Anton Osokin
- Leading Research Fellow:Faculty of Computer Science / Big Data and Information Retrieval School / Samsung-HSE Laboratory
- Anton Osokin has been at HSE since 2017.
Education and Degrees
- 2014
Candidate of Sciences* (PhD) in Discrete Mathematics and Mathematical Cybernetics
Lomonosov Moscow State University
Thesis Title: Submodular relaxation for energy minimization in Markov random fields - 2010
Diploma in Applied Mathematics and Computer Science
Lomonosov Moscow State University, Computational Mathematics and Cybernetics
According to the International Standard Classification of Education (ISCED) 2011, Candidate of Sciences belongs to ISCED level 8 - "doctoral or equivalent", together with PhD, DPhil, D.Lit, D.Sc, LL.D, Doctorate or similar. Candidate of Sciences allows its holders to reach the level of the Associate Professor.
Employment history
École Normale Supérieure & INRIA, Paris, France
Computer Science Department
Postdoctoral researcher in WILLOW project-team
October 2016 – August 2017
École Normale Supérieure & INRIA, Paris, France
Computer Science Department
Postdoctoral researcher in SIERRA project-team
October 2014 – September 2016
Moscow State University, Moscow, Russia
Faculty of Computational Mathematics and Cybernetics
Assistant in the department of mathematical methods of forecasting
October 2012 –September 2014
20172
- Chapter Osokin A., Chessel A., Carazo Salas R. E., Vaggi F. GANs for Biological Image Synthesis, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV 2017). Venice : IEEE, 2017. P. 2252-2261.
- Chapter Osokin A., Bach F., Lacoste-Julien S. On Structured Prediction Theory with Calibrated Convex Surrogate Losses, in: Advances in Neural Information Processing Systems 30 (NIPS 2017). Montreal : Curran Associates, 2017. P. 1-12.
20162
- Chapter Bartunov S., Kondrashkin D., Osokin A., Vetrov D. Breaking Sticks and Ambiguities with Adaptive Skip-gram, in: Proceedings of Machine Learning Research. Proceedings of The International Conference on Artificial Intelligence and Statistics (AISTATS 2016) Vol. 51. Cadiz : , 2016. P. 130-138.
- Chapter Osokin A., Lukasewitz I., Dokania P., Alayrac J., Lacoste-Julien S. Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs, in: Proceedings of Machine Learning Research. Proceedings of the International Conference on Machine Learning (ICML 2016) Vol. 48. NY : , 2016. P. 593-602.
20153
- Chapter Vu T., Osokin A., Laptev I. Context-Aware CNNs for Person Head Detection, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV 2015). Santiago de Chile : IEEE, 2015. P. 2893-2901. doi
- Article Osokin A., Vetrov D. Submodular Relaxation for Inference in Markov Random Fields // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2015. Vol. 37. No. 7. P. 1347-1359.
- Chapter Novikov A., Podoprikhin D., Osokin A., Vetrov D. Tensorizing Neural Networks, in: Advances in Neural Information Processing Systems 28 (NIPS 2015). NY : Curran Associates, 2015.
20142
- Chapter Osokin A., Kohli P. Perceptually Inspired Layout-Aware Losses for Image Segmentation, in: Lecture Notes in Computer Science. Proceedings of the 13th European Conference on Computer Vision (ECCV 2014) Vol. 8690. Part 2. Zürich : Springer, 2014. P. 663-678. doi
- Chapter Vetrov D., Osokin A., Novikov A., Rodomanov A. Putting MRFs on a Tensor Train, in: JMLR Workshop and Conference Proceedings Issue 32: Proceedings of The 31st International Conference on Machine Learning. Beijing : Microtome Publishing, 2014. P. 811-819.
20131
20122
- Article Delong A., Osokin A., Isack H. N., Boykov Y. Fast Approximate Energy Minimization with Label Costs // International Journal of Computer Vision. 2012. Vol. 96. No. 1. P. 1-27. doi
- Chapter Delong A., Veksler O., Osokin A., Boykov Y. Minimizing sparse high-order energies by submodular vertex-cover, in: Advances in Neural Information Processing Systems 26 (NIPS 2012). Lake Tahoe : Curran Associates, Inc., 2012.
20111
20101
How to Adjust a Smaller Size Neural Network without Quality Loss
Staff members of the HSE Faculty of Computer Science recently presented their papers at the biggest international conference on machine learning, Neural Information Processing Systems (NIPS)’.
How to Adjust a Smaller Size Neural Network without Quality Loss
Staff members of the HSE Faculty of Computer Science recently presented their papers at the biggest international conference on machine learning, Neural Information Processing Systems (NIPS)’.
Welcome Aboard: Tenure-Track Introductions
Every year The HSE Look continues its tradition of welcoming newly recruited international faculty via short summaries about their positions and research interests. In the 34th issue we introduce the tenure-track faculty members, and in November you can learn more about post-doctoral researchers who are starting their work at HSE this fall.
