Sameh Khamis

Photo

I am a Researcher in the Interactive 3D Technologies (I3D) group at Microsoft Research Redmond.

I am interested in building large-scale, real-time solutions for real-world computer vision and machine learning problems, leveraging all aspects of system design, statistical learning, probabilistic models, and discrete and continuous optimization.

I am currently working on Holoportation [Video], a new type of 3D capture technology that allows high-quality 3D models of people to be reconstructed, compressed and transmitted anywhere in the world in real time. The press coverage includes ZDNet, Gizmodo, VentureBeat, Mashable, Engadget, Gamasutra, Wired, and many more. This technology was running live on stage at TED 2016. New

I received a PhD in computer science from the University of Maryland, where I worked with Larry Davis at the Institute for Advanced Computer Studies (UMIACS). In my thesis, I focused on modeling the contextual and spatiotemporal structure in activity recognition. During my PhD, I was a research intern at SRI International, Microsoft Research Cambridge, IST Austria, and Siemens Corporate Research. Before that, I received a MSc in computer science from the University of Western Ontario, where I was advised by Yuri Boykov.

Here:

EmailCV

Elsewhere:

DBLPScholarGithubLinkedInGoogle+Facebook

Publications

Conference

Workshop

Talks

  • Learning an Efficient Model of Hand Shape Variation from Depth Images.
    UMD Computer Vision Student Seminars, College Park, MD. April, 2015.
  • What Recognizing Activities and Tracking Hands Have in Common.
    Microsoft Research, Redmond, WA. February, 2015.
  • Learning a Model of Hand Shape Variation from Depth Images.
    Microsoft Research, Cambridge, UK. September, 2014.
  • Combining Per-Frame and Per-Track Cues for Multi-Person Action Recognition.
    KU Leuven VISICS Group Seminar, Heverlee, Belgium. March, 2013.
  • Combining Per-Frame and Per-Track Cues for Multi-Person Action Recognition.
    IST Austria CV&ML Seminar, Klosterneuburg, Austria. March, 2013.
  • Combining Per-Frame and Per-Track Cues for Multi-Person Action Recognition.
    UMD Computer Vision Student Seminars, College Park, MD. September, 2012.
  • Person Re-Identification in Surveillance Scenarios via Attributes.
    Siemens Corporate Research, Princeton, NJ. August, 2012.
  • Energy Minimization with Graph Cuts.
    UMD Computer Vision Student Seminars, College Park, MD. February, 2012.
  • A Flow Model for Joint Action Recognition and Identity Maintenance.
    Siemens Corporate Research, Princeton, NJ. November, 2011.

Teaching

University of Maryland

  • [CMSC498F] Machine Learning - Lilyana Mihalkova (Fall '10)

University of Western Ontario

  • [CS1037a] Computer Science Fundamentals II (C++) - Yuri Boykov (Fall '09)
  • [CS1027a] Computer Science Fundamentals II (Java) - Aija Downing and Steven Beauchemin (Spring '08)
  • [CS1032a] Information Systems and Design - Diane Goldstein (Fall '08)
HTML5 Powered with CSS3 / Styling, and Semantics Creative Commons Attribution-ShareAlike 3.0 Unported License
(license excludes the papers and the code)