Close mobile menu

Author Image

Marcus A. Brubaker

Assistant Professor

Department:

Electrical Engineering & Computer Science

Bio

Marcus Brubaker received his PhD in Computer Science from the University of Toronto in 2011. After that, he worked as a postdoctoral researcher at Toyota Technological Institute at Chicago and taught at the University of Toronto, Scarborough. He is the co-founder of Structura Biotechnology Inc, consults with a number of companies on computer vision and machine learning application and served as the Research Director for BorealisAI (the AI Research and Development arm of the Royal Bank of Canada) from 2018 through 2020. He joined York University as an Assistant Professor in July, 2016.He has worked on a range of problems including human pose and motion estimation, vehicle localization, electron cryomicroscopy, Markov Chain Monte Carlo, non-parametric statistical inference and ballistic forensics.

Research Interests

  • Computer Vision
  • Machine Learning
  • Bayesian Statistics
  • Computational Biology

Selected Publications

  • Wavelet Flow: Fast Training of High Resolution Normalizing Flows. Yu, J. J.; Derpanis, K.; and Brubaker, M. A. In Proceedings of Neural Information Processing Systems (NeurIPS), 2020.
  • Normalizing Flows: An Introduction and Review of Current Methods. Kobyzev, I.; Prince, S. J.; and Brubaker, M. A. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2020.
  • Noise Flow: Noise Modeling with Conditional Normalizing Flows. Abdelhamed, A.; Brubaker, M. A.; and Brown, M. S. In Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019.
  • Two-Stream Convolutional Networks for Dynamic Texture Synthesis. Tesfaldet, M.; Brubaker, M. A.; and Derpanis, K. G. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  • cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination. Punjani, A.; Rubinstein, J. L.; Fleet, D. J.; and Brubaker, M. A. Nature Methods. 2017.
  • Map-based Probabilistic Visual Self-Localization. Brubaker, M. A.; Geiger, A.; and Urtasun, R. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016.
  • Building Proteins in a Day: Efficient 3D Molecular Reconstruction. Brubaker, M. A.; Punjani, A.; and Fleet, D. J. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2015.
  • Efficient Optimization for Sparse Gaussian Process Regression. Cao, Y.; Brubaker, M. A.; Fleet, D. J.; and Hertzmann, A. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(12): 2415 -- 2427. 2015.
  • Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization. Brubaker, M. A.; Geiger, A.; and Urtasun, R. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2013.
  • A Family of MCMC Methods on Implicitly Defined Manifolds. Brubaker, M. A.; Salzmann, M.; and Urtasun, R. In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS), 2012.
  • Physics-based Person Tracking using the Anthropomorphic Walker. Brubaker, M. A.; Fleet, D. J.; and Hertzmann, A. International Journal of Computer Vision, 87(1): 140--155. 2010.
  • Estimating Contact Dynamics. Brubaker, M. A.; Sigal, L.; and Fleet, D. J. In Proceedings of IEEE International Conference on Computer Vision, 2009.