Prof. Dr. Björn Ommer

Professor for Computer Vision

Heidelberg Collaboratory for Image Processing (HCI) &
Interdisciplinary Center for Scientific Computing (IWR),
Heidelberg University

Mathematikon (INF 205), Room 4.321
HCI / IWR, Uni Heidelberg
D-69120 Heidelberg, Germany
Tel.(office): +49 6221/54-14806
Tel.(secret.): +49 6221/54-14807
Fax: +49 6221/54-14814
Email: ommer (at) uni-heidelberg (dot) de

Open PhD and PostDoc Positions in Computer Vision
Bjorn


Brief C.V.


Björn Ommer is a full professor for Scientific Computing and leads the Computer Vision Group at Heidelberg University.

He has studied computer science together with physics as a minor subject at the University of Bonn, Germany. His diploma (~M.Sc.) 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" which was awarded the ETH Medal.

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

He serves as an associate editor for the journal IEEE T-PAMI and previously for Pattern Recognition Letters. Björn is one of the directors of the HCI and of the IWR, part of the ELLIS unit Heidelberg, principle investigator in the research training group 1653 ("Spatio/Temporal Graphical Models and Applications in Image Analysis"), and a member of the executive board and scientific committee of the Heidelberg Graduate School HGS MathComp. He has served as Area Chair for ICCV'21, CVPR'20, and ECCV'18 and organized the 2011 DAGM Workshop on Unsolved Problems in Pattern Recognition.



Research Interests


Computer vision, machine learning, cognitive science, biomedical image analysis, and the digital humanities; esp.:
semantic scene understanding, visual synthesis and interpretable AI, deep learning & self-supervision, deep metric and representation learning, object recognition in images and videos, behavior analysis, and their interdisciplinary applications.

»» Research pages

Publications


Main publications' list »» Publications of the Ommer lab

News:
  • NeurIPS'20 ORAL on cINNs for Network-to-Network Translation
  • T-PAMI publication accepted on
    • Shared feature learning for Deep Metric Learning
  • PLoS ONE publication on weakly supervised transliteration alignment for cuneiform sign detection
  • GCPR'20 ORAL on unsupervised part learning by disentangling
  • 2 papers accepted at ECCV'20 on:
    • Explainable AI and semantic image manipulation
    • Deep Metric Learning beyond discriminative features
  • ICML'20 paper accepted on
    • Generalization in Deep Metric Learning
  • Best Paper Award at CVPR'20—AI for Content Creation WS on
    • Interpretable Models for Visual Synthesis
  • 3 papers accepted at CVPR'20 on:
    • Explainable AI
    • Reinforcement Learning for Deep Metric Learning
    • Unsupervised Behavior Analytics.
  • 3 papers accepted at ICCV'19
  • Best paper finalist at CVPR'19
  • 3 papers accepted at CVPR'19

2011

Monroy, A, Eigenstetter, A and Ommer, B (2011). Beyond Straight Lines - Object Detection using Curvature. International Conference on Image Processing (ICIP). IEEEPDF icon Technical Report (2.65 MB)

2010

Yarlagadda, P, Monroy, A and Ommer, B (2010). Voting by Grouping Dependent Parts. Proceedings of the European Conference on Computer Vision. Springer. 6315 197--210PDF icon Technical Report (2.99 MB)
Wagner, J and Ommer, B (2010). Efficiently Clustering Earth Mover's Distance. Proceedins of the Aian Conference on Computer Vision. Springer. 477--488PDF icon Technical Report (841.98 KB)
Yarlagadda, P, Monroy, A, Carque, B and Ommer, B (2010). Recognition and Analysis of Objects in Medieval Images. Proceedins of the Aian Conference on Computer Vision, Workshop on e-Heritage. Springer. 296--305PDF icon Technical Report (2.76 MB)
Ommer, B and Buhmann, J M (2010). Learning the Compositional Nature of Visual Object Categories for Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE. 32 501--516PDF icon Technical Report (2.78 MB)

2009

Ommer, B and Malik, J (2009). Multi-scale Object Detection by Clustering Lines. Proceedings of the IEEE International Conference on Computer Vision. IEEE. 484--491PDF icon Technical Report (3.18 MB)
Keränen, S V E, DePace, A, Hendriks, C L Luengo, Fowlkes, C, Arbelaez, P, Ommer, B, Brox, T, Henriquez, C, Wunderlich, Z, Eckenrode, K, Fischer, B, Hammonds, A and Celniker, S E (2009). Computational Analysis of Quantitative Changes in Gene Expression and Embryo Morphology between Species. Evolution-The Molecular Landscape
Yarlagadda, P, Monroy, A, Carque, B and Ommer, B (2009). Towards a Computer-based Understanding of Medieval Images. Scientific Computing & Cultural Heritage. Springer. 89--97. http://link.springer.com/chapter/10.1007%2F978-3-642-28021-4_10#page-1
Ommer, B, Mader, T and Buhmann, J M (2009). Seeing the Objects Behind the Dots: Recognition in Videos from a Moving Camera. International Journal of Computer Vision. Springer. 83 57--71PDF icon Technical Report (9.61 MB)

2008

Ommer, B (2008). Seeing The Objects Behind The Parts: Learning Compositional Models For Visual Recognition. VDM Verlag. http://www.amazon.com/Seeing-Objects-Behind-Parts-Compositional/dp/3639021444/ref=sr_1_1?ie=UTF8&s=books&qid=1232659136&sr=1-1

2007

Ommer, B and Buhmann, J M (2007). Compositional Object Recognition, Segmentation, and Tracking in Video. Proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition. Springer. 4679 318--333PDF icon Technical Report (2.78 MB)
Sigg, C, Fischer, B, Ommer, B, Roth, V and Buhmann, J M (2007). Nonnegative CCA for Audiovisual Source Separation. International Workshop on Machine Learning for Signal Processing. IEEE. 253--258PDF icon Technical Report (1.27 MB)
Ommer, B and Buhmann, J M (2007). Learning the Compositional Nature of Visual Objects. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE. 1--8PDF icon Technical Report (2.78 MB)

2006

Roth, V and Ommer, B (2006). Exploiting Low-level Image Segmentation for Object Recognition. Pattern Recognition, Symposium of the DAGM. Springer. 4174 11--20PDF icon Technical Report (473.84 KB)
Ommer, B, Sauter, M and M., B J (2006). Learning Top-Down Grouping of Compositional Hierarchies for Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Workshop on Perceptual Organization in Computer Vision. IEEE. 194--194PDF icon Technical Report (358.98 KB)
Ommer, B and Buhmann, J M (2006). Learning Compositional Categorization Models. Proceedings of the European Conference on Computer Vision. Springer. 3953 316--329PDF icon Technical Report (1.35 MB)

2005

Ommer, B and Buhmann, J M (2005). Object Categorization by Compositional Graphical Models. Proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition. Springer. 3757 235--250PDF icon Technical Report (2.07 MB)

2003

Ommer, B and Buhmann, J M (2003). A Compositionality Architecture for Perceptual Feature Grouping. Proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition. Springer. 2683 275--290PDF icon Technical Report (2.89 MB)

Pages



Selected Reports and Publications in Popular Science


"Das Objekt jenseits der Digitalisierung“, Deutsches Museum, 12/2018, The Future of the Digital Humanities beyond Digitization.

"Der Geist aus dem Computer“, Bild der Wissenschaft, 10/2018, covering part of our work in the digital humanities.

AI Learned How To Generate Human Appearance, Video on Two-Minute-Papers about our CVPR'18 paper on disentangling human behavior and appearance.

Painter AI Fools Art Historians, Video on Two-Minute-Papers about our ECCV'18 paper on artistic style transfer.

Improving Stroke Treatment Through Machine Learning, report on interdisciplinary project with neuroscientists from ETH Zurich.

Improving Motor Skills after Stroke, report on interdisciplinary project with neuroscientists from ETH Zurich.

TV documentary on our interdisciplinary work featured by RNF Television.

Björn Ommer, Bilder im Chaos, in: Universitas 68(810): 46-55, 2013.

Björn Ommer, From Chaos to Image - The Grammar of Patterns, in: Ruperto Carola Magazine, 03/2013.

Björn Ommer, Vom Pixel zum Bild - Wie Computer das Sehen lernen und die Forschungsarbeiten von Geistes- und Naturwissenschaftlern unterstützen können, in: Ruperto Carola Magazine, 02/2011.

Image Recognition: Teaching Computers to See, in: Young Talents -Innovative Ideas - Viable Alliances, 2011.

Automatische Bildanalyse - Blinde Computer sollen sehen lernen, in: Spiegel Online news report, 22.07.2011.

Dem Computer das Sehen beibringen, in: Rhein-Neckar-Zeitung newspaper article, 19.04.2010.



Teaching


Computer Vision Group: Teaching Website


Links


Computer Vision Group @ Uni Heidelberg

HCI @ Uni Heidelberg

University of Heidelberg

Computer Vision Group @ UC Berkeley

Institute for Machine Learning @ ETH Zurich