Martin Kiefel

Address: Spemannstr. 41
72076 Tübingen
Room number: 1.A.20
Fax: +49 7071 601 552
E-Mail: martin.kiefel
Print page    
Picture of Kiefel, Martin

Martin Kiefel

Position: PhD Student  Unit: Schölkopf

I am interested in efficient inference methods for computer vision. What makes models stand out to allow fast inference and how push the computational burden towards training time? In particular, I am working on human pose estimation from single images, a challenging structured prediction problem.

References per page: Year: Medium:

Show abstracts

Articles (1):

Hennig P Person and Kiefel M Person (2013) Quasi-Newton Methods: A New Direction Journal of Machine Learning Research 14 807-829.

Conference papers (4):

Kiefel M Person and Gehler P Person (2014) Human Pose Estimation with Fields of Parts In: 13th European Conference on Computer Vision, ECCV 2014. accepted
Kiefel M Person, Schuler CH Person and Hennig P Person (2014) Probabilistic Progress Bars 36th German Conference on Pattern Recognition (GCPR) 2014. accepted
Hennig P Person and Kiefel M Person (2012) Quasi-Newton Methods: A New Direction 29th International Conference on Machine Learning (ICML 2012), 1-8.
Gehler P Person, Rother C , Kiefel M Person, Zhang L Person and Schölkopf B Person (2011) Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance In: Advances in Neural Information Processing Systems 24, (Ed) J Shawe-Taylor, RS Zemel, PL Bartlett, FCN Pereira and KQ Weinberger, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011), Curran Associates, Inc., Red Hook, NY, USA, 765-773.

Export as:
BibTeX, XML, Pubman, Edoc