publications <- back to the main page of Dr. Bogdan Savchynskyy

Publications:

2024:

  • Max Kahl, Sebastian Stricker, Lisa Hutschenreiter, Florian Bernard, Bogdan Savchynskyy
    Unlocking the Potential of Operations Research for Multi-Graph Matching
    arXiv:2406.18215 [pdf] [code]
  • Siddharth Tourani, Carsten Rother, Muhammad Haris Khan, Bogdan Savchynskyy
    Unsupervised Deep Graph Matching Based on Cycle Consistency
    AAAI 2024 [extended version] [code] [poster]
2023:

  • Max Kahl, Bogdan Savchynskyy
    Analysis and Generalization of the HiPPI Algorithm for Multi-Graph Matching
    Techreport 2023 [pdf]
  • Siddharth Tourani, Carsten Rother, Muhammad Haris Khan, Bogdan Savchynskyy
    Unsupervised Deep Graph Matching Based on Cycle Consistency
    ArXiv:2307.08930 [pdf]
  • Tomas Dlask, Bogdan Savchynskyy
    Relative-Interior Solution for (Incomplete) Linear Assignment Problem with Applications to Quadratic Assignment Problem
    ArXiv:2301.11201 [pdf]
2022:

  • S. Haller, L. Feineis, L.Hutschenreiter, C. Rother, D. Kainmueller, P. Swoboda, B. Savchynskyy
    A Comparative Study of Graph Matching Algorithms in Computer Vision
    Accepted to ECCV 2022 [pdf] [project page]
  • Paul Swoboda, Andrea Hornakova, Paul Roetzer, Bogdan Savchynskyy, Ahmed Abbas
    Structured Prediction Problem Archive
    ArXiv:2202.03574 [pdf]
2021:

  • L.Hutschenreiter, S. Haller, L. Feineis, C. Rother, D. Kainmueller, B. Savchynskyy
    Fusion Moves for Graph Matching
    ICCV 2021 oral [pdf] [project page] [slides] [poster]
2020:

2019:

2018:

  • S. Tourani, A. Shekhovtsov, C. Rother and B. Savchynskyy
    MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
    ECCV 2018. [pdf] [poster] [Project page]
  • S. Haller, P. Swoboda and B. Savchynskyy
    Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation
    Accepted to AAAI 2018. [pdf] [code] [Project page]
  • A. 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
    Accepted to IEEE Signal Processing Magazine 2018. [pdf]
2017:

  • A. Shekhovtsov, P. Swoboda and B. Savchynskyy
    Maximum Persistency via Iterative Relaxed Inference with Graphical Models
    PAMI 2017. [pdf] [Project page]
  • P. Swoboda, J. Kuske, B. Savchynskyy
    A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems
    CVPR 2017. [pdf] [poster] [code]
  • P. Swoboda, C. Rother, H. A. Alhaija, D. Kainmueller, B. Savchynskyy
    A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching
    CVPR 2017. [pdf] [poster]
  • F. Michel, A. Kirillov, E. Brachmann, A. Krull, S. Gumhold, B. Savchynskyy, C. Rother
    Global Hypothesis Generation for 6D Object Pose Estimation
    CVPR 2017. [pdf] [Project page] [video]
  • A. Kirillov, E. Levinkov, B. Andres, B. Savchynskyy, C. Rother
    InstanceCut: from Edges to Instances with MultiCut
    CVPR 2017. [pdf]
2016:

  • A. Kirillov, A. Shekhovtsov, C. Rother, B. Savchynskyy
    Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
    NIPS 2016. [pdf] [Project page]
  • A. Kirillov, D. Schlesinger, S. Zheng, B. Savchynskyy, P.H.S. Torr, C. Rother
    Joint Training of Generic CNN-CRF Models with Stochastic Optimization
    ACCV 2016. [pdf]
  • Kappes, J.H.; Swoboda, P.; Savchynskyy, B.; Hazan, T. and Schnörr, C.
    Multicuts and Perturb & MAP for Probabilistic Graph Clustering.
    In J. Math. Imag. Vision, 2016. [preprint] [bib]
  • Swoboda, P.; Shekhovtsov, A.; Kappes, J.H.; Schnörr, C. and Savchynskyy, B.
    Partial Optimality by Pruning for MAP-Inference with General Graphical Models.
    In IEEE Trans. Patt. Anal. Mach. Intell., vol. 38, July 2016, pp. 1370-1382. [preprint] [bib] [Project page]
2015:

2014:
2013:
  • B. Savchynskyy, S. Schmidt
    Getting Feasible Variable Estimates From Infeasible Ones: MRF Local Polytope Study.
    In Workshop on Inference for Probabilistic Graphical Models at ICCV 2013 [bib] [pdf] [poster-pdf]
    The code is available in OpenGM library (inference class PrimalLPBound )
  • B. Savchynskyy, J. Kappes, P. Swoboda, C. Schnörr
    Global MAP-Optimality by Shrinking the Combinatorial Search Area with Convex Relaxation
    NIPS-2013
    [bib] [pdf] [presentation-pdf] [poster-pdf] [Project page]  
    The code is available in <OpenGM library (inference class CombiLP )
  • P. Swoboda, B. Savchynskyy, J. Kappes, C. Schnörr
    Partial optimality via iterative pruning for the Potts model
    SSVM-2013, pp.477-488 - oral presentation
    [bib] [pdf] [presentation-pdf]  [Project page]
2012:
  • B. Savchynskyy, S. Schmidt, J. H. Kappes, C. Schnörr
    Efficient MRF Energy Minimization via Adaptive Diminishing Smoothing
    In UAI, 2012, pp. 746-755. [bib] [PDF (revised version with appendix)][UAI Poster with additional comparison to ADLP algorithm]
    The code is available in OpenGM library (inference class ADSal)
  • J. H. Kappes, B. Savchynskyy, C. Schnörr
    A Bundle Approach To Efficient MAP-Inference by Lagrangian Relaxation
    In CVPR, 2012 [bib] [pdf] 
    The code is available in OpenGM library
2011:
2009 and before:
  • Savchynskyy B.D., Olefirenko S.A.
    Estimation of character template sizes for OCR
    Collection of scientific works of International Research and Training Center of Information Technologies and Systems NAS and MES Ukraine. Perspective technologies of education and education spaces. Kyiv: IRTC ITS, 2009.-Num.2.-Pp.24-45 [pdf (in Russian)][pdf (Presentation in English)][bib]
  • Sdobnikov V., Savchynskyy B.
    Vanishing points detection in city block images
    Proceedings of the 9-th all-ukrainian international conference UkrOBRAZ'2008 Kiev, Nov. 3-7 2008, pp. 123-126 [pdf (Ukrainian)]
  • Bogdan Savchynskyy, Vojtěch Franc
    Discriminative Learning of Max-Sum Classifiers
    Journal of Machine Learning Research, 9(Jan):67--104, 2008, Microtome Publishing [pdf][bib]
  • Savchynskyy B.D., Olefirenko S.A.
    Partially supervised learning for text recognition problem
    Control Systems and Computers, 2007(1), Kiev, pp.19-29 [pdf (English)][pdf (Russian)][pdf (Ukrainian)][bib]
  • Bogdan Savchynskyy, Olexander Kamotskyy
    Character templates learning for textual images recognition as an example of learning in structural recognition
    Proc. of the Intern. Conf. on Document Image Analysis for Libraries DIAL, 2006, Lyon, pp.88-95, IEEE Press [pdf][bib]
  • Savchynskyy B.D., Kamotskyy O.V.
    Tuning of a text recognition algorithm
    Control Systems and Computers, 2005(2), Kiev, pp.17-24 [pdf (Ukrainian)][pdf (Russian)]
  • Savchynskyy B.D. Pavlyuk O.V.
    Effective parsing and recognition of structured images
    Control Systems and Computers, 2005(5), Kiev, pp.13-24 [pdf (Ukrainian)][bib]
  • Savchynskyy B.D.
    Non-traditional Tasks of an Optical Text Recognition in the Framework of Bayesian Theory of Statistical Decisions
    Control Systems and Computers, 2003(4), Kiev, pp.8-21 [pdf (Ukrainian)] [pdf (Russian)]
  • Schlesinger M.I., Savchynskyy B.D., Anokhina M.O.
    Parsing and recognition of printed notes
    Control Systems and Computers, 2003(4), Kiev, pp.30-38 [pdf (English preprint)] [pdf (Ukrainian)] [pdf (Russian)][bib]
  • Schlesinger M.I., Savchynskyy B.D., Anokhina M.O.
    Computer technology for printed notes recognition
    Proc. of Inter. Conf. "Electronic Images and Visual Arts" EVA 2002, Kiev, 2002, pp.82-86 [pdf (Ukrainian)]
  • Savchynskyy B.
    Comparative analysis of stereovision algorithms in the framework of Bayes statistical decision theory
    Proceedings of the fifth all-ukrainian international conference UkrOBRAZ2000, Kiev, nov. 27-dec.1, 2000 [pdf (Ukrainian)][bib]

My publications till 2009 are available also here.