Bogdan Savchynskyy

Scopus Id 15061960700

Google Scholar

 Degree: Ph D. (Eng.), 2007.

Research interests: optimization in computer vision and machine learning

Affiliation: Universität Heidelberg, Germany, Akademischer Rat

Education: National Technical University of Ukraine “Kyiv Polytechnic Institute”, 2002

Contact: bogdan.savchynskyy@iwr.uni-heidelberg.de

Publications

1. Tourani, A. Shekhovtsov, C. Rother and B. Savchynskyy. MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models. Proceedings of ECCV 2018.
2. Haller, P. Swoboda and B. Savchynskyy. Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation. Proceedings of AAAI 2018.
3. Arnab, S. Zheng, S. Jayasumana, B. Romera-Paredes, M. Larsson, A. Kirillov, B. Savchynskyy, C. Rother, F. Kahl, Philip H. S. Torr. Conditional Random Fields meet Deep Neural Networks for Semantic Segmentation. IEEE Signal Processing Magazine 2018.
4. Shekhovtsov, P. Swoboda and B. Savchynskyy. Maximum Persistency via Iterative Relaxed Inference with Graphical Models. IEEE Transactions on PAMI 2017.
5. Swoboda, J. Kuske, B. Savchynskyy. A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems. Proceedings of CVPR 2017.