Jörg Hendrik Kappes
Jörg Hendrik Kappes
Heidelberg Engineering
Bestätigte E-Mail-Adresse bei math.uni-heidelberg.de
Titel
Zitiert von
Zitiert von
Jahr
A comparative study of modern inference techniques for discrete energy minimization problems
J Kappes, B Andres, F Hamprecht, C Schnorr, S Nowozin, D Batra, S Kim, ...
Proceedings of the IEEE conference on computer vision and pattern …, 2013
1972013
A comparative study of modern inference techniques for structured discrete energy minimization problems
JH Kappes, B Andres, FA Hamprecht, C Schnörr, S Nowozin, D Batra, ...
International Journal of Computer Vision 115 (2), 155-184, 2015
1812015
Convex multi-class image labeling by simplex-constrained total variation
J Lellmann, J Kappes, J Yuan, F Becker, C Schnörr
International conference on scale space and variational methods in computer …, 2009
1682009
A study of parts-based object class detection using complete graphs
M Bergtholdt, J Kappes, S Schmidt, C Schnörr
International journal of computer vision 87 (1-2), 93, 2010
1672010
Spine detection and labeling using a parts-based graphical model
S Schmidt, J Kappes, M Bergtholdt, V Pekar, S Dries, D Bystrov, ...
Biennial International Conference on Information Processing in Medical …, 2007
1392007
OpenGM: A C++ library for discrete graphical models
B Andres, T Beier, JH Kappes
arXiv preprint arXiv:1206.0111, 2012
1002012
Probabilistic image segmentation with closedness constraints
B Andres, JH Kappes, T Beier, U Köthe, FA Hamprecht
2011 International Conference on Computer Vision, 2611-2618, 2011
942011
Globally optimal image partitioning by multicuts
JH Kappes, M Speth, B Andres, G Reinelt, C Schn
International Workshop on Energy Minimization Methods in Computer Vision and …, 2011
652011
A study of Nesterov's scheme for Lagrangian decomposition and MAP labeling
B Savchynskyy, J Kappes, S Schmidt, C Schnörr
CVPR 2011, 1817-1823, 2011
652011
A bundle approach to efficient MAP-inference by Lagrangian relaxation
JH Kappes, B Savchynskyy, C Schnörr
2012 IEEE Conference on Computer Vision and Pattern Recognition, 1688-1695, 2012
582012
Efficient MRF Energy Minimization via Adaptive Diminishing Smoothing
B Savchynskyy, S Schmidt, J Kappes, C Schnörr
Uncertainty in Artificial Intelligence, UAI-2012, 746--755, 2012
532012
Higher-order segmentation via multicuts
JH Kappes, M Speth, G Reinelt, C Schnörr
Computer Vision and Image Understanding 143, 104-119, 2016
442016
Cut, Glue & Cut: A Fast, Approximate Solver for Multicut Partitioning
T Beier, T Kroeger, J Kappes, U Kothe, F Hamprecht
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2014
402014
Towards efficient and exact MAP-inference for large scale discrete computer vision problems via combinatorial optimization
J Hendrik Kappes, M Speth, G Reinelt, C Schnorr
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2013
402013
Fusion moves for correlation clustering
T Beier, FA Hamprecht, JH Kappes
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015
382015
The Lazy Flipper: Efficient Depth-limited Exhaustive Search in Discrete Graphical Models
B Andres, JH Kappes, T Beier, U Köthe, FA Hamprecht
ECCV 2012, 2012
342012
An empirical comparison of inference algorithms for graphical models with higher order factors using OpenGM
B Andres, JH Kappes, U Köthe, C Schnörr, FA Hamprecht
Joint Pattern Recognition Symposium, 353-362, 2010
342010
Partial optimality by pruning for MAP-inference with general graphical models
P Swoboda, B Savchynskyy, JH Kappes, C Schnorr
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2014
322014
Global MAP-optimality by shrinking the combinatorial search area with convex relaxation
B Savchynskyy, JH Kappes, P Swoboda, C Schnörr
Advances in Neural Information Processing Systems 26, 1950-1958, 2013
242013
Partial optimality via iterative pruning for the Potts model
P Swoboda, B Savchynskyy, J Kappes, C Schnörr
International Conference on Scale Space and Variational Methods in Computer …, 2013
212013
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20