I will be joining Google DeepMind in February 2015 as a Research Scientist.

In 2014 I was a post-doctoral researcher at Microsoft Research, and a member of the Machine Learning and Perception group in Cambridge.

I did my PhD at the University of Edinburgh, where I was a Carnegie scholar. My supervisors were Chris Williams, Bob Fisher and Amos Storkey.

During my PhD I was also at Oxford University working with Andrew Zisserman, and at Microsoft Research working with John Winn and Nicolas Heess.

Since 2012 I have helped organise the PASCAL Visual Object Classes challenge. In 2014 I also helped run the MSc industry project programme at University College London.

Full Curriculum Vitae

Last updated 05 Apr 2014: PDF.

Working papers

  • Consensus Message Passing for Layered Graphical Models Consensus Message Passing for Layered Graphical Models
    • Varun Jampani*
    • S. M. Ali Eslami*
    • Daniel Tarlow
    • Pushmeet Kohli
    • John Winn
    • 24 Oct 2014.

Publications

  • Just-In-Time Learning for Fast and Flexible Inference Just-In-Time Learning for Fast and Flexible Inference
    • S. M. Ali Eslami
    • Daniel Tarlow
    • Pushmeet Kohli
    • John Winn
    • 08 Dec 2014.
    Neural Information Processing Systems (NIPS), Montreal, Quebec, Canada.
  • The Pascal Visual Object Classes Challenge — a Retrospective The Pascal Visual Object Classes Challenge — a Retrospective
    • Mark Everingham
    • S. M. Ali Eslami
    • Luc Van Gool
    • Christopher K. I. Williams
    • John Winn
    • Andrew Zisserman
    • 27 Jun 2014.
    International Journal of Computer Vision (IJCV), Springer.
  • Assessing the Significance of Performance Differences on the PASCAL VOC Challenges via Bootstrapping Assessing the Significance of Performance Differences on the PASCAL VOC Challenges via Bootstrapping
    • Mark Everingham
    • S. M. Ali Eslami
    • Luc Van Gool
    • Christopher Williams
    • John Winn
    • Andrew Zisserman
    • 18 Oct 2013.
    Technical note.
  • The Shape Boltzmann Machine: a Strong Model of Object Shape The Shape Boltzmann Machine: a Strong Model of Object Shape
    • S. M. Ali Eslami
    • Nicolas Heess
    • Christopher K. I. Williams
    • John Winn
    • 11 Oct 2013.
    International Journal of Computer Vision (IJCV), Springer. CVPR special issue.
  • A Generative Model for Parts-based Object Segmentation A Generative Model for Parts-based Object Segmentation
    • S. M. Ali Eslami
    • Christopher K. I. Williams
    • 03 Dec 2012.
    Neural Information Processing Systems (NIPS), Lake Tahoe, California, USA.
  • The Shape Boltzmann Machine: a Strong Model of Object Shape The Shape Boltzmann Machine: a Strong Model of Object Shape
    • S. M. Ali Eslami
    • Nicolas Heess
    • John Winn
    • 16 Jun 2012.
    Computer Vision and Pattern Recognition (CVPR), Rhode Island, USA. Oral presentation.
  • Factored Shapes and Appearances for Parts-based Object Understanding Factored Shapes and Appearances for Parts-based Object Understanding
    • S. M. Ali Eslami
    • Christopher K. I. Williams
    • 29 Aug 2011.
    British Machine Vision Conference (BMVC), Dundee, UK. Oral presentation.

Theses

  • Generative Probabilistic Models for Object Segmentation Generative Probabilistic Models for Object Segmentation
    • S. M. Ali Eslami
    • Supervisor: Christopher K. I. Williams,
      Examiners: Richard Zemel, Vittorio Ferrari
    • 11 Oct 2013.
    The University of Edinburgh, PhD thesis.
  • Evolving Robust Control Strategies for Simulated Animats Evolving Robust Control Strategies for Simulated Animats
    • S. M. Ali Eslami
    • Supervisor: Subramanian Ramamoorthy
    • 31 Mar 2009.
    The University of Edinburgh, BEng dissertation.

Selected talks

  • Boltzmann Machines and their Extensions Boltzmann Machines and their Extensions
    • Heriot-Watt University, Edinburgh, UK (March 2013)
  • Generative Models of Images of Objects Generative Models of Images of Objects
    • Sharif University of Technology, Tehran, Iran (January 2013)
    • Redwood Institute at the University of California at Berkeley, USA (December 2012)
    • Bosch Research and Technology North America, Palo Alto, USA (December 2012)
    • Toyota Technological Institute, University of Chicago, Chicago, USA (June 2012)
    • New York University, New York, USA (June 2012)
  • The Shape Boltzmann Machine: a Strong Model of Object Shape The Shape Boltzmann Machine: a Strong Model of Object Shape
    • Computer Vision and Pattern Recognition (CVPR), Providence, USA (June 2012)
    • Rank Prize Symposium on Machine Learning and Vision, Windermere, UK (March 2012)
  • Factored Shapes and Appearances for Parts-based Object Understanding Factored Shapes and Appearances for Parts-based Object Understanding
    • British Machine Vision Conference, Dundee, UK (August 2011)
    • ACM Seminar, University of Tehran, Tehran, Iran (September 2011)
  • Hierarchical Probabilistic Models for Object Segmentation Hierarchical Probabilistic Models for Object Segmentation
    • CIFAR Summer School, Neural Computation and Adaptive Perception, Toronto, Canada (August 2010)
  • High Dynamic Range Lighting on the Xbox 360 High Dynamic Range Lighting on the Xbox 360
    • TechMeetup, Edinburgh, UK (April 2010)

Other things

  • The Zeroth Rule of Presentations The Zeroth Rule of Presentations
  • Patterns for Research in Machine Learning Patterns for Research in Machine Learning
  • Thoughts on the Role of Supervision in Computer Vision Thoughts on the Role of Supervision in Computer Vision
  • A Visual Summary of the PASCAL 2009 Dataset A Visual Summary of the PASCAL 2009 Dataset