Dr. Sebastian Nowozin

Portrait of Sebastian NowozinWelcome! 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.


My main research interest is in developing machine learning models and algorithms suitable for solving problems arising in computer vision.

High-level computer vision tasks are a unique source of hard machine learning problems for three reasons. First, in contrast to physics-based processes, for many tasks we currently do not have accurate predictive models, which means we have to work in situations with high model uncertainty and misspecification. Second, humans excel at high-level vision tasks that were beneficial to our evolutionary survival and therefore humans can provide accurate ground truth data and model criticism (ground truth oracle). Third, image and video data is available for free at an enormous scale (data availability) with inexpensive cameras enabling novel consumer applications. These properties make computer vision a particularly attractive area for machine learning research.

In terms of methodology I am particularly interested in structured prediction, that is, using statistical models to address structured decision tasks.

In terms of industrial applications of my work, I have worked in image processing (denoising, demosaicing, deblurring), time-of-flight imaging, gesture recognition, cloud-based machine learning, and optimization.



Former students:

Publications and related materials












  • Area chair: NIPS (2012, 2014, 2015), ICML (2015), ECCV (2016)
  • Editorial activities: JMLR action editor (2013-), IJCV associate editor (2014-), TPAMI associate editor (2014-)
  • Reviewer, machine learning conferences: NIPS (2008-2011, 2013, 2016, best reviewer award 2008), ICML (2009-2014), GCPR (2013-2016), AISTATS (2010), UAI (2009), ECML/PKDD (2010)
  • Reviewer, computer vision conferences: CVPR (2010-2016), ECCV (2010, 2012, 2014), ICCV (2011, 2013, 2015)
  • 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). International Workshop on Graphical Models in Computer Vision (GMCV 2014) (at ECCV 2014). Machine Learning for Intelligent Image and Video Processing (at ICCV 2015).

Software and Datasets



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