Sebastian Nowozin

Welcome!

My name is Sebastian Nowozin and I am researcher at Microsoft Research, Cambridge, UK. On this page you find publications and software related to my work.

I am looking for PhD student collaborators for possible internships or visits to Microsoft Research Cambridge, UK. If you work at the intersection of machine learning and computer vision, please send me an email.

News

April 2013. At the Microsoft Machine Learning Summit in Paris, I was interviewed together with Prof. Fei-Fei Li in the Research in Focus series on the topic of computer vision and machine learning. See the interview.
February 2013. I am co-organizing the CVPR 2013 workshop Structured Prediction: Tractability, Learning, and Inference.
November 2012. Decision Tree Fields code released, authored by Toby Sharp and myself.

Students

Andreas Lehrmann, jointly supervised with Peter Gehler

Research

My main research interest is in developing machine learning techniques suitable for solving high-level computer vision tasks, such as image classification and object recognition.

High-level computer vision tasks are a unique source of hard machine learning problems for three reasons. First, in contrast to physics-based processes we do not know the correct model (model uncertainty). Second, humans excel at all high-level vision tasks and thus can provide data and assess model performance (ground truth oracle). Third, image and video data is available for free at an enormous scale (data availability). These properties make computer vision a particularly attractive area for machine learning research.

I am particularly interested in using mathematical optimization as a tool to solve computer vision machine learning tasks.

Publications and related materials

2013

Jeremy Jancsary, Sebastian Nowozin, Carsten Rother, "Learning Convex QP Relaxations for Structured Prediction", (PDF), 2013 International Conference on Machine Learning (ICML 2013).
Uwe Schmidt, Carsten Rother, Sebastian Nowozin, Jeremy Jancsary, Stefan Roth, "Discriminative Non-blind Deblurring", (PDF), 2013 Conference on Computer Vision and Pattern Recognition (CVPR 2013).
Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Jan Lellmann, Nikos Komodakis, Carsten Rother, "A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems", (PDF, project link soon), 2013 Conference on Computer Vision and Pattern Recognition (CVPR 2013).

2012

Jeremy Jancsary, Sebastian Nowozin, Carsten Rother, "Non-parametric CRFs for Image Labeling", (PDF), Modern Nonparametric Methods in Machine Learning, NIPS workshop paper.
Sungwoong Kim, Sebastian Nowozin, Pushmeet Kohli, Chang D. Yoo, "Task-Specific Image Partitioning", (PDF), IEEE Transactions on Image Processing.
Jeremy Jancsary, Sebastian Nowozin, Carsten Rother, "Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art", (PDF, supplementary, project), 12th European Conference on Computer Vision.
Sebastian Nowozin, Jamie Shotton, "Action Points: A Representation for Low-latency Online Human Action Recognition", (PDF, MSR link), technical report.
Andreas Müller, Sebastian Nowozin, Christoph H. Lampert, "Information Theoretic Clustering using Minimum Spanning Trees", (PDF), DAGM-OAGM 2012.
Christoph Dann, Peter V. Gehler, Stefan Roth, Sebastian Nowozin, "Pottics - The Potts Topic Model for Semantic Segmentation", (PDF), DAGM-OAGM 2012.
Sebastian Nowozin, "Improved Information Gain Estimates for Decision Tree Induction", (PDF, arXiv, video recording), 29th International Conference on Machine Learning (ICML 2012).
Jeremy Jancsary, Sebastian Nowozin, Toby Sharp, Carsten Rother, "Regression Tree Fields -- An Efficient, Non-parametric Approach to Image Labeling Problems", (PDF, supplementary materials, project), 2012 Conference on Computer Vision and Pattern Recognition (CVPR 2012).
Simon Fothergill, Helena Mentis, Pushmeet Kohli, Sebastian Nowozin, "Instructing People for Training Gestural Interactive Systems", (PDF), ACM SIGCHI Conference on Human Factors in Computing Systems (CHI 2012).

2011

Sungwoong Kim, Sebastian Nowozin, Pushmeet Kohli, Chang D. Yoo, "Higher-Order Correlation Clustering for Image Segmentation", (PDF), 25th Annual Conference on Neural Information Processing Systems (NIPS 2011).
Sebastian Nowozin, Carsten Rother, Shai Bagon, Toby Sharp, Bangpeng Yao, Pushmeet Kohli, "Decision Tree Fields", (PDF, supplementary materials, talk slides, poster, code, hard energy minimization instances (142MB)), 13th International Conference on Computer Vision (ICCV 2011).
Suvrit Sra, Sebastian Nowozin, and Stephen J. Wright (Editors), "Optimization for Machine Learning", (publisher link), edited volume published November 2011, Neural Information Processing series, MIT Press.
Patrick Pletscher, Sebastian Nowozin, Pushmeet Kohli, Carsten Rother, "Putting MAP back on the map", (PDF, supplementary), 33rd Annual Symposium of the German Association for Pattern Recognition (DAGM 2011).
Tutorial: Sebastian Nowozin and Christoph H. Lampert, "Structured Learning and Prediction in Computer Vision", (PDF, updated May 2011), Foundations and Trends in Computer Graphics and Vision series of now publishers. Tutorial slides online.
Dhruv Batra, Sebastian Nowozin, Pushmeet Kohli, "Tighter Relaxations for MAP-MRF Inference: A Local Primal-Dual Gap based Separation Algorithm", (PDF), International Conference on Artificial Intelligence and Statistics (AISTATS 2011).
Taesup Kim, Sebastian Nowozin, Pushmeet Kohli, Chang D. Yoo, "Variable Grouping for Energy Minimization", (PDF), IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011).
Hiroto Saigo, Andre Altmann, Jasmina Bogojeska, Fabian Müller, Sebastian Nowozin, Thomas Lengauer, "Learning from Past Treatments and Their Outcome Improves Prediction of In Vivo Response to Anti-HIV Therapy", (PDF), Statistical Applications in Genetics and Molecular Biology, Vol. 10 (2011), Issue 1.

2010

Sebastian Nowozin, Peter V. Gehler, and Christoph H. Lampert, "On Parameter Learning in CRF-based Approaches to Object Class Image Segmentation", (PDF, supplementary), 11th European Conference on Computer Vision (ECCV 2010).
Tutorial: Carsten Rother and Sebastian Nowozin, "Higher-order Models in Computer Vision", (homepage, PDF slides), IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010).
Sebastian Nowozin and Christoph H. Lampert, "Global Interactions in Random Field Models: A Potential Function Ensuring Connectedness", (PDF, publisher link), SIAM Journal on Imaging Sciences (SIIMS), Vol. 3, Issue 4, 2010.

2009

Sebastian Nowozin, "Learning with Structured Data: Applications to Computer Vision", (PDF) PhD dissertation at the Technical University of Berlin.
Peter V. Gehler and Sebastian Nowozin, "On Feature Combination Methods for Multiclass Object Classification", (PDF, talk slides, project), IEEE International Conference on Computer Vision (ICCV 2009).
Paramveer S. Dhillon, Sebastian Nowozin, and Christoph H. Lampert, "Combining Appearance and Motion for Human Action Classification in Videos", (PDF), 1st International Workshop on Visual Scene Understanding (ViSU 09).
Sebastian Nowozin and Stefanie Jegelka, "Solution Stability in Linear Programming Relaxations: Graph Partitioning and Unsupervised Learning", (PDF), International Conference on Machine Learning (ICML 2009).
Sebastian Nowozin and Christoph H. Lampert, "Global Connectivity Potentials for Random Field Models", (PDF, additional material, project), IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009).
Peter V. Gehler and Sebastian Nowozin, "Let the Kernel Figure it Out; Principled Learning of Pre-processing for Kernel Classifiers", (PDF, project) IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009).

2008

Sebastian Nowozin and Koji Tsuda, "Frequent Subgraph Retrieval in Geometric Graph Databases", (PDF, project) IEEE International Conference on Data Mining (ICDM 2008).
Peter V. Gehler and Sebastian Nowozin, "Infinite Kernel Learning", (PDF, project), Max Planck Institute for Biological Cybernetics Techreport TR-178.
Hiroto Saigo, Sebastian Nowozin, Tadashi Kadowaki, Taku Kudo and Koji Tsuda, "gBoost: A Mathematical Programming Approach to Graph Classification and Regression", (PDF, project), Machine Learning Journal, Springer, Vol 75, Number 1.
Sebastian Nowozin and Gökhan BakIr, "A Decoupled Approach to Exemplar-based Unsupervised Learning", (PDF, project), 25th International Conference on Machine Learning (ICML 2008).
Paramveer S. Dhillon, Sebastian Nowozin, and Christoph H. Lampert, "Combining Appearance and Motion for Human Action Classification in Videos", (PDF), Max Planck Institute for Biological Cybernetics Techreport TR-174.
Sebastian Nowozin and Koji Tsuda, "Frequent Subgraph Retrieval in Geometric Graph Databases", (PDF, project), Max Planck Institute for Biological Cybernetics Techreport TR-180, extended version of ICDM 2008 paper.

2007

Sebastian Nowozin, Gökhan BakIr, and Koji Tsuda, "Discriminative Subsequence Mining for Action Classification", (PDF, project), IEEE International Conference on Computer Vision (ICCV 2007).
Sebastian Nowozin, Koji Tsuda, Takeaki Uno, Taku Kudo, and Gökhan BakIr, "Weighted Substructure Mining for Image Analysis", (PDF, additional material, project), IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007).

Community

Area chair: NIPS (2012)
Editorial activities: JMLR action editor (2013-)
Reviewer, machine learning conferences: NIPS (2008-2011, best reviewer award 2008), ICML (2009-2013), AISTATS (2010), UAI (2009), ECML/PKDD (2010)
Reviewer, computer vision conferences: CVPR (2010-2013), ECCV (2010, 2012), ICCV (2011)
Reviewer, machine learning journals: JMLR, TNN, ADAC
Reviewer, computer vision journals: TPAMI, IJCV
PC member, workshops: Machine Learning Open Source Software (at ICML 2010), Structured Models in Computer Vision (at CVPR 2010), 1st International Workshop on Parts and Attributes (at ECCV 2010), HiPot: Workshop on Higher-Order Models and Global Constraints in Computer Vision (at ECCV 2012).
Workshop organizer: Optimization for Machine Learning (OPT 2008-2011 at NIPS), Structured Prediction: Tractability, Learning, and Inference (at CVPR 2013).

Software and Datasets

MSRC-12 Kinect gesture data set. Details are described in our CHI 2012 paper.
Decision Tree Fields - C++ implementation of the ICCV 2011 model
grante - C++ discrete factor graph estimation and inference library
Tuwo - C++ computer vision library
gboost - graph mining and classification
pboost - sequence mining and classification
freqgeo - geometric subgraph mining
infex - exemplar-based models for unsupervised learning
lpstability - multicut LP relaxation code

Contact

You can reach me by email at nowozin@gmail.com.