures. Gesture sequences often have a complex underlying structure, and models that can incorpo...
Sy Bor Wang, Ariadna Quattoni, Louis-Philippe More...
Sparse graphical models have proven to be a flexible class of multivariate probability models for approximating high-dimensional distributions. In this paper, we propose techniques...
Vincent Y. F. Tan, Sujay Sanghavi, John W. Fisher ...