Sciweavers

821 search results - page 25 / 165
» Labeling images with a computer game
Sort
View
PAMI
2007
176views more  PAMI 2007»
13 years 7 months ago
Approximate Labeling via Graph Cuts Based on Linear Programming
A new framework is presented for both understanding and developing graph-cut based combinatorial algorithms suitable for the approximate optimization of a very wide class of MRFs ...
Nikos Komodakis, Georgios Tziritas
LICS
2008
IEEE
14 years 2 months ago
A Neutral Approach to Proof and Refutation in MALL
We propose a setting in which the search for a proof of B or a refutation of B (a proof of ¬B) can be carried out simultaneously: this is in contrast to the usual approach in aut...
Olivier Delande, Dale Miller
DAGM
2010
Springer
13 years 9 months ago
Uncertainty Driven Multi-scale Optimization
This paper proposes a new multi-scale energy minimization algorithm which can be used to efficiently solve large scale labelling problems in computer vision. The basic modus operan...
Pushmeet Kohli, Victor S. Lempitsky, Carsten Rothe...
CIVR
2004
Springer
117views Image Analysis» more  CIVR 2004»
14 years 1 months ago
Using Maximum Entropy for Automatic Image Annotation
In this paper, we propose the use of the Maximum Entropy approach for the task of automatic image annotation. Given labeled training data, Maximum Entropy is a statistical techniqu...
Jiwoon Jeon, R. Manmatha
EMMCVPR
2011
Springer
12 years 7 months ago
SlimCuts: GraphCuts for High Resolution Images Using Graph Reduction
Abstract. This paper proposes an algorithm for image segmentation using GraphCuts which can be used to efficiently solve labeling problems on high resolution images or resource-lim...
Björn Scheuermann, Bodo Rosenhahn