| Fast approximate energy minimization with label costs A Delong, A Osokin, HN Isack, Y Boykov IJCV, International journal of computer vision 96 (1), 1-27, 2012 | 584 | 2012 |
| Fast approximate energy minimization with label costs A Delong, A Osokin, HN Isack, Y Boykov CVPR, Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2010 | 584 | 2010 |
| Tensorizing neural networks A Novikov, D Podoprikhin, A Osokin, DP Vetrov NIPS, Advances in Neural Information Processing Systems, 442-450, 2015 | 468 | 2015 |
| Breaking Sticks and Ambiguities with Adaptive Skip-gram S Bartunov, D Kondrashkin, A Osokin, D Vetrov AISTATS, Proceedings of the International Conference on Artificial …, 2016 | 146 | 2016 |
| Context-aware CNNs for person head detection TH Vu, A Osokin, I Laptev ICCV, Proceedings of the International Conference on Computer Vision, 2893-2901, 2015 | 100 | 2015 |
| A principled deep random field model for image segmentation P Kohli, A Osokin, S Jegelka CVPR, Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2013 | 88 | 2013 |
| GANs for Biological Image Synthesis A Osokin, A Chessel, REC Salas, F Vaggi ICCV, Proceedings of the International Conference on Computer Vision, 2017 | 67 | 2017 |
| Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs A Osokin, JB Alayrac, I Lukasewitz, PK Dokania, S Lacoste-Julien ICML, Proceedings of the International Conference on Machine Learning, 2016 | 60 | 2016 |
| On structured prediction theory with calibrated convex surrogate losses A Osokin, F Bach, S Lacoste-Julien NIPS, Advances in Neural Information Processing Systems, 301-312, 2017 | 35 | 2017 |
| SEARNN: Training RNNs with Global-Local Losses R Leblond, JB Alayrac, A Osokin, S Lacoste-Julien ICLR, Proceedings of International Conference on Learning Representations, 2018 | 28 | 2018 |
| Putting MRFs on a Tensor Train. A Novikov, A Rodomanov, A Osokin, D Vetrov ICML, Proceedings of the International Conference on Machine Learning, 811-819, 2014 | 27 | 2014 |
| Submodular decomposition framework for inference in associative markov networks with global constraints A Osokin, D Vetrov, V Kolmogorov CVPR, Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2011 | 23 | 2011 |
| Minimizing sparse high-order energies by submodular vertex-cover A Delong, O Veksler, A Osokin, Y Boykov NIPS, Advances in Neural Information Processing Systems, 962-970, 2012 | 15 | 2012 |
| Perceptually inspired layout-aware losses for image segmentation A Osokin, P Kohli ECCV, Proceedings of the European Conference on Computer Vision, 663-678, 2014 | 10 | 2014 |
| Submodular relaxation for inference in Markov random fields A Osokin, DP Vetrov TPAMI, IEEE transactions on pattern analysis and machine intelligence 37 (7 …, 2015 | 7 | 2015 |
| Submodular relaxation for MRFs with high-order potentials A Osokin, D Vetrov ECCV workshops, Proceedings of the workshops of European Conference on …, 2012 | 5 | 2012 |
| Variational segmentation algorithms with label frequency constraints D Kropotov, D Laptev, A Osokin, D Vetrov Pattern Recognition and Image Analysis 20 (3), 324-334, 2010 | 5 | 2010 |
| 3-D mouse brain model reconstruction from a sequence of 2-D slices in application to Allen brain atlas A Osokin, D Vetrov, D Kropotov International Meeting on Computational Intelligence Methods for …, 2009 | 5 | 2009 |
| Quantifying Learning Guarantees for Convex but Inconsistent Surrogates K Struminsky, S Lacoste-Julien, A Osokin NIPS, Advances in Neural Information Processing Systems, 666-674, 2018 | 4 | 2018 |
| Modeling Spatio-Temporal Human Track Structure for Action Localization G Chéron, A Osokin, I Laptev, C Schmid arXiv preprint arXiv:1806.11008, 2018 | 3 | 2018 |
Dmitry VetrovHigher School of Economics, Samsung AI Center, MoscowVerified email at hse.ru
