Assistant Professor Toyota Technological Institute at Chicago 6045 S. Kenwood Ave. Chicago, IL 60637 e-mail: rurtasun (at) ttic (dot) edu tel: +1 (773) 834-2550 fax: +1 (773) 834-9881

Since September 2009, I'm an Assistant Professor at TTI-Chicago, a philanthropically endowed academic institute located in the campus of the University of Chicago. I was a visiting professor at ETH Zurich during the spring semester of 2010, working with Prof. Marc Pollefeys. Previously I was a postdoctoral research scientist at UC Berkeley EECS and ICSI. Before that, I was a postdoctoral associate at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, where I worked with Prof. Trevor Darrell.

I completed my PhD at the Computer Vision Laboratory, at EPFL, Switzerland, on June 2006, under the supervision of Prof. Pascal Fua and Prof. David Fleet at the University of Toronto. I previously worked as a research assistant at the Ecole National Superior de Telecomunication (ENST) in Paris, in the Image Procesing Department. I graduated as an Electric Engineer in the Universidad Publica de Navarra, Pamplona, Spain. I did my Master Thesis in Eurecom, France.

My major interests are statistical learning and computer vision, with a particular interest in non-parametric Bayesian statistics, latent variable models, structured prediction and their application to 3D scene understanding and human pose estimation. I also like to do computer graphics from time to time.

I'm looking for motivated students interested in the areas of machine learning, computer vision and graphics. Please contact me for details.

Postdocs

• Marcus Brubaker (jointly with David Fleet at University of Toronto)

Current students

• Andreas Geiger (jointly with Christoph Stiller at Karlsruhe Institute of Technology)
• Alexander Schwing (jointly with Marc Pollefeys and Tamir Hazan at ETH Zurich
• Lam Tram (at TTIC)
• Jian Yao (at TTIC)

Visiting students

• Aydin Varol (from EPFL)
• Jose Javier Yebes (from Universidad de Alcala)

Past students

• Mario Christoudias (PhD, jointly with Trevor Darrell at MIT). Now postdoc at EPFL.
• Taehwan Kim (Masters, jointly supervised with Greg Shakhnarovich at TTIC)
• Alex Shyr (PhD, jointly with Michael I. Jordan and Trevor Darrell at UC Berkeley)

Past visiting students

• Roland Angst (from ETH Zurich).
• Martin Hjelm (from KTH)
• Angela Yao (from ETH Zurich)

Professional Service

• Area Chair / Senior Program Committee: NIPS 2010, NIPS 2011, UAI 2012
• Program Committee (computer vision): ICCV 2007, 2009, 2011, CVPR 2007, 2009, 2010, 2011, ECCV 2008, 2010, ACCV 2010, BMVC 2011
• Program Committee (machine learning): NIPS 2008, 2009, ICML 2008, 2009, 2010, 2011, AISTATS 2010, 2011, IJCAI 2009

Teaching

• Spring 2012 TTI course: Visual Recognition.
• Spring 2011 TTI course: Learning and Inference in Graphical Models, with Tamir Hazan
• Spring 2010 ETH Zurich course: Human Motion Anaysis.
• I'm helping David McAllester and Nathan Srebro teach the TTI Autumn 2009 course: Statistical Learning in Artificial Intelligence.
• Fall 2007 MIT course: 6.976, Seminar on Human Motion Tracking with Trevor Darrell.
• I TA the spring 2002-2006 EPFL course: Introduction to computer vision.

Publications

• List of ALL publications

Curriculum Vitae

• Full CV

Funding

• NSF 1017626: "Probabilistic Latent Variable Models for Sparse Data".

Highlights of Recent/Upcoming papers (ONLY last 2 years)

• M. Brubaker, M. Salzmann and R. Urtasun
  A Family of MCMC Methods on Implicitly Defined Manifolds
  In International Conference on Artificial Intelligence and Statistics (AISTATS), Gran Canaria, Spain, April 2012


• A. Geiger, C. Wojek and R. Urtasun
  Joint 3D Estimation of Objects and Scene Layout [pdf] [supplementary] [video]
  In Neural Information Processing Systems (NIPS), Granada, Spain, December 2011


• A. Yao, J. Gall, L. van Gool and R. Urtasun
  Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities [pdf] [video learning] [video humaneva] [software]
  In Neural Information Processing Systems (NIPS), Granada, Spain, December 2011


• M. Salzmann and R. Urtasun
  Physically-based Motion Models for 3D Tracking: A Convex Formulation
  In International Conference on Computer Vision (ICCV), Barcelona, Spain, November 2011


• J. Peng, T. Hazan, D. McAllester and R. Urtasun
  Convex Max-Product over Compact Sets for Protein Folding (oral presentation)
  In International Conference in Machine Learning (ICML), Bellevue, Washington, June 2011


• A. Geiger, M. Lauer and R. Urtasun
  A generative model for 3D urban scene understanding from movable platforms [pdf] [talk] [slides] [data] [software] (oral presentation)
  In Conference of Computer Vision and Pattern Recognition (CVPR), Colorado Springs, June 2011


• A. Schwing, T. Hazan, M. Pollefeys and R. Urtasun
  Distributed Message Passing for Large Scale Graphical Models [pdf] [software]
  In Conference of Computer Vision and Pattern Recognition (CVPR), Colorado Springs, June 2011


• A. Shyr, T. Darrell, M. Jordan and R. Urtasun
  Supervised Hierarchical Pitman-Yor Process for Natural Scene Segmentation
  In Conference of Computer Vision and Pattern Recognition (CVPR), Colorado Springs, June 2011


• H. Hamer, J. Gall, R. Urtasun and L. Van Gool
  Data-Driven Animation of Hand- Object Interaction (oral presentation)
  In Face and Gesture Recognition (FGR), Santa Barbara, April 2011


• T. Hazan and R. Urtasun
  A Primal-Dual Message-Passing Algorithm for Approximated Large Scale Structured Prediction
  In Neural Information Processing Systems (NIPS), Vancouver, December 2010


• M. Salzmann and R. Urtasun
  Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation
  In Neural Information Processing Systems (NIPS), Vancouver, December 2010


• T. Kim, G. Shakhnarovich and R. Urtasun
  Sparse coding for learning interpretable spatio-temporal primitives
  In Neural Information Processing Systems (NIPS), Vancouver, December 2010


• A. Geiger, M. Roser and R. Urtasun
  Efficient Large-Scale Stereo Matching [pdf] [talk] [software] (oral presentation)
  In Asian Conference in Computer Vision (ACCV), Queenstown, New Zealand, November 2010


• T. Hazan and R. Urtasun
  Approximated Structured Prediction for Learning Large Scale Graphical Models
  Arxiv 1006.2899, June 2010


• C. M. Christoudias, R. Urtasun, M. Salzmann and T. Darrell
  Learning to Recognize Objects from Unseen Modalities [pdf] [project page] [software]
  In European Conference in Computer Vision (ECCV), Crete, September 2010


• M. Salzmann and R. Urtasun
  Combining Discriminative and Generative Methods for 3D Deformable Surface and Articulated Pose Reconstruction [pdf] [supplementary] (oral presentation)
  In Conference in Computer Vision and Pattern Recognition (CVPR), San Francisco, June 2010


• A. Shyr, R. Urtasun and M. I. Jordan
  Sufficient Dimensionality Reduction for Visual Sequence Classification
  In Conference in Computer Vision and Pattern Recognition (CVPR), San Francisco, June 2010


• M. Salzmann, C. Ek, R. Urtasun and T. Darrell
  Factorized Orthogonal Latent Spaces
  In International Conference on Artificial Intelligence and Statistics (AISTATS), Sardinia, Italy, May 2010


• A. Kapoor, K. Grauman, R. Urtasun and T. Darrell
  Gaussian Processes for Object Categorization
  In International Journal of Computer Vision (IJCV) 2010

Talks on the web

• A Gaussian Process View on MKL, at the NIPS 2010 workshop on New Directions in Multiple Kernel Learning (NIPS 2010) .




• Non-Linear Matrix Factorization with Gaussian Processes, at the 26th International Conference on Machine Learning (ICML 2009).




• Topologically-Constrained Latent Variable Models, at the 25th International Conference on Machine Learning (ICML 2008).




• Gaussian Processes for Monocular 3D People tracking, at the Gaussian Processes in Practice Workshop, UK 2006.