Super-resolution aims to produce a high-resolution image from a set of one or more low-resolution images by recovering or inventing plausible high-frequency image content. Typical...
Lyndsey C. Pickup, Stephen J. Roberts, Andrew Ziss...
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...
Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has p...
Abstract— This work considers a combination classificationregression based framework with the proposal of using learned kernels in modified support vector regression to provide...
Abstract We review the evolution of the nonparametric regression modeling in imaging from the local Nadaraya-Watson kernel estimate to the nonlocal means and further to transform-d...
Vladimir Katkovnik, Alessandro Foi, Karen Egiazari...