Selected Publications by Topic

Theses

• Graphical Models for Visual Object Recognition and Tracking E. B. Sudderth Doctoral Thesis, Massachusetts Institute of Technology, May 2006.  
• Embedded Trees: Estimation of Gaussian Processes on Graph with Cycles E. B. Sudderth Masters Thesis, Massachusetts Institute of Technology, Feb. 2002.  

Selected Presentations

• Toward Reliable Bayesian Nonparametric Learning E. Sudderth, D. Wei, M. Bryant, M. Hughes, and E. Fox NIPS Workshop on Bayesian Nonparametric Models for Reliable Planning and Decision-Making Under Uncertainty, Dec. 2012.  
• Spatial Bayesian Nonparametrics for Natural Image Segmentation E. Sudderth, M. Jordan, and S. Ghosh NIPS Workshop on Bayesian Nonparametrics: Hope or Hype? Dec. 2011.  
• Representation in Low-Level Visual Learning E. Sudderth NSF Workshop on Frontiers in Computer Vision, Aug. 2011.  
• Visual Learning via Topics, Transformations, and Trees E. Sudderth NIPS Workshop on Transfer Learning by Learning Rich Generative Models, Dec. 2010.  
• Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes E. Sudderth and M. Jordan Neural Information Processing Systems, Dec. 2008.  
• Loop Series and Bethe Variational Bounds in Attractive Graphical Models E. Sudderth, M. Wainwright, and A. Willsky Allerton Conference on Communication, Control, and Computing, Oct. 2007.  

Object Recognition & Scene Understanding

• A Fully-Connected Layered Model of Foreground and Background Flow D. Sun, J. Wulff, E. Sudderth, H. Pfister, and M. Black IEEE Conference on Computer Vision & Pattern Recognition, June 2013.  
• From Deformations to Parts: Motion-based Segmentation of 3D Objects S. Ghosh, E. Sudderth, M. Loper, and M. Black Neural Information Processing Systems, Dec. 2012.  
• Layered Segmentation and Optical Flow Estimation Over Time D. Sun, E. Sudderth, and M. Black IEEE Conference on Computer Vision & Pattern Recognition, June 2012.  
• Nonparametric Learning for Layered Segmentation of Natural Images S. Ghosh and E. Sudderth IEEE Conference on Computer Vision & Pattern Recognition, June 2012.  
• Nonparametric Discovery of Activity Patterns from Video Collections M. Hughes and E. Sudderth CVPR Workshop on Perceptual Organization in Computer Vision.  
• Spatial Distance Dependent Chinese Restaurant Processes for Image Segmentation S. Ghosh, A. Ungureanu, E. Sudderth, and D. Blei Neural Information Processing Systems, Dec. 2011.  
• Layered Image Motion with Explicit Occlusions, Temporal Consistency, and Depth Ordering D. Sun, E. Sudderth, and M. Black Neural Information Processing Systems, Dec. 2010.  
• Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes E. Sudderth and M. Jordan Neural Information Processing Systems, Dec. 2008.  
• Describing Visual Scenes Using Transformed Objects and Parts E. Sudderth, A. Torralba, W. Freeman, and A. Willsky International Journal of Computer Vision, vol. 77, Mar. 2008.  
• Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes J. Kivinen, E. Sudderth, and M. Jordan IEEE International Conference on Computer Vision, Oct. 2007.  
• Depth from Familiar Objects: A Hierarchical Model for 3D Scenes E. Sudderth, A. Torralba, W. Freeman, and A. Willsky IEEE Conference on Computer Vision & Pattern Recognition, June 2006.  
• Describing Visual Scenes using Transformed Dirichlet Processes E. Sudderth, A. Torralba, W. Freeman, and A. Willsky Neural Information Processing Systems, Dec. 2005.  
• Learning Hierarchical Models of Scenes, Objects, and Parts E. Sudderth, A. Torralba, W. Freeman, and A. Willsky International Conference on Computer Vision, Oct. 2005.  

Bayesian Nonparametrics

• Truly Nonparametric Online Variational Inference for Hierarchical Dirichlet Processes M. Bryant and E. Sudderth Neural Information Processing Systems, Dec. 2012.  
• Effective Split-Merge Monte Carlo Methods for Nonparametric Models of Sequential Data M. Hughes, E. Fox, and E. Sudderth Neural Information Processing Systems, Dec. 2012.  
• The Nonparametric Metadata Dependent Relational Model D. Kim, M. Hughes, and E. Sudderth International Conference on Machine Learning, June 2012.  
• The Doubly Correlated Nonparametric Topic Model D. Kim and E. Sudderth Neural Information Processing Systems, Dec. 2011.  
• A Sticky HDP-HMM with Application to Speaker Diarization E. Fox, E. Sudderth, M. Jordan, and A. Willsky Annals of Applied Statistics, vol. 5(2A), 2011.  
• Bayesian Nonparametric Inference of Switching Dynamic Linear Models E. Fox, E. Sudderth, M. Jordan, and A. Willsky IEEE Transactions on Signal Processing, vol. 59(4), Apr. 2011.  
• Bayesian Nonparametric Learning of Markov Switching Processes E. Fox, E. Sudderth, M. Jordan, and A. Willsky IEEE Signal Processing Magazine, vol. 27(6), Nov. 2010.  
• Sharing Features among Dynamical Systems with Beta Processes E. Fox, E. Sudderth, M. Jordan, and A. Willsky Neural Information Processing Systems, Dec. 2009.  
• Nonparametric Bayesian Identification of Jump Systems with Sparse Dependencies E. Fox, E. Sudderth, M. Jordan, and A. Willsky IFAC Symposium on System Identification, July 2009.  
• The Sticky HDP-HMM: Bayesian Nonparametric Hidden Markov Models with Persistent States E. Fox, E. Sudderth, M. Jordan, and A. Willsky MIT LIDS Technical Report P-2777, revised May 2009.  
• Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes E. Sudderth and M. Jordan Neural Information Processing Systems, Dec. 2008.  
• Nonparametric Bayesian Learning of Switching Linear Dynamical Systems E. Fox, E. Sudderth, M. Jordan, and A. Willsky Neural Information Processing Systems, Dec. 2008.  
• An HDP-HMM for Systems with State Persistence E. Fox, E. Sudderth, M. Jordan, and A. Willsky International Conference on Machine Learning, July 2008.  
• Describing Visual Scenes Using Transformed Objects and Parts E. Sudderth, A. Torralba, W. Freeman, and A. Willsky International Journal of Computer Vision, vol. 77, Mar. 2008.  
• Learning Multiscale Representations of Natural Scenes Using Dirichlet Processes J. Kivinen, E. Sudderth, and M. Jordan IEEE International Conference on Computer Vision, Oct. 2007.  
• Image Denoising with Nonparametric Hidden Markov Trees J. Kivinen, E. Sudderth, and M. Jordan IEEE International Conference on Image Processing, Sep. 2007.  
• Hierarchical Dirichlet Processes for Tracking Maneuvering Targets E. Fox, E. Sudderth, and A. Willsky International Conference on Information Fusion, July 2007.  
• Describing Visual Scenes using Transformed Dirichlet Processes E. Sudderth, A. Torralba, W. Freeman, and A. Willsky Neural Information Processing Systems, Dec. 2005.  

Hand Tracking & Nonparametric Belief Propagation

• Nonparametric Belief Propagation E. Sudderth, A. Ihler, M. Isard, W. Freeman, and A. Willsky Communications of the ACM, vol. 53(10), Oct. 2010.  
• Nonparametric Belief Propagation for Distributed Tracking of Robot Networks with Noisy Inter-Distance Measurements J. Schiff, E. Sudderth, and K. Goldberg IEEE International Conference on Intelligent Robots and Systems, Oct. 2009.  
• Distributed Occlusion Reasoning for Tracking with Nonparametric Belief Propagation E. Sudderth, M. Mandel, W. Freeman, and A. Willsky Neural Information Processing Systems, Dec. 2004.  
• Visual Hand Tracking Using Nonparametric Belief Propagation E. Sudderth, M. Mandel, W. Freeman, and A. Willsky Workshop on Generative Model Based Vision, CVPR, June 2004.  
• Efficient Multiscale Sampling from Products of Gaussian Mixtures A. Ihler, E. Sudderth, W. Freeman, and A. Willsky Neural Information Processing Systems, Dec. 2003.  
• Nonparametric Belief Propagation E. Sudderth, A. Ihler, W. Freeman, and A. Willsky IEEE Conference on Computer Vision & Pattern Recognition, June 2003.  

Graphical Models & Belief Propagation

• Minimization of Continuous Bethe Approximations: A Positive Variation J. Pacheco and E. Sudderth Neural Information Processing Systems, Dec. 2012.  
• Improved Variational Inference for Tracking in Clutter J. Pacheco and E. Sudderth IEEE Statistical Signal Processing Workshop, Aug. 2012.  
• Loop Series and Bethe Variational Bounds in Attractive Graphical Models E. Sudderth, M. Wainwright, and A. Willsky Neural Information Processing Systems, Dec. 2007.  
• Embedded Trees: Estimation of Gaussian Processes on Graphs with Cycles E. Sudderth, M. Wainwright, and A. Willsky IEEE Transactions on Signal Processing, vol. 52(11), Nov. 2004.  
• Projection Algebra Analysis of Error-Correcting Codes J. Yedidia, E. Sudderth, and J-P. Bouchaud Allerton Conference on Communication, Control, and Computing, Oct. 2001.  
• Tree-Based Modeling and Estimation of Gaussian Processes on Graphs with Cycles M. Wainwright, E. Sudderth, and A. Willsky Neural Information Processing Systems, Dec. 2000.  

Reviews & Tutorials

• Applied Bayesian Nonparametrics E. Sudderth Tutorial at the IEEE Conf. on Computer Vision & Pattern Recognition, June 2012.  
• Nonparametric Belief Propagation E. Sudderth, A. Ihler, M. Isard, W. Freeman, and A. Willsky Communications of the ACM, vol. 53(10), Oct. 2010.  
• Signal and Image Processing with Belief Propagation E. Sudderth and W. Freeman IEEE Signal Processing Magazine, DSP Applications Column, Mar. 2008.  

©2013 Erik Sudderth
Valid XHTML & CSS