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
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
2017
Ufer, N and Ommer, B (2017). Deep Semantic Feature Matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) article (8.88 MB) |
Bautista, M, Fuchs, P and Ommer, B (2017). Learning Where to Drive by Watching Others. Proceedings of the German Conference Pattern Recognition. Springer-Verlag, Basel. 1 |
Wahl, A - S, Büchler, U, Brändli, A, Brattoli, B, Musall, S, Kasper, H, Ineichen, B V, Helmchen, F, Ommer, B and Schwab, M E (2017). Optogenetically stimulating the intact corticospinal tract post-stroke restores motor control through regionalized functional circuit formation. Nature Communications. (ASW & UB contributed equally; BO and MES contributed equally). https://www.nature.com/articles/s41467-017-01090-6 |
2016
Bell, P and Ommer, B (2016). Digital Connoisseur? How Computer Vision Supports Art History. Connoisseurship nel XXI secolo. Approcci, Limiti, Prospettive, A. Aggujaro & S. Albl (ed.). Artemide, Rome |
Bautista, M, Sanakoyeu, A, Sutter, E and Ommer, B (2016). CliqueCNN: Deep Unsupervised Exemplar Learning. Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS). MIT Press, Barcelona. https://arxiv.org/abs/1608.08792 Article (5.79 MB) |
2015
Rubio, J C and Ommer, B (2015). Regularizing Max-Margin Exemplars by Reconstruction and Generative Models. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE. 4213--4221 Technical Report (2.8 MB) |
Antic, B, Büchler, U, Wahl, A - S, Schwab, M E and Ommer, B (2015). Spatiotemporal Parsing of Motor Kinematics for Assessing Stroke Recovery. Medical Image Computing and Computer-Assisted Intervention. Springer Article (2.24 MB) |
Antic, B and Ommer, B (2015). Per-Sample Kernel Adaptation for Visual Recognition and Grouping. Proceedings of the IEEE International Conference on Computer Vision. IEEE Technical Report (1.58 MB) |
Rubio, J C, Eigenstetter, A and Ommer, B (2015). Generative Regularization with Latent Topics for Discriminative Object Recognition. Pattern Recognition. Elsevier. 48 3871--3880 Technical Report (5.49 MB) |
Yarlagadda, P and Ommer, B (2015). Beyond the Sum of Parts: Voting with Groups of Dependent Entities. IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE. 37 1134--1147. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6926849 |
Bell, P and Ommer, B (2015). Training Argus. Kunstchronik. Monatsschrift für Kunstwissenschaft, Museumswesen und Denkmalpflege. Zentralinstitut für Kunstgeschichte. 68 414--420 |
Antic, B and Ommer, B (2015). Spatio-temporal Video Parsing for Abnormality Detection. arXiv. abs/1502.06235. http://arxiv.org/abs/1502.06235 Technical Report (4.61 MB) |
2014
Antic, B and Ommer, B (2014). Learning Latent Constituents for Recognition of Group Activities in Video. Proceedings of the European Conference on Computer Vision (ECCV) (Oral). Springer. 33--47 Technical Report (4.54 MB) |
Eigenstetter, A, Takami, M and Ommer, B (2014). Randomized Max-Margin Compositions for Visual Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE. 3590--3597 Technical Report (8.01 MB) |
Kandemir, M, Rubio, J C, Schmidt, U, Wojek, C, Welbl, J, Ommer, B and Hamprecht, F A (2014). Event Detection by Feature Unpredictability in Phase-Contrast Videos of Cell Cultures. Medical Image Computing and Computer-Assisted Intervention. Springer. 154--161 Technical Report (2 MB) |
Takami, M, Bell, P and Ommer, B (2014). Offline Learning of Prototypical Negatives for Efficient Online Exemplar SVM. Winter Conference on Applications of Computer Vision. IEEE. 377--384. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6836075 |
Kandemir, M, Rubio, J C, Schmidt, U, Welbl, J, Ommer, B and Hamprecht, F A (2014). Event Detection by Feature Unpredictability in Phase-Contrast Videos of Cell Cultures. MICCAI. Proceedings. Springer. 154-161 Paper (2 MB) |
Takami, M, Bell, P and Ommer, B (2014). An Approach to Large Scale Interactive Retrieval of Cultural Heritage. Eurographics Workshop on Graphics and Cultural Heritage. The Eurographics Association Technical Report (7.94 MB) |
Monroy, A, Bell, P and Ommer, B (2014). Morphological Analysis for Investigating Artistic Images. Image and Vision Computing. Elsevier. 32 414--423 Technical Report (2.86 MB) |
Wahl, A - S, Omlor, W, Rubio, J C, Chen, J L, Zheng, H, Schröter, A, Gullo, M, Weinmann, O, Kobayashi, K, Helmchen, F, Ommer, B and Schwab, M E (2014). Asynchronous Therapy Restores Motor Control by Rewiring of the Rat Corticospinal Tract after Stroke. Science. American Association for The Advancement of Science. 344 1250--1255. http://www.sciencemag.org/content/344/6189/1250 |
2013
Ommer, B (2013). The Role of Shape in Visual Recognition. Shape Perception in Human Computer Vision: An Interdisciplinary Perspective. Springer. 373--385 Technical Report (8.18 MB) |
Yarlagadda, P, Monroy, A, Carque, B and Ommer, B (2013). Towards a Computer-based Understanding of Medieval Images. Scientific Computing & Cultural Heritage. Springer. 89--97. http://link.springer.com/chapter/10.1007/978-3-642-28021-4_10 |
Garbe, C S and Ommer, B (2013). Parameter Estimation in Image Processing and Computer Vision. Model Based Parameter Estimation: Theory and Applications. Springer. 311--334 Technical Report (928 KB) |
Monroy, A, Bell, P and Ommer, B (2013). A Morphometric Approach to Reception Analysis of Premodern Art. Scientific Computing & Cultural Heritage Technical Report (17.75 MB) |
Arnold, M, Bell, P and Ommer, B (2013). Automated Learning of Self-Similarity and Informative Structures in Architecture. Scientific Computing & Cultural Heritage |
Antic, B, Milbich, T and Ommer, B (2013). Less is More: Video Trimming for Action Recognition. Proceedings of the IEEE International Conference on Computer Vision, Workshop on Understanding Human Activities: Context and Interaction. IEEE. 515--521 Technical Report (984.89 KB) |
Bell, P, Schlecht, J and Ommer, B (2013). Nonverbal Communication in Medieval Illustrations Revisited by Computer Vision and Art History. Visual Resources Journal, Special Issue on Digital Art History. Taylor & Francis. 29 26--37. http://www.tandfonline.com/doi/abs/10.1080/01973762.2013.761111 |
2012
Yarlagadda, P, Eigenstetter, A and Ommer, B (2012). Learning Discriminative Chamfer Regularization. BMVC. Springer. 1--11. http://www.bmva.org/bmvc/2012/BMVC/paper020/paper020.pdf |
Eigenstetter, A and Ommer, B (2012). Visual Recognition using Embedded Feature Selection for Curvature Self-Similarity. Proceedings of the Conference on Advances in Neural Information Processing Systems. MIT Press. 377--385 Technical Report (3.27 MB) |
Yarlagadda, P and Ommer, B (2012). From Meaningful Contours to Discriminative Object Shape. Proceedings of the European Conference on Computer Vision. Springer. 7572 766--779 Technical Report (4.58 MB) |
Monroy, A, Bell, P and Ommer, B (2012). Shaping Art with Art: Morphological Analysis for Investigating Artistic Reproductions. Proceedings of the European Conference on Computer Vision, Workshop on VISART. Springer. 7583 571--580 Technical Report (7 MB) |
Eigenstetter, A, Yarlagadda, P and Ommer, B (2012). Max-Margin Regularization for Reducing Accidentalness in Chamfer Matching. Proceedins of the Aian Conference on Computer Vision. Springer. 152--163 Technical Report (7.31 MB) |
Antic, B and Ommer, B (2012). Robust Multiple-Instance Learning with Superbags. Proceedings of the Aian Conference on Computer Vision (ACCV) (Oral). Springer. 242--255 Technical Report (319.58 KB) |
Monroy, A and Ommer, B (2012). Beyond Bounding-Boxes: Learning Object Shape by Model-driven Grouping. IEEE Transactions on Pattern Analysis and Machine Intelligence. Springer. 7574 582--595 Technical Report (1.58 MB) |
2011
Antic, B and Ommer, B (2011). Video Parsing for Abnormality Detection. Proceedings of the IEEE International Conference on Computer Vision. IEEE. 2415--2422 Technical Report (990.21 KB) |
Schlecht, J and Ommer, B (2011). Contour-based Object Detection. BMVC. 1--9 Technical Report (2.62 MB) |
Schlecht, J, Carque, B and Ommer, B (2011). Detecting Gestures in Medieval Images. Proceedings of the International Conference on Image Processing. IEEE. 1309--1312 Technical Report (1.61 MB) |
Monroy, A, Carque, B and Ommer, B (2011). Reconstructing the Drawing Process of Reproductions from Medieval Images. Proceedings of the International Conference on Image Processing. IEEE. 2974--2977. https://hciweb.iwr.uni-heidelberg.de/compvis/research/manesse/ Technical Report (2.43 MB) |
Monroy, A, Kröger, T, Arnold, M and Ommer, B (2011). Parametric Object Detection for Iconographic Analysis. Scientific Computing & Cultural Heritage. http://www.academia.edu/9439693/Parametric_Object_Detection_for_Iconographic_Analysis |
Yarlagadda, P, Monroy, A, Carque, B and Ommer, B (2011). Top-down Analysis of Low-level Object Relatedness Leading to Semantic Understanding of Medieval Image Collections. Conference on Computer Vision and Image Analysis of Art II. 7869 61--69 Technical Report (11.06 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