This paper considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with assoc...
In this paper, we propose a framework for isolating text regions from natural scene images. The main algorithm has two functions: it generates text region candidates, and it veri...
We give a new class of outer bounds on the marginal polytope, and propose a cutting-plane algorithm for efficiently optimizing over these constraints. When combined with a concav...
This work presents a real-time, data-parallel approach for global label assignment on regular grids. The labels are selected according to a Markov random field energy with a Potts...
Christopher Zach, David Gallup, Jan-Michael Frahm,...
In this paper we describe a new method for improving the representation of textures in blends of multiple images based on a Markov Random Field (MRF) algorithm. We show that direc...