Sciweavers

8 search results - page 1 / 2
» What is optimized in tight convex relaxations for multi-labe...
Sort
View
CVPR
2012
IEEE
11 years 7 months ago
What is optimized in tight convex relaxations for multi-label problems?
In this work we present a unified view on Markov random fields and recently proposed continuous tight convex relaxations for multi-label assignment in the image plane. These rel...
Christopher Zach, Christian Hane, Marc Pollefeys
ICCV
2011
IEEE
12 years 4 months ago
Tight Convex Relaxations for Vector-Valued Labeling Problems
The multi-label problem is of fundamental importance to computer vision, yet finding global minima of the associated energies is very hard and usually impossible in practice. Rec...
Evgeny Strekalovskiy, Bastian Goldluecke, Daniel C...
IVC
2007
114views more  IVC 2007»
13 years 4 months ago
Evaluation of a convex relaxation to a quadratic assignment matching approach for relational object views
We introduce a convex relaxation approach for the quadratic assignment problem to the field of computer vision. Due to convexity, a favourable property of this approach is the ab...
Christian Schellewald, Stefan Roth, Christoph Schn...
ICML
2006
IEEE
14 years 5 months ago
Quadratic programming relaxations for metric labeling and Markov random field MAP estimation
Quadratic program relaxations are proposed as an alternative to linear program relaxations and tree reweighted belief propagation for the metric labeling or MAP estimation problem...
Pradeep D. Ravikumar, John D. Lafferty
ICCV
2007
IEEE
14 years 6 months ago
Globally Optimal Affine and Metric Upgrades in Stratified Autocalibration
We present a practical, stratified autocalibration algorithm with theoretical guarantees of global optimality. Given a projective reconstruction, the first stage of the algorithm ...
Manmohan Krishna Chandraker, Sameer Agarwal, David...