Home

Olga Barinova

  I am a full-time researcher at Graphics&Media Lab. I got my doctoral degree from Moscow State University in 2010. My research interests lie in computer vision and machine learning. I have participated in a number of joint research projects with different companies, including Samsung Advanced Institute of Technology (SAIT). Also I consult a spin-off from our lab, Mobile Mapping Technologies.

Since 2009 I'm working on joint projects with Microsoft Research. I'm organizing Microsoft Computer Vision Summer School in Moscow in July-August 2011.

E-mail: obarinova [at] graphics [dot] cs [dot] msu [dot] ru

Projects:

Geometric image parsing in man-made environments
Detection of multiple object instances using Hough transform
Fast automatic single-view 3-d reconstruction of urban scenes
Road monitoring
Avoiding Boosting Overfitting by Removing "Confusing Samples"
   Image-based 3D reconstruction of urban scenes
GML Balanced On-line Learning Toolkit

Talks:

  • Local cues and global contraints in image understanding, in Microsoft Research PhD Summer School, Cambridge, June 2011 [link]

  • Advancing geometric analysis of man-made environments, in Emerging Leaders in Multimedia, IBM Watson Center, New York, October 2010 [link]

  • On detection of multiple object instances using Hough Transforms, in Computer Vision and Pattern Recognition, San Francisco, June 2010 [link]

  • Advancing 3D reconstruction of urban scenes from a single photograph, in Joint Institutes Workshop INRIA-Microsoft Joint Center, Orsay, April 2010 [link]

Patents:

  • DETECTING AND LOCALIZING MULTIPLE OBJECTS IN IMAGES USING PROBABILISTIC INFERENCE, MS1-5225US, Pushmeet Kohli, Olga Barinova, Victor Lempitsky

  • METHOD FOR DETERMINING GROUND LINE, 1911.1137, US, Chae sunhyuck, Kim dokyoon, Lee KeeChang, Lim Hwasup, Konushin Anton, Barinova Olga, Konushin Vadim, Yakubenko Anton [link] (US)
  • METHOD FOR DETERMINING GROUND LINE, 10-2008-0105977, 28.10.2008, Chae sunhyuck, Kim dokyoon, Lee KeeChang, Lim Hwasup, Konushin Anton, Barinova Olga, Konushin Vadim, Yakubenko Anton (Korea)
  • METHOD FOR DETERMINING GROUND LINE, 2008132273, RU, 17.07.2008, Chae sunhyuck, Kim dokyoon, Lee KeeChang, Lim Hwasup, Konushin Anton, Barinova Olga, Konushin Vadim, Yakubenko Anton (Russia)
  • IMAGE PROCESSING METHOD, 2008129149, RU, 17.07.2008,
    Lim Hwasup, Lee KeeChang, Barinova Olga, Konushin Anton, Konushin
    Vadim, Yakubenko Anton (Russia)


Publications(in English):

2012
Barinova O, Shapovalov R, Sudakov S, Velizhev A. Online Random Forest for Interactive Image Segmentation. In: International Workshop on Experimental Economics and Machine Learning. Leuven, BE; 2012. Abstract
2011
Tretiak E, Barinova O, Kohli P, Lempitsky V. Geometric image parsing in man-made environments. IJCV. 2011.
2010
Barinova O, Gavrishchaka V. Generic Regularization of Boosting-Based Optimization for the Discovery of Regime-Independent Trading Strategies from High-Noise Time Series. ICIC Express Letters. 2010.
Barinova O, Lempitsky V, Tretiak E, Kohli P. Geometric Image Parsing in Man‐Made Environments. In: European Conference on Computer Vision.; 2010.
Shapovalov R, Velizhev A, Barinova O. Non-Associative Markov Networks for 3D Point Cloud Classification. In: Photogrammetric Computer Vision and Image Analysis. Paris: ISPRS; 2010. Abstract
Barinova O, Lempitsky V, Kohli P. On detection of multiple object instances using Hough transform. In: Computer Vision and Pattern Recognition.; 2010. Abstract
2009
Barinova O, Shapovalov R, Sudakov S, Velizhev A, Konushin A. Efficient Road Mapping via Interactive Image Segmentation. In: Object Extraction for 3D City Models, Road Databases and Traffic Monitoring (CMRT). Vol XXXVIII.; 2009. Abstract
Barinova O, Gavrishchaka V. Generic regularization of boosting-based algorithms for the discovery of regime-independent portfolio strategies from high-noise time series. In: The Fourth International Conference on Innovative Computing, Information and Control.; 2009.
Barinova O. Incorporating posterior estimates into AdaBoost. Pattern Recognition and Image Analysis. 2009;19(3):421-34.
Barinova O, Vetrov D. ODDboost: Incorporating posterior estimates into AdaBoost . Lecture Notes in Computer Science. 2009;5632/2009:178-90.
2008
Gavrishchaka V, Barinova O, Vezhnevets A, Monina M. Discovery of multi-component portfolio strategies with continuous tuning to the changing market micro-regimes using input-dependent boosting. In: Computational Finance and its Applications III.; 2008.
Barinova O, Konushin V, Yakubenko A, Lim H, Lee K, Konushin A. Fast automatic single-view 3-d reconstruction of urban scenes. In: Proceedings of European Conference of Computer Vision.; 2008.
Barinova O, Gavrishchaka V. Removal of confusing training samples as a generic mechanism to improve and diversify trading strategies discovered by boosting-based optimisation. In: Proceedings of Computational Intelligence in Economics and Finance.; 2008.
Sudakov S, Barinova O, Velizhev A, Konushin A. Semantic segmentation of road images based on cascade classifiers. In: Proceedings of PRIA.; 2008.
2007
Vezhnevets A, Barinova O. Avoiding Boosting Overfitting by Removing 'Confusing Samples'. In: European Conference on Machine Learning ECML. Springer; 2007. p. 430-41.
Barinova O, Kuzmishkina A, Vezhnevets A, Vezhnevets V. Learning class specific edges for vanishing point estimation. In: Graphicon.; 2007.

Publications(in Russian):

2012
Шаповалов Р, Велижев А, Баринова О, Конушин А. Семантическая сегментация данных лазерного сканирования. Программные продукты и системы. 2012;(1).
2008
Крылов А, Судаков С, Киншаков В, Семашко А, Баринова О, Конушин А. Алгоритмы детектирования разметки и дефектов дорожного покрытия. In: GraphiCon .; 2008. p. 206-12.
Баринова О, Конушин В, Якубенко А, Конушин А. Быстрый метод семантической сегментации изображений для автоматической трехмерной реконструкции городских сцен по одной фотографии. In: Интеллектуализация обработки информации 2008.; 2008. p. 22-4.
Кузьмишкина А, Баринова О, Конушин А. Выбор объектов для обучения в условиях сильной несбалансированности классов. In: Graphicon.; 2008. p. 213-7.
Кузьмишкина А, Баринова О, Конушин А. Выбор объектов для обучения в условиях сильной несбалансированности классов. In: GraphiCon .; 2008. p. 213-6.
Шаповалов Р, Баринова О, Велижев А, Конушин А. Онлайн-бэггинг, чувствительный к стоимости ошибок на разных классах. In: Труды 51-й научной конференции МФТИ «Современные проблемы фундаментальных и прикладных наук»: Часть IX. – М. : МФТИ.; 2008. p. 79-82.
2007
Баринова О, Вежневец А. Повышение обобщающей способности алгоритмов Boosting в задачах с пересекающимися классами. In: ММРО-2007.; 2007. p. 82-4.
Баринова О, Вежневец А, Вежневец В. Повышение обобщающей способности бустинга в задачах с перекрывающимися классами. In: Математические Методы Распознавания Образов.; 2007.
Баринова О, Вежневец А, Вежневец В. Повышение обобщающей способности бустинга в задачах с пересекающимися распределениями . In: 50-я юбилейная Конференция МФТИ 2007.; 2007. p. 91-3.
2006
Вежневец А, Баринова О. Методы сегментации изображений: автоматическая сегментация. Graphics and Multimedia Magazin. 2006.
2005
Баринова О. Об одном методе прогнозирования временных рядов с несимметричных функционалом потерь. In: Математические Методы Распознавания Образов.; 2005. p. 258-60.
Баринова О, Ефимов А, Чехович Ю, Вальков А, Воронцов К, Громов С. Система прогнозирования потребительского спроса Goods4Cast. In: Математические методы распознавания образов.; 2005.