Skip navigation
Skip navigation

Alphabet SOUP: A Framework for Approximate Energy Minimization

Gould, Stephen; Amat, Fernando; Koller, Daphne


Many problems in computer vision can be modeled using conditional Markov random fields (CRF). Since finding the maximum a posteriori (MAP) solution in such models is NP-hard, much attention in recent years has been placed on finding good approximate solutions. In particular, graph-cut based algorithms, such as α-expansion, are tremendously successful at solving problems with regular potentials. However, for arbitrary energy functions, message passing algorithms, such as max-product belief...[Show more]

CollectionsANU Research Publications
Date published: 2009
Type: Conference paper
Source: Proceeings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009)
DOI: 10.1109/CVPRW.2009.5206650


File Description SizeFormat Image
01_Gould_Alphabet_SOUP:_A_Framework_for_2009.pdf779.23 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator