Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
We present a method of robustly identifying a text block in complex web images. The method is a MLP (Multilayer perceptron) classifier trained on LBP (Local binary patterns), wavel...
Digital scanners are commonplace and are used in many different applications to obtain three-dimensional shapes and linear and circumferential measurements. Even though scanners ca...
Ravindra S. Goonetilleke, Channa P. Witana, Jianhu...
We present an extension of sparse PCA, or sparse dictionary learning, where the sparsity patterns of all dictionary elements are structured and constrained to belong to a prespeci...
Rodolphe Jenatton, Guillaume Obozinski, Francis Ba...
Abstract-- This paper studies a statistical distribution of instantaneous power in pulse-shaped single-carrier (SC) modulation. Such knowledge is of significant importance to estim...