Björn Ommer

Postdoctoral Research Scholar in Computer Science

 
UC Berkeley
Dept. of EECS

527 Soda Hall
University of California, Berkeley
Berkeley CA, 94720-1776

Tel:    +1 (510) 642-9582
Fax:   +1 (510) 642-5775
Email: ommer (at) eecs (dot) berkeley (dot) edu
           

That's me


Brief C.V.

Björn Ommer has studied computer science together with physics as a minor subject at the Rheinische Friedrich-Wilhelms-Universität Bonn, Germany. In 2003 he was awarded a diploma (~M.Sc.) in computer science---his diploma thesis focused on visual grouping based on perceptual organization and compositionality.

After that he pursued his doctoral studies at ETH Zurich Switzerland in the Pattern Analysis and Machine Learning Group headed by Joachim M. Buhmann. He received his Ph.D. degree from ETH Zurich in 2007 for his dissertation "Learning the Compositional Nature of Objects for Visual Recognition".

Currently, Björn holds a post-doc position in the Computer Vision Group of Jitendra Malik at UC Berkeley.


Research Areas

Computer vision, machine learning, cognitive science; esp.: visual object recognition, compositionality, graphical models and perceptual organization


Publications


Björn Ommer and Joachim M. Buhmann,
Compositional Object Recognition, Segmentation, and Tracking in Video,
in: International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR'07), LNCS 4679, Springer, 2007.

Christian Sigg, Bernd Fischer, Björn Ommer, Volker Roth, and Joachim M. Buhmann,
Nonnegative CCA for Audiovisual Source Separation,
in: IEEE International Workshop on Machine Learning for Signal Processing'07, IEEE, 2007.

Björn Ommer and Joachim M. Buhmann,
Learning the Compositional Nature of Visual Objects,
in: CVPR'07, IEEE, 2007.

Volker Roth and Björn Ommer
Exploiting Low-level Image Segmentation for Object Recognition,
in: Pattern Recognition (Symposium of the DAGM), LNCS 4174, Springer, 2006.

Björn Ommer, Michael Sauter and Joachim M. Buhmann,
Learning Top-Down Grouping of Compositional Hierarchies for Recognition,
in: CVPR'06 (POCV), IEEE 2006.

Björn Ommer and Joachim M. Buhmann,
Learning Compositional Categorization Models,
in: ECCV'06, LNCS 3953, Springer, 2006.

Björn Ommer and Joachim M. Buhmann,
Object Categorization by Compositional Graphical Models,
in: EMMCVPR'05, LNCS 3757, Springer, 2005.

 

Björn Ommer and Joachim M. Buhmann,
A Compositionality Architecture for Perceptual Feature Grouping,
in: EMMCVPR'03, LNCS 2683, pp. 275-290, Springer, 2003.


Teaching


Links


UC Berkeley

Computer Vision Group @ UC Berkeley

Pattern Analysis and Machine Learning Group @ ETH Zurich