Jörg Hendrik Kappes

HCI->Jörg Hendrik Kappes

Dr. Jörg Hendrik Kappes


Heidelberg Collaboratory for Image Processing (HCI)
Heidelberg University
Speyerer Strasse 6, G 2.07
D-69115 Heidelberg

Tel: ++49-6221-54 5272
Fax: ++49-6221-54 8850
Email: kappes AT math.uni-heidelberg.de

Links: Google Scholar  Research Gate

Scientific Interests

My main research interests are combinatorial optimization, graphical models, and its application in computer vision and image analysis.

Projects

  • openGM - A C++-Library for Infernce on Graphical Models [Project website]
  • Combinatorial / Polyhedral Optimization
  • Part-Based Object Detection
  • Unsupervised Image Segmentation

Community

  • Reviewer, computer vision and machine learning conferences: ECCV, ICCV, CVPR, ICML, NIPS
  • Reviewer, computer vision and machine learning journals: TPAMI, JMIV, IJCV
  • Reviewer, mathematical journals: Statistics & Probability Letters

CV

  1999-2004 Studies in Computer Engineering at the University of Mannheim
    2004 Diploma Thesis: Fitting Articulated Bodies to Images and Image Sequences
    2005-2010 Research Assistent and Doctoral/PhD-Student in the Image and Pattern Analysis Group, Department of Mathematics and Computer Science, Heidelberg University (former Computer Vision, Graphics and Pattern Recognition Group, Department of Mathematics and Computer Science, University of Mannheim)
    2010/2011 Doctoral/PhD Thesis: Inference on Highly-Connected Discrete Graphical Models with Applications to Visual Object Recognition
    2011-2014 PostDoc in the Image and Pattern Analysis Group, Department of Mathematics and Computer Science, Heidelberg University
    2014-2015 PostDoc at the Heidelberg Collaboratory on Image Processing, Heidelberg University

Publications

2011

Kappes, J H (2011). Inference on Highly-Connected Discrete Graphical Models with Applications to Visual Object Recognition. Ruprecht-Karls-Universität Heidelberg, Faculty of Mathematics and Computer Sciences. http://www.ub.uni-heidelberg.de/archiv/11872/

2010

Kappes, J H, Schmidt, S and Schnörr, C (2010). MRF Inference by k-Fan Decomposition and Tight Lagrangian Relaxation. European Conference on Computer Vision (ECCV). Springer Berlin / Heidelberg. 6313 735--747PDF iconTechnical Report (1.49 MB)
Andres, B, Kappes, J H, Köthe, U, Schnörr, C and Hamprecht, F A (2010). An Empirical Comparison of Inference Algorithms for Graphical Models with Higher Order Factors Using OpenGM. Pattern Recognition, Proc.~32th DAGM Symposium. 353-362
Andres, B, Kappes, J H, Köthe, U, Schnörr, C and Hamprecht, F A (2010). An Empirical Comparison of Inference Algorithms for Graphical Models with Higher Order Factors Using OpenGM. Pattern Recognition, Proc.~32th DAGM SymposiumPDF iconTechnical Report (218.43 KB)
Kappes, J H, Schmidt, S and Schnörr, C (2010). MRF Inference by k-Fan Decomposition and Tight Lagrangian Relaxation. European Conference on Computer Vision (ECCV). Springer. 6313 735--747
Bergtholdt, M, Kappes, J H, Schmidt, S and Schnörr, C (2010). A Study of Parts-Based Object Class Detection Using Complete Graphs. Int.~J.~Comp.~Vision. 87 93-117. http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s11263-009-0209-1PDF iconTechnical Report (2.18 MB)
Andres, B, Kappes, J H, Köthe, U and Hamprecht, F A (2010). The Lazy Flipper: MAP Inference in Higher-Order Graphical Models by Depth-limited Exhaustive Search. ArXiv e-prints. http://arxiv.org/abs/1009.4102PDF iconTechnical Report (625.06 KB)

2009

Lellmann, J, Kappes, J H, Yuan, J, Becker, F and Schnörr, C (2009). Convex Multi-Class Image Labeling by Simplex-Constrained Total Variation. Scale Space and Variational Methods in Computer Vision (SSVM 2009). Springer. 5567 150-162PDF iconTechnical Report (1.75 MB)
Lellmann, J, Kappes, J H, Yuan, J, Becker, F, Schnörr, C, Mórken, K and Lysaker, M (2009). Convex Multi-Class Image Labeling by Simplex-Constrained Total Variation. Scale Space and Variational Methods in Computer Vision (SSVM 2009). Springer. 5567 150-162

2008

Kappes, J H and Schnörr, C (2008). MAP-Inference for Highly-Connected Graphs with DC-Programming. Pattern Recognition -- 30th DAGM Symposium. Springer Verlag. 5096 1--10PDF iconTechnical Report (1.91 MB)
Lellmann, J, Kappes, J H, Yuan, J, Becker, F and Schnörr, C (2008). Convex Multi-Class Image Labeling By Simplex-Constrained Total Variation. IWR, University of Heidelberg. http://www.ub.uni-heidelberg.de/archiv/8759/PDF iconTechnical Report (2.6 MB)

2007

Schmidt, S, Kappes, J H, Bergtholdt, M, Pekar, V, Dries, S, Bystrov, D and Schnörr, C (2007). Spine Detection and Labeling Using a Parts-Based Graphical Model. Proc. 20th International Conference on Information Processing in Medical Imaging (IPMI 2007). Springer. 4584 122-133PDF iconTechnical Report (1.46 MB)
Karim, R, Bergtholdt, M, Kappes, J H and Schnörr, C (2007). Greedy-Based Design of Sparse Two-Stage SVMs for Fast Classification. Pattern Recognition -- 29th DAGM Symposium. Springer. 4713 395-404PDF iconTechnical Report (491.56 KB)

2006

Bergtholdt, M, Kappes, J H and Schnörr, C (2006). Learning of Graphical Models and Efficient Inference for Object Class Recognition. Proc.~DAGM 2006. Springer. 375-388 375-388

Pages