generated by bibbase.org
  2022 (8)
Efficient CDF Approximations for Normalizing Flows. Sastry, C. S.; Lehrmann, A.; Brubaker, M. A.; and Radovic, A. Transactions on Machine Learning Research (TMLR). 2022.
Efficient CDF Approximations for Normalizing Flows [link]Paper   Efficient CDF Approximations for Normalizing Flows [link] arxiv   link   bibtex  
Residual Multiplicative Filter Networks for Multiscale Reconstruction. Shekarforoush, S.; Lindell, D. B.; Fleet, D. J.; and Brubaker, M. A. In Neural Information Processing Systems (NeurIPS), 2022.
Residual Multiplicative Filter Networks for Multiscale Reconstruction [link] arxiv   link   bibtex  
Neural Image Representations for Multi-Image Fusion and Layer Separation. Nam, S.; Brubaker, M. A.; and Brown, M. S. In Proceedings of the European Conference on Computer Vision (ECCV), 2022.
Neural Image Representations for Multi-Image Fusion and Layer Separation [link] arxiv   Neural Image Representations for Multi-Image Fusion and Layer Separation [link] website   link   bibtex  
Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images. Maleky, A.; Kousha, S.; Brown, M. S.; and Brubaker, M. A. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images [link] arxiv   Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images [link] website   link   bibtex  
Modeling sRGB Camera Noise with Normalizing Flows. Kousha, S.; Maleky, A.; Brown, M. S.; and Brubaker, M. A. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
Modeling sRGB Camera Noise with Normalizing Flows [link] arxiv   Modeling sRGB Camera Noise with Normalizing Flows [link] website   link   bibtex  
Learning sRGB-to-Raw De-rendering with Content-Aware Metadata. Nam, S.; Punnappurath, A.; Brubaker, M. A.; and Brown, M. S. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
Learning sRGB-to-Raw De-rendering with Content-Aware Metadata [link] arxiv   Learning sRGB-to-Raw De-rendering with Content-Aware Metadata [link] code   link   bibtex  
Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals. Brofos, J. A.; Gabrié, M.; Brubaker, M. A.; and Lederman, R. R. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals [link] arxiv   link   bibtex  
Auto White-Balance Correction for Mixed-Illuminant Scenes. Afifi, M.; Brubaker, M. A.; and Brown, M. S. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2022.
Auto White-Balance Correction for Mixed-Illuminant Scenes [link] arxiv   Auto White-Balance Correction for Mixed-Illuminant Scenes [link] code   link   bibtex  
  2021 (10)
Continuous Latent Process Flows. Deng, R.; Brubaker, M. A.; Mori, G.; and Lehrmann, A. In Neural Information Processing Systems (NeurIPS), 2021.
Continuous Latent Process Flows [link] arxiv   link   bibtex  
HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms. Afifi, M.; Brubaker, M. A.; and Brown, M. S. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms [link] arxiv   link   bibtex  
Manifold Density Estimation via Generalized Dequantization. Brofos, J. A.; Brubaker, M. A.; and Lederman, R. R. In ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 2021.
Manifold Density Estimation via Generalized Dequantization [link] arxiv   Manifold Density Estimation via Generalized Dequantization [link] code   link   bibtex  
Agent Forecasting at Flexible Horizons using ODE Flows. Radovic, A.; He, J.; Ramanan, J.; Brubaker, M. A.; and Lehrmann, A. In ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 2021.
link   bibtex  
Continuous Latent Process Flows. Deng, R.; Brubaker, M. A.; Mori, G.; and Lehrmann, A. In ICML Workshop on Time Series, 2021.
Continuous Latent Process Flows [link] arxiv   link   bibtex  
Zero-shot Learning with Class Description Regularization. Kousha, S.; and Brubaker, M. A. In CVPR Workshop on Fine-Grained Visual Categorization, 2021.
Zero-shot Learning with Class Description Regularization [link] arxiv   link   bibtex  
Equivariant Finite Normalizing Flows. Bose, A. J.; Brubaker, M. A.; and Kobyzev, I. 2021.
Equivariant Finite Normalizing Flows [link] arxiv   link   bibtex  
CAMS: Color-Aware Multi-Style Transfer. Afifi, M.; Abuolaim, A.; Hussien, M.; Brubaker, M. A.; and Brown, M. S. 2021.
CAMS: Color-Aware Multi-Style Transfer [link] arxiv   CAMS: Color-Aware Multi-Style Transfer [link] code   link   bibtex  
Differential Privacy Tutorial II: Machine Learning and Data Generation. Sharma, G.; Hegde, N.; Prince, S. J.; and Brubaker, M. A. March 2021.
Differential Privacy Tutorial II: Machine Learning and Data Generation [link] blog   link   bibtex  
Differential Privacy Tutorial I: Introduction. Brubaker, M. A.; and Prince, S. J. February 2021.
Differential Privacy Tutorial I: Introduction [link] blog   link   bibtex  
  2020 (8)
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.
Normalizing Flows: An Introduction and Review of Current Methods [link] arxiv   link   bibtex  
Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model. Ghorbani, S.; Wloka, C.; Etemad, A.; Brubaker, M. A.; and Troje, N. F. Proceedings of Symposium on Computer Animation (SCA) in Computer Graphics Forum, 39(8). 2020.
Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model [link] paper   Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model [pdf] local   link   bibtex  
Wavelet Flow: Fast Training of High Resolution Normalizing Flows. Yu, J. J.; Derpanis, K.; and Brubaker, M. A. In Neural Information Processing Systems (NeurIPS), 2020.
Wavelet Flow: Fast Training of High Resolution Normalizing Flows [link] arxiv   Wavelet Flow: Fast Training of High Resolution Normalizing Flows [link] website   Wavelet Flow: Fast Training of High Resolution Normalizing Flows [link] code   link   bibtex  
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows. Deng, R.; Chang, B.; Brubaker, M. A.; Mori, G.; and Lehrmann, A. In Neural Information Processing Systems (NeurIPS), 2020.
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows [link] arxiv   Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows [link] code   link   bibtex  
Tails of Lipschitz Triangular Flows. Jaini, P.; Kobyzev, I.; Brubaker, M. A.; and Yu, Y. In Proceedings of the International Conference on Machine Learning (ICML), 2020.
Tails of Lipschitz Triangular Flows [link] arxiv   link   bibtex  
Diachronic Embedding for Temporal Knowledge Graph Completion. Goel, R.; Kazemi, S. M.; Brubaker, M. A.; and Poupart, P. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020.
Diachronic Embedding for Temporal Knowledge Graph Completion [link] arxiv   Diachronic Embedding for Temporal Knowledge Graph Completion [pdf] paper   link   bibtex  
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows. Deng, R.; Chang, B.; Brubaker, M. A.; Mori, G.; and Lehrmann, A. In ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 2020.
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows [link] arxiv   link   bibtex  
Variational Hyper RNN for Sequence Modeling. Deng, R.; Cao, Y.; Chang, B.; Sigal, L.; Mori, G.; and Brubaker, M. A. 2020.
Variational Hyper RNN for Sequence Modeling [link] arxiv   link   bibtex  
  2019 (7)
Noise Flow: Noise Modeling with Conditional Normalizing Flows. Abdelhamed, A.; Brubaker, M. A.; and Brown, M. S. In Proceedings of the International Conference on Computer Vision (ICCV), 2019.
Noise Flow: Noise Modeling with Conditional Normalizing Flows [link] arxiv   Noise Flow: Noise Modeling with Conditional Normalizing Flows [pdf] paper   Noise Flow: Noise Modeling with Conditional Normalizing Flows [pdf] supplemental   Noise Flow: Noise Modeling with Conditional Normalizing Flows [link] code   link   bibtex  
HydraPicker: Fully Automated Particle Picking in Cryo-EM by Utilizing Dataset Bias in Single Shot Detection. Masoumzadeh, A.; and Brubaker, M. A. In Proceedings of the British Machine Vision Conference (BMVC), 2019.
HydraPicker: Fully Automated Particle Picking in Cryo-EM by Utilizing Dataset Bias in Single Shot Detection [pdf] paper   HydraPicker: Fully Automated Particle Picking in Cryo-EM by Utilizing Dataset Bias in Single Shot Detection [link] supplemental   HydraPicker: Fully Automated Particle Picking in Cryo-EM by Utilizing Dataset Bias in Single Shot Detection [link] code   link   bibtex  
Differentiable probabilistic models of scientific imaging with the Fourier slice theorem. Ullrich, K.; van den Berg, R.; Brubaker, M. A.; Fleet, D. J.; and Welling, M. In Proceedings of Conference on Uncertainty in Artificial Intelligence (UAI), 2019.
Differentiable probabilistic models of scientific imaging with the Fourier slice theorem [link] arxiv   Differentiable probabilistic models of scientific imaging with the Fourier slice theorem [pdf] paper   Differentiable probabilistic models of scientific imaging with the Fourier slice theorem [link] openreview   link   bibtex  
On the Effectiveness of Low Frequency Perturbations. Sharma, Y.; Ding, G. W.; and Brubaker, M. A. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2019.
On the Effectiveness of Low Frequency Perturbations [pdf] paper   On the Effectiveness of Low Frequency Perturbations [link] arxiv   link   bibtex  
Diachronic Embedding for Temporal Knowledge Graph Completion. Goel, R.; Kazemi, S. M.; Brubaker, M. A.; and Poupart, P. In NeurIPS Workshop on Graph Representation Learning, December 2019.
Diachronic Embedding for Temporal Knowledge Graph Completion [link] arxiv   link   bibtex  
Point Process Flows. Mehrasa, N.; Deng, R.; He, J.; Chang, B.; Durand, T.; Ahmed, M. O.; Brubaker, M. A.; and Mori, G. In NeurIPS Workshop on Learning with Temporal Point Processes, December 2019.
Point Process Flows [link] arxiv   link   bibtex  
Time2Vec: Learning a Vector Representation of Time. Kazemi, S. M.; Goel, R.; Eghbali, S.; Ramanan, J.; Sahota, J.; Thakur, S.; Wu, S.; Smyth, C.; Poupart, P.; and Brubaker, M. 2019.
Time2Vec: Learning a Vector Representation of Time [link] arxiv   link   bibtex  
  2018 (6)
Two-Stream Convolutional Networks for Dynamic Texture Synthesis. Tesfaldet, M.; Brubaker, M. A.; and Derpanis, K. G. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
Two-Stream Convolutional Networks for Dynamic Texture Synthesis [link] website   Two-Stream Convolutional Networks for Dynamic Texture Synthesis [pdf] paper   Two-Stream Convolutional Networks for Dynamic Texture Synthesis [link] arxiv   link   bibtex  
Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture. Livne, M.; Sigal, L.; Brubaker, M. A.; and Fleet, D. J. In Proceedings of the Conference on Computer and Robot Vision (CRV), 2018.
Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture [link] arxiv   Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture [pdf] paper   Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture [pdf] supplemental   Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture [link] website   Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture [link] video   link   bibtex  
Convolutional Photomosaic Generation via Multi-scale Perceptual Losses. Tesfaldet, M.; Saftarli, N.; Brubaker, M. A.; and Derpanis, K. G. In ECCV Workshop on Computer Vision for Fashion, Art and Design, 2018.
Convolutional Photomosaic Generation via Multi-scale Perceptual Losses [link] website   Convolutional Photomosaic Generation via Multi-scale Perceptual Losses [pdf] paper   link   bibtex  
Algorithmic Advances in Single Particle Cryo-EM Data Processing. Punjani, A.; Zhang, H.; Rubinstein, J.; Brubaker, M. A.; and Fleet, D. J. Microscopy and Microanalysis, 24(S1): 868-869. 2018.
Algorithmic Advances in Single Particle Cryo-EM Data Processing [link] paper   doi   link   bibtex  
On Learning Wire-Length Efficient Neural Networks. Blake, C.; Wang, L.; Castiglione, G.; Srinivasa, C.; and Brubaker, M. A. In NeurIPS 2018 Workshop on Compact Deep Neural Network Representation with Industrial Applications, December 2018.
link   bibtex  
The Integral Cross-Discipline Approach to Pushing AI Research. Brubaker, M. A. techvibes.com. February 2018.
The Integral Cross-Discipline Approach to Pushing AI Research [link]Paper   link   bibtex  
  2017 (7)
cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination. Punjani, A.; Rubinstein, J. L.; Fleet, D. J.; and Brubaker, M. A. Nature Methods, 14(3): 290 – 296. 2017.
cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination [pdf] preprint   cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination [link] paper   cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination [link] software   link   bibtex  
Stan: A Probabilistic Programming Language. Carpenter, B.; Gelman, A.; Hoffman, M.; Lee, D.; Goodrich, B.; Betancourt, M.; Brubaker, M. A.; Guo, J.; Li, P.; and Riddell, A. Journal of Statistical Software, 76(1). 2017.
Stan: A Probabilistic Programming Language [pdf] paper   Stan: A Probabilistic Programming Language [link] website   Stan: A Probabilistic Programming Language [link] software   link   bibtex  
Development and validation of a virtual examination tool for firearm forensics. Duez, P.; Weller, T.; Brubaker, M. A.; Hockensmith, R. E.; and Lilien, R. Journal of Forensic Sciences. 2017.
Development and validation of a virtual examination tool for firearm forensics [link] paper   link   bibtex  
Building Proteins in a Day: Efficient 3D Molecular Structure Estimation with Electron Cryomicroscopy. Punjani, A.; Brubaker, M. A.; and Fleet, D. J. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2017.
Building Proteins in a Day: Efficient 3D Molecular Structure Estimation with Electron Cryomicroscopy [pdf] paper   link   bibtex  
Find your Way by Observing the Sun and Other Semantic Cues. Ma, W.; Wang, S.; Brubaker, M. A.; Fidler, S.; and Urtasun, R. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2017.
Find your Way by Observing the Sun and Other Semantic Cues [pdf] paper   Find your Way by Observing the Sun and Other Semantic Cues [link] arxiv   Find your Way by Observing the Sun and Other Semantic Cues [link] youtube   link   bibtex  
Size and Texture-based Classification of Lung Tumors with 3D CNNs. Luo, Z. H.; Brubaker, M. A.; and Brudno, M. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2017.
Size and Texture-based Classification of Lung Tumors with 3D CNNs [pdf] paper   link   bibtex  
New algorithms in cryoSPARC. Punjani, A.; Rubinstein, J.; Fleet, D. J.; and Brubaker, M. A. In Three Dimensional Electron Microscopy Gordon Research Conference, June 2017.
link   bibtex  
  2016 (3)
Map-based Probabilistic Visual Self-Localization. Brubaker, M. A.; Geiger, A.; and Urtasun, R. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2016.
Map-based Probabilistic Visual Self-Localization [pdf] paper   link   bibtex  
Sequential Inference for Deep Gaussian Process. Wang, Y.; Brubaker, M. A.; Chaib-draa, B.; and Urtasun, R. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
Sequential Inference for Deep Gaussian Process [pdf] paper   link   bibtex  
Algorithmic Differentiation in the Stan Math C++ Library. Carpenter, B.; Hoffman, M. D.; Brubaker, M. A.; Lee, D.; Betancourt, M.; Weber, S.; and Trangucci, R. In ADMB Developers Workshop, June 2016.
link   bibtex  
  2015 (7)
Introduction and Initial Evaluation of a Novel Three-Dimensional Imaging and Analysis System for Firearm Forensics. Weller, T.; Brubaker, M. A.; Duez, P.; and Lilien, R. Association of Firearm and Tool Mark Examiners (AFTE) Journal, 47(4): 198 – 208. 2015.
Introduction and Initial Evaluation of a Novel Three-Dimensional Imaging and Analysis System for Firearm Forensics [link] journal   link   bibtex  
Alignment of cryo-EM movies of individual particles by optimization of image translations. Rubinstein, J. L.; and Brubaker, M. A. Journal of Structural Biology, 192(2): 188 – 195. 2015.
Alignment of cryo-EM movies of individual particles by optimization of image translations [link] arxiv   Alignment of cryo-EM movies of individual particles by optimization of image translations [link] paper   link   bibtex  
Description and comparison of algorithms for correcting anisotropic magnification in cryo-EM images. Zhao, J.; Brubaker, M. A.; Benlekbir, S.; and Rubinstein, J. L. Journal of Structural Biology, 192(2): 209 – 215. 2015.
Description and comparison of algorithms for correcting anisotropic magnification in cryo-EM images [link] arxiv   Description and comparison of algorithms for correcting anisotropic magnification in cryo-EM images [link] paper   link   bibtex  
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 (PAMI), 37(12): 2415 – 2427. 2015.
Efficient Optimization for Sparse Gaussian Process Regression [pdf] paper   link   bibtex  
Building Proteins in a Day: Efficient 3D Molecular Reconstruction. Brubaker, M. A.; Punjani, A.; and Fleet, D. J. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
Building Proteins in a Day: Efficient 3D Molecular Reconstruction [pdf] paper   Building Proteins in a Day: Efficient 3D Molecular Reconstruction [link] arxiv   Building Proteins in a Day: Efficient 3D Molecular Reconstruction [pdf] extended abstract   Building Proteins in a Day: Efficient 3D Molecular Reconstruction [link] github   Building Proteins in a Day: Efficient 3D Molecular Reconstruction [link] presentation   link   bibtex  
Efficient 3D Macromolecular Reconstruction with Electron Cryomicroscopy. Brubaker, M. A.; Punjani, A.; and Fleet, D. J. In BioImage Computing Workshop at IEEE Conference on Computer Vision and Pattern Recognition, June 2015.
link   bibtex  
The Stan Math Library: Reverse-Mode Automatic Differentiation in C++. Carpenter, B.; Hoffman, M. D.; Brubaker, M. A.; Lee, D.; Li, P.; and Betancourt, M. 2015.
The Stan Math Library: Reverse-Mode Automatic Differentiation in C++ [link] arxiv   link   bibtex  
  2014 (3)
Bayesian Filtering with Online Gaussian Process Latent Variable Models. Wang, Y.; Brubaker, M. A.; Chaib-draa, B.; and Urtasun, R. In Proceedings of Conference on Uncertainty in Artificial Intelligence (UAI), 2014.
Bayesian Filtering with Online Gaussian Process Latent Variable Models [pdf] paper   link   bibtex  
Microscopic Advances with Large-Scale Learning: Stochastic Optimization for Cryo-EM. Punjani, A.; and Brubaker, M. A. In Neural Information Processing Systems Workshop: Machine Learning in Computational Biology (MLCB), December 2014.
Microscopic Advances with Large-Scale Learning: Stochastic Optimization for Cryo-EM [link] arxiv   link   bibtex  
Progress Towards a Novel 3D-Topography Imaging and Analysis System for Firearm Identification, TopMatch-GS, and Results of a Large-Scale Study. Lilien, R.; Brubaker, M. A.; and Weller, T. In The Association of Firearm and Tool Mark Examiners Annual Training Seminar, May 2014.
link   bibtex  
  2013 (5)
TMaCS: A hybrid template matching and classification system for partially-automated particle selection. Zhao, J.; Brubaker, M. A.; and Rubinstein, J. L. Journal of Structural Biology, 181(3): 234 – 242. 2013.
TMaCS: A hybrid template matching and classification system for partially-automated particle selection [link] paper   TMaCS: A hybrid template matching and classification system for partially-automated particle selection [link] code   link   bibtex  
Efficient Optimization for Sparse Gaussian Process Regression. Cao, Y.; Brubaker, M. A.; Hertzmann, A.; and Fleet, D. J. In Neural Information Processing Systems (NeurIPS), 2013.
Efficient Optimization for Sparse Gaussian Process Regression [pdf] paper   Efficient Optimization for Sparse Gaussian Process Regression [link] arxiv   Efficient Optimization for Sparse Gaussian Process Regression [link] website   Efficient Optimization for Sparse Gaussian Process Regression [link] proceedings   link   bibtex  
Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization. Brubaker, M. A.; Geiger, A.; and Urtasun, R. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [pdf] paper   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [pdf] supplemental   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [pdf] poster   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [pdf] slides   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [link] presentation   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [link] video   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [link] youtube   Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization [link] website   link   bibtex  
Probabilistic Map Localization Through Visual Odometry. Brubaker, M. A.; Geiger, A.; and Urtasun, R. In Proceedings of SUNw: Scene Understanding Workshop at IEEE Conference on Computer Vision and Pattern Recognition (CVPRW), 2013.
Probabilistic Map Localization Through Visual Odometry [pdf] paper   Probabilistic Map Localization Through Visual Odometry [link] workshop   link   bibtex  
Development of a 3D-Topography Imaging and Analysis System for Firearm Identification using GelSight and Feature Based Case Matching. Lilien, R.; Brubaker, M. A.; and Weller, T. In The Association of Firearm and Tool Mark Examiners Annual Training Seminar, June 2013.
link   bibtex  
  2012 (3)
A Family of MCMC Methods on Implicitly Defined Manifolds. Brubaker, M. A.; Salzmann, M.; and Urtasun, R. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2012.
A Family of MCMC Methods on Implicitly Defined Manifolds [pdf] paper   A Family of MCMC Methods on Implicitly Defined Manifolds [pdf] poster   A Family of MCMC Methods on Implicitly Defined Manifolds [link] website   link   bibtex  
Three-Dimensional Topography System for Firearm Identification using GelSight. Lilien, R.; Brubaker, M. A.; Weller, T.; and Johnson, M. In NIJ and FBI Impression and Pattern Evidence Symposium, Clearwater, Florida, August 2012.
link   bibtex  
Surface Topography Measurement using GelSight Elastomeric Sensor for Firearm Forensics. Brubaker, M. A.; Lilien, R.; Weller, T.; and Johnson, M. In NIST Conference on Measurement Science and Standards in Forensic Firearms Analysis, Gaithersburg, Maryland, July 2012.
link   bibtex  
  2011 (1)
Physical Models of Human Motion for Estimation and Scene Analysis. Brubaker, M. A. Ph.D. Thesis, University of Toronto, 2011.
Physical Models of Human Motion for Estimation and Scene Analysis [pdf] thesis   link   bibtex  
  2010 (2)
Physics-based Person Tracking using the Anthropomorphic Walker. Brubaker, M. A.; Fleet, D. J.; and Hertzmann, A. International Journal of Computer Vision (IJCV), 87(1): 140–155. 2010.
Physics-based Person Tracking using the Anthropomorphic Walker [pdf] paper   Physics-based Person Tracking using the Anthropomorphic Walker [link] website   link   bibtex  
A Bayesian Method for 3-D Macromolecular Structure Inference using Class Average Images from Single Particle Electron Microscopy. Jaitly, N.; Brubaker, M. A.; Rubinstein, J.; and Lilien, R. H. Bioinformatics, 26: 2406-2415. 2010.
A Bayesian Method for 3-D Macromolecular Structure Inference using Class Average Images from Single Particle Electron Microscopy [link] paper   A Bayesian Method for 3-D Macromolecular Structure Inference using Class Average Images from Single Particle Electron Microscopy [link] website   link   bibtex  
  2009 (4)
Estimating Contact Dynamics. Brubaker, M. A.; Sigal, L.; and Fleet, D. J. In Proceedings of the International Conference on Computer Vision (ICCV), 2009.
Estimating Contact Dynamics [pdf] paper   Estimating Contact Dynamics [link] mocapresults   Estimating Contact Dynamics [link] mocapyoutube   Estimating Contact Dynamics [link] videoresults   Estimating Contact Dynamics [link] videoyoutube   link   bibtex  
A Bayesian method for 3D reconstruction of macromolecular structure using class averages from single particle electron microscopy. Jaitly, N.; Brubaker, M. A.; Rubinstein, J.; and Lilien, R. In Neural Information Processing Systems Workshop: Machine Learning in Computational Biology (MLCB), December 2009.
link   bibtex  
Video-based People Tracking. Brubaker, M. A.; Sigal, L.; and Fleet, D. J. In Nakashima, H.; Aghajan, H.; and Augusto, J., editor(s), Handbook on Ambient Intelligence and Smart Environments. Springer Verlag, 2009.
Video-based People Tracking [pdf] paper   link   bibtex  
Physics-based Human Motion Modelling for people tracking: A short tutorial. Brubaker, M. A.; Sigal, L.; and Fleet, D. J. Tutorial at IEEE International Conference of Computer Vision, Kyoto, Japan, 2009.
link   bibtex  
  2008 (1)
The Kneed Walker for Human Pose Tracking. Brubaker, M. A.; and Fleet, D. J. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
The Kneed Walker for Human Pose Tracking [pdf] paper   The Kneed Walker for Human Pose Tracking [link] video   The Kneed Walker for Human Pose Tracking [link] youtube   link   bibtex  
  2007 (1)
Physics-based person tracking using simplified lower-body dynamics. Brubaker, M. A.; Fleet, D. J.; and Hertzmann, A. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007.
Physics-based person tracking using simplified lower-body dynamics [pdf] paper   Physics-based person tracking using simplified lower-body dynamics [link] video   Physics-based person tracking using simplified lower-body dynamics [link] youtube   link   bibtex  
  2006 (2)
Physics-based Human Pose Tracking. Brubaker, M. A.; Fleet, D. J.; and Hertzmann, A. In Neural Information Processing Systems Workshop: Evaluation of Articulated Human Motion and Pose Estimation (EHuM), December 2006.
link   bibtex  
Physics-Based Priors for Human Pose Tracking. Brubaker, M. A. Master's thesis, University of Toronto, 2006.
Physics-Based Priors for Human Pose Tracking [pdf] thesis   link   bibtex