Greg Shakhnarovich

Assistant Professor Toyota Technological Institute at Chicago 6045 S. Kenwood Ave. Chicago, IL 60637 e-mail gregory at ttic dot edu tel +1 (773) 834-2572 fax +1 (773) 834-9881

Brief bio:

Since February 2008, I am an Assistant Professor at TTI-Chicago, a philanthropically endowed academic computer science institute located on the University of Chicago campus.
We at TTI-Chicago continue to admit students to our PhD program. Please contact me for details.

Prior to coming to TTI-Chicago, I was a post-doctoral researcher at the Department of Computer Science of Brown University where I worked with Michael Black. I received my PhD degree at MIT where I worked at CSAIL with Trevor Darrell on computer vision and machine learning. My thesis topic was Learning Task-Specific Similarity.

Before coming to MIT, I was a graduate student in the Computer Science Department of the Technion, Israel Institute of Technology in Haifa, Israel, where I got my MSc thesis under the advisement of Ran El-Yaniv and Yoram Baram. I got my undergraduate degree in Math and CS from Hebrew University in Jerusalem, Israel.

My CV: PDF

Research interests:

• Computational vision: parsing of visual scenes, object detection and categorization, inferrind 3D and 2.5D structure from images and videos, parsing of visual motion
• Machine learning: example-base methods, supervised and semi-supervised learning of similarity and distance, general semi-supervised learning, structure learning for spatial/temporal data

Student collaborators

• Payman Yadollahpour (TTIC, PhD advisee)
• Daniel Glasner (Weizmann Institute of Sciences)
• Uri Patish (Weizmann Institute of Sciences)

MsC thesis, Technion, 2001: Statistical Data Cloning for Machine Learning. Advisors: Ran El-Yaniv and Yoram Baram.

PhD thesis, MIT, 2006: Learning Task-Specific Similarity. Advisor: Trevor Darrell.

Recent work and other news

• Kilian Weinberger, Brian Kulis and Dhruv Batra and I organized a NIPS 2011 workshop "Beyond Mahalanobis: Supervised Large-Scale Learning of Similarity".

• Workshop presentation: P. Yadollahpour, D. Batra, G. Shakhnarovich, "M-Best Modes: Diverse M-Best Solutions in MRFs", Workshop on Discrete Optimization in Machine Learning, NIPS 2011.

• Workshop presentation: D. Batra, G. Shakhnarovich. "Similarity Sensitive Nonlinear Embeddings", Workshop on Kernels and Distances for Computer Vision, ICCV 2011. [pdf]

Refereed publications, full list in reverse chronological order:

• D. Glasner, M. Galun, S. Alpert, R. Basri, G. Shakhnarovich, "Viewpoint-Aware Object Detection and Pose Estimation", ICCV 2011. [pdf], project page

• T. Kim, G. Shakhnarovich, R. Urtasun, "Sparse Coding for Learning Interpretable Spatio-Temporal Primitives", NIPS, 2010. [pdf], [correction]

• C. Vargas-Irwin, G. Shakhnarovich, P. Yadollahpour, J. M. K. Mislow, M. J. Black, J. P. Donoghue, "Decoding Complete Reach and Grasp Actions from Local Primary Motor Cortex Populations", The Journal of Neuroscience, 2010.

• A. Ritz, G. Shakhnarovich, A. R. Salomon, B. J. Raphael, "Discovery of Phosphorylation Motif Mixtures in Phosphoproteomics Data". Bioinformatics, 2009. abstract

• C. Demiralp, G. Shakhnarovich, S. Zhang, D. H. Laidlaw, "Slicing-based coherence measure for refining clusters of 3D curves." Proceedings of MICCAI Conference, 2008. [pdf]

• P. K. Artemiadis, G. Shakhnarovich, C. Vargas-Irwin, J. P. Donoghue, M. J. Black, "Decoding grasp aperture from motor-cortical population activity", IEEE Conf. on Neural Engineering, 2007. [pdf]

• G. Shakhnarovich, S.-P. Kim, M. J. Black, "Nonlinear physically-based models for decoding motor-cortical population activity", NIPS 2006. [pdf]
  

• L. Taycher, G. Shakhnarovich, D. Demirdjian, and T. Darrell, "Conditional Random People: Tracking Humans with CRFs and Grid Filters". Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, 2006. [pdf]
  Also in MIT CSAIL Technical Report MIT-CSAIL-2005-079, 2006 [pdf]

• N. Srebro, G. Shakhnarovich, S. Roweis, "An Investigation of Computational and Informational Limits in Gaussian Mixture Clustering". ICML, 2006. [pdf] [UoT technical report]

• G. Shakhnarovich, J. Fisher, "Performance of Approximate Nearest Neighbor Classification". Poster presented at Machine Learning Workshop at Snowbird, 2006, with preliminary results (work in progress).

  G. Shakhnarovich, T. Darrell, P. Indyk, editors, "Nearest-Neighbors methods in Learning and Vision: Theory and Practice". MIT Press, 2006.

• D. Demirdjian, L. Taycher, G. Shakhnarovich, K. Grauman, T. Darrell, "Avoiding the Streetlight Effect: Tracking by Exploring Likelihood Modes", Proceedings of the International Conference on Computer Vision,2005. [pdf]

• L. Ren, G. Shakhnarovich, J. Hodgins, H. Pfister, P. Viola, "Learning Silhouette Features for Control of Human Motion", ACM Transactions on Graphics,2005. [pdf]

• O. Aranjelovic, G. Shakhnarovich, J. Fisher, R. Cippola, T. Darrell, "Face Recognition with Image Sets Using Manifold Density Divergence", Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, pp. 581--588, 2005. [pdf]

• G. Shakhnarovich, B. Moghaddam, "Face Recognition in Subspaces", In Handbook of Face Recognition, S. Z. Li and A. K. Jain, Ed. Springer-Verlag,2004. [pdf]

• K. Grauman, G. Shakhnarovich, T. Darrell, "Virtual Visual Hulls: Example-Based 3D Shape Inference from a Single Silhouette", Proceedings of the 2nd Workshop on Statistical Methods in Video Processing,2004. [pdf]

• G. Shakhnarovich, P. Viola, T. Darrell, "Fast Pose Estimation with Parameter Sensitive Hashing", Proceedings of the International Conference on Computer Vision,2003.[pdf]

• K. Grauman, G. Shakhnarovich, T. Darrell, "Inferring 3D Structure with a Statistical Image-Based Shape Model", Proceedings of the International Conference on Computer Vision,2003. [pdf]

• K. Grauman, G. Shakhnarovich, T. Darrell, "A Bayesian Approach to Image-Based Visuall Hull Reconstruction", Proceedings IEEE Conf. on Computer Vision and Pattern Recognition,2003.[pdf]

• B. Moghaddam, G. Shakhnarovich, "Boosted Dyadic Kernel Discriminants", NIPS, 2002. [ps]

• G. Shakhnarovich, J. W. Fisher, T. Darrell, "Face recognition from long-term observations", Proceedings of European Conference on Computer Vision,2002. [pdf]

• G. Shakhnarovich, T. Darrell, "On Probabilistic Combination of Face and Gait Cues for Identification", Proceedings of the Int. Conf. on Automatic Face and Gesture Recognition,2002. [pdf]

• G. Shakhnarovich, P. Viola, B. Moghaddam, "A Unified Learning Framework for Real Time Face Detection and Classification", Proceedings of the Int. Conf. on Automatic Face and Gesture Recognition,2002. [pdf]

• G. Shakhnarovich, R. El-Yaniv, Y. Baram, "Smoothed Bootstrap and Statistical Data Cloning for Classifier Evaluation", Proccedings of International Conference on Machine Learning, 2001. [pdf]

• G. Shakhnarovich, L. Lee, T. Darrell, "Integrated Face and Gait Recognition From Multiple Views", Proceedings IEEE Conf. on Computer Vision and Pattern Recognition,2001. [pdf]

Teaching