Corpus-based stochastic language models have achieved significant success in speech recognition, but construction of a corpus pertaining to a specific application is a difficult ta...
— Successful biological image analysis usually requires satisfactory segmentations to identify regions of interest as an intermediate step. Here we present a novel graphical mode...
Shann-Ching Chen, Ting Zhao, Geoffrey J. Gordon, R...
Abstract. In this work, we present an approach to jointly segment a rigid object in a two-dimensional (2D) image and estimate its three-dimensional (3D) pose, using the knowledge o...
Samuel Dambreville, Romeil Sandhu, Anthony J. Yezz...
A natural language generation system must generate expressions that allow a reader to identify the entities to which they refer. This paper describes the creation of referring-exp...
Jill Nickerson, Stuart M. Shieber, Barbara J. Gros...
This paper proposes a framework for semi-supervised structured output learning (SOL), specifically for sequence labeling, based on a hybrid generative and discriminative approach...