Contact

Sameh Khamis

I am a PhD student in computer science at the University of Maryland working with Larry Davis. I am also a member of the Computer Vision Laboratory (CVL) and the Institute for Advanced Computer Studies (UMIACS). I received a MSc in computer science in 2010 from the University of Western Ontario under the supervision of Yuri Boykov, where I worked on semantic image segmentation. I spent the summer of 2012 at Siemens Corporate Research in Princeton, New Jersey with Vinay Shet, and I spent the spring of 2013 at IST Austria with Christoph Lampert.

I am interested in aspects of discrete optimization, graphical models, and statistical learning applied to high-level vision problems in general and activity recognition in particular.

I am co-organizing the 1st Workshop on Understanding Human Activities: Context and Interactions, which is to be held in conjunction with ICCV 2013, along with Mohamed Amer, Wongun Choi, and Tian Lan. New

Publications

Conference

  • Sameh Khamis, Vlad I. Morariu, Larry S. Davis.
    Combining Per-Frame and Per-Track Cues for Multi-Person Action Recognition.
    In European Conference on Computer Vision (ECCV), 2012.
    [PDF] [Bibtex] [Poster] [Errata]
    @inproceedings{khamis-eccv2012,
        author = {Sameh Khamis and Vlad I. Morariu and Larry S. Davis},
        title  = {Combining Per-Frame and Per-Track Cues for Multi-Person Action Recognition},
        booktitle = {European Conference on Computer Vision},
        year = {2012}
    }
    In the published version, equation (3) should use the distance directly,
    and not its pseudo-probability:
    v_{ab}(i, j) = \lambda_d\ d(i, j) - \lambda_c \log(p_{ab})
    
  • Sameh Khamis, Vlad I. Morariu, Larry S. Davis.
    A Flow Model for Joint Action Recognition and Identity Maintenance.
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
    [PDF] [Bibtex] [Poster] [Spotlight] [Errata]
    @inproceedings{khamis-cvpr2012,
        author = {Sameh Khamis and Vlad I. Morariu and Larry S. Davis},
        title  = {A Flow Model for Joint Action Recognition and Identity Maintenance},
        booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
        year = {2012}
    }
    In the published version, equation (3) should use the distance directly,
    and not its pseudo-probability:
    v_{ab}(i, j) = \lambda_d\ d(i, j) - \lambda_c \log(p_{ab})
    

Workshop

Code

All my code is generally provided for non-commercial research purposes only. Please read the bundled README file for the licensing details. Available code for class projects is unmaintained and unsupported.

  • RegionPushRelabel 1.09: a parallel out-of-core max-flow algorithm for massive graphs with a regular structure. The algorithm extends the work on grid graphs in Delong and Boykov, CVPR 2008. Visit the computer vision lab at Western for more details.

Talks

  • 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

TA @ UMD

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

TA @ UWO

  • [CS1037a] Computer Science Fundamentals II (C++) - Yuri Boykov (Fall '09)
  • [CS1027a] Computer Science Fundamentals II (Java) - Aija Downing / Steven Beauchemin (Spring '08)
  • [CS1032a] Information Systems and Design - Diane Goldstein (Fall '08)

Coursework

Courses @ IST Austria

  • Machine Learning (Advanced) - Christoph Lampert (Spring '13)

PhD Courses @ UMD

  • [CMSC754] Computational Geometry - David Mount (Spring '12)
  • [ENEE633/CMSC828C] Statistical Pattern Recognition - Rama Chellappa (Fall '11)
  • [CMSC733] Computer Processing of Pictorial Information (Waived) - Yiannis Aloimonos (Fall '11)
  • [CMSC727] Neural Modeling - James Reggia (Spring '11)
  • [CMSC734] Information Visualization - Ben Schneiderman (Spring '11)
  • [CMSC764] Numerical Optimization - Dianne O'Leary (Fall '10)
  • [CMSC828B] Advances in Biometrics - David Jacobs (Fall '10)
  • [CMSC726] Machine Learning (Waived) - Lise Getoor (Fall '10)
  • [ENEE731/CMSC828P] Image Understanding (Waived) - Rama Chellappa (Fall '10)

MSc Courses @ UWO

  • [CS9837b] Vision for Graphics - Yuri Boykov (Spring '09)
  • [CS9840a] Learning and Computer Vision - Olga Veksler (Fall '08)
  • [CS9687a] Image Processing, Medical Imaging and Computer Graphics - Yuri Boykov (Fall '08)
HTML5 Powered with CSS3 / Styling, and Semantics Creative Commons Attribution-ShareAlike 3.0 Unported License
(license excludes the papers and the code)