David J. Fleet



  • Fellow
  • Learning in Machines & Brains


  • University of Toronto
Department of Computer Science


  • Canada


PhD (Computer Science), University of Toronto
MS (Computer Science), University of Toronto
BSc (Honours Computer Science and Mathematics), Queen's University


David Fleet is a computer scientist whose research interests include computer vision, machine learning, image processing, visual perception and visual neuroscience.

He is interested in how animals see, and in how we can develop machines with similar or better visual capabilities. Most of Fleet’s specific research has focused on mathematical foundations and algorithms for visual motion analysis, tracking, human pose and motion estimation, latent variable models, physics-based models of human motion and scene interactions, data structures for indexing and search on massive image corpora, and models of biological motion perception and stereopsis.


Koenderink Prize, 2010

Best Paper Award, British Machine Vision Conference (BMVC), 2009

Best Paper Award, ACM Symposium on User Interface Software and Technology (UIST), 2003

Marr Prize Honorary Mention, 1999

Alfred P. Sloan Research Fellowship, 1996

Relevant Publications

Brubaker, M.A. et al. "Building proteins in a day: Efficient 3D molecular reconstruction." Paper presented at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 2015.

Norouzi, M. et al. "Fast exact search in Hamming space with multi-index hashing." TPAMI 36, no. 6 (2014): 1107–1119.

Norouzi, M. et al. "Hamming distance metric learning." Paper presented at NIPS conference, Lake Tahoe, 2012.

de La Gorce, M. et al. "Model-based 3D hand pose estimation from monocular video." TPAMI 33, no. 9 (2011): 1793–1805.

Taylor, G.W. et al. "Dynamical binary latent variable models for 3D human pose tracking." Paper presented at IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, 2010.