Hello!
Andrew Delong I was a postdoc working with Yuri Boykov and Olga Veksler as part of the computer vision research group.
Sadly I have moved.
My new home is at the University of Toronto.
You may still spot me in London occasionally...
I'll miss everyone.

I like butter chicken. I also like the new Battlestar Galactica, Dexter, and have a mild crush on Tina Fey. The success of The Secret has shattered my faith in humanity.

Your moment of Zen...
We seldom stop to think that we are still creatures of the sea, able to leave it only because, from birth to death, we wear the water-filled space suits of our skins.
Next time you walk across campus, think of that quote as you look around. If you're like me, you can't help but smile to yourself at the thought of it.

Research interests:

  • optimisation • machine learning & inference • medical imaging • GPGPU

Journal publications:

  1. Minimizing Energies with Hierarchical Costs. Andrew Delong, Lena Gorelick, Olga Veksler, and Yuri Boykov. International Journal of Computer Vision (IJCV), 100(1):38–58, October 2012.
  2. Fast Approximate Energy Minimization with Label Costs. Andrew Delong,
    Anton Osokin, Hossam N. Isack, and Yuri Boykov. International Journal of Computer Vision (IJCV), 96(1):1–27, January 2012. [ slides, code ]

Conference publications:

  1. Fast Fusion Moves for Multi-Model Estimation. Andrew Delong, Olga Veksler, and Yuri Boykov. In European Conference on Computer Vision (ECCV), October 2012. [ code coming soon ]
  2. Segmentation with Non-Linear Regional Constraints via Line-Search Cuts. Lena Gorelick, Frank R. Schmidt, Yuri Boykov, Andrew Delong, and Aaron Ward. In European Conference on Computer Vision (ECCV), October 2012.
  3. Recursive MDL via Graph Cuts: Application to Segmentation. Lena Gorelick, Andrew Delong, Olga Veksler, and Yuri Boykov. In International Conference on Computer Vision (ICCV), November 2011. [ poster ]
  4. Interactive Segmentation with Super Labels. Andrew Delong, Lena Gorelick
    Frank R. Schmidt, Olga Veksler, and Yuri Boykov. In Energy Min. Methods in Comp. Vision and Pattern Recognition (EMMCVPR), July 2011. [ slides ]
  5. Fast Approximate Energy Minimization with Label Costs. Andrew Delong,
    Anton Osokin, Hossam N. Isack, and Yuri Boykov. In Computer Vision and Pattern Recognition (CVPR), June 2010. [ poster, slides, code ]
  6. Globally Optimal Segmentation of Multi-Region Objects. Andrew Delong and    Yuri Boykov. In Int'l Conference on Computer Vision (ICCV), October 2009.
  7. A Scalable Graph-Cut Algorithm for N-D Grids. Andrew Delong and Yuri Boykov. In Computer Vision and Pattern Recognition (CVPR), June 2008.
  8. An Integral Solution to Surface Evolution PDEs via Geo-Cuts. Yuri Boykov, Vladimir Kolmogorov, Daniel Cremers, Andrew Delong. In European Conference on Computer Vision (ECCV), LNCS 3953, 3:409–422, May 2006.

PhD Thesis:

Papers/articles that I particularly liked:

  1. Sustainable Energy – without the hot air, David J.C. MacKay, December 2008.
  2. Calculus Reform, David Mumford. Replies [1,2] by David Klein & Jerry Rosen.
  3. An Impossibility Theorem for Clustering, Jon Kleinberg, 2003
  4. Boosting Algorithms as Gradient Descent. Llew Mason et al., 2000.

Instructor for...

  • CS 3388 – Introduction to Computer Graphics (Fall 2011)
  • CS 1037 – Computer Science Fundamentals II (Fall 2010)

Teaching Assistant for...

  • CS 3340 – Analysis of Algorithms (Winter 2010)
  • CS 1037 – Computer Science Fundamentals II (Fall 2009)
  • CS 1037 – Computer Science Fundamentals II (Fall 2008)
  • CS 3307 – Object Oriented Design & Analysis (Winter 2008)
  • CS 1037 – Computer Science Fundamentals II (Fall 2007)
  • CS 1037 – Computer Science Fundamentals II (Fall 2006)
Created Sep 8, 2006   --   Updated Aug 15, 2011   --   ©2011 Andrew Delong    
Andrew Delong >> Enter for hot girls!! >>