We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications suc...
Julia A. Lasserre, Christopher M. Bishop, Thomas P...
Abstract. Finding solutions to minimal problems for estimating epipolar geometry and camera motion leads to solving systems of algebraic equations. Often, these systems are not tri...
We analyze a simple, Bellman-error-based approach to generating basis functions for valuefunction approximation. We show that it generates orthogonal basis functions that provably...
Ronald Parr, Christopher Painter-Wakefield, Lihong...
The GIVE Challenge is a new Internetbased evaluation effort for natural language generation systems. In this paper, we motivate and describe the software infrastructure that we de...
Alexander Koller, Donna Byron, Justine Cassell, Ro...