Postdoctoral Researcher
Computer Vision Group
Technical University of Munich

Short Bio

Csaba Domokos graduated from the University of Szeged, Hungary and received Master's degrees in Computer Science, Informatics (Institute of Informatics) and Mathematics (Bolyai Institute) in 2004, 2006 and 2010, respectively. He made his Ph.D. research (2006-2010) under the supervision of Prof. Zoltan Kato at the Department of Image Processing and Computer Graphics, University of Szeged. He obtained the Ph.D. degree (summa cum laude) in 2011. After working as a scientific programmer in the industry for one and half year, in 2012 he joined to the Learn­ing and Vi­sion Re­search GroupNa­tion­al Uni­ver­si­ty of Sin­ga­pore, di­rect­ed by Prof. Shuicheng Yan, where he worked as a Research Fellow (i.e. post-doctoral researcher). In 2014-2015 he also worked as a post-doctoral researcher at the Computer Vision and Machine Learning GroupInstitute of Science and Technology Austria (IST Austria), directed by Prof. Christoph H. Lampert. Since April 2015 he is an Alexander von Humboldt Fellow (postdoc) at the Computer Vision Group, Technical University of Munich, directed by Prof. Dr. Daniel Cremers.

Research Interest

My research interests include

  • Semantic image segmentation
    Recently I have mainly focused on developing semantic segmentation methods via Probabilistic Graphical Models (e.g., Conditional Random Fields) and Deep Learning.
  • Image registration and shape matching
  • Combinatorial Optimization
  • Low-rank approximation of matrices

You can also consult the list of my publications.


This semester I will again offer the lectures on Probabilistic Graphical Models in Computer Vision.