Mohammed E. Fathy

PhD Student

Department of Computer Science
University of Maryland College Park

mefathy *a*t* {umiacs or cs}.umd.edu

About

I am a PhD candidate at the Department of Computer Science, the University of Maryland, College Park (UMD). I work with Prof. Rama Chellappa in machine learning and computer vision. I am interested in deep learning, sparse representations and (non-)convex optimization. I work(ed) on video-based recognition, feature learning, correspondence estimation, 3D vision model estimation (e.g. fundamental/essential matrices), monocular visual odometry, and (deep) audio analysis. I am also affiliated with the Computer Vision Laboratory (CVL) of the Center for Automation Research (CfAR) at the University of Maryland Institute for Advanced Computer Studies (UMIACS).

News

Datasets

Coming soon...

Publications

  1. Mohammed E. Fathy, Azadeh Alavi, Rama Chellappa.Discriminative Log-Euclidean Feature Learning for Sparse Representation-Based Recognition of Faces from Videos. In Proc. Int'l Joint Conf. on Artificial Intelligence (IJCAI), 2016. [PDF] [MATLAB Code]
    [Oral/Poster - Acceptance Rate: 24.02% (511/2294)]

  2. Mohammed E. Fathy, Vishal Patel, Rama Chellappa. Face-Based Active Authentication on Mobile Devices. In Proc. Int'l Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2015. [PDF]
    [Oral - Acceptance Rate: 16.9%]

  3. Heng Zhang, Vishal Patel, Mohammed E. Fathy, Rama Chellappa. Touch Gesture-Based Active User Authentication Using Dictionaries. In Proc. IEEE Winter Conf. on Applications of Computer Vision (WACV), 2015. [PDF]
    [Acceptance Rate: 36.7%]

  4. Mohammed E. Fathy, Michael C. Rotkowtiz. Essential Matrix Estimation Using Adaptive Penalty Formulations. In Proc. 25th British Machine Vision Conf. (BMVC), 2014. (This was an extension of my Convex Optimization course project) [PDF][Extended Abstract]
    [Acceptance Rate: 30.2%]

  5. Mohammed E. Fathy, Vishal M. Patel, Tom Yeh, Yangmuzi Zhang, Rama Chellappa, Larry Davis. Screen-Based Active User Authentication. Pattern Recognition Letters, 42, 2014, Elsevier. doi: 10.1016/j.patrec.2014.02.007 [Preprint PDF]
    [JCR 2014 Impact Factor: 1.551]

  6. Osama Khalil, Mohammed E. Fathy, Dina Khalil El Kholy, Motaz El Saban, Pushmeet Kohli, Jamie Shotton and Yasmine Badr. Synthetic Training in Object Detection. In Proc. 20 Int'l Conf. on Image Processing (ICIP), 2013. [PDF]

  7. Vishal M. Patel, Tom Yeh, Mohammed. E. Fathy, Yangmuzi Zhang, Yan Chen, Rama Chellappa, and Larry Davis. Screen Fingerprints: a Novel Modality for Active Authentication. IT Professional, 15 (4), 2013, IEEE. doi: 10.1109/MITP.2013.56 [PDF]

  8. Mohammed E. Fathy, Ashraf S. Hussein, Mohammed F. Tolba. Fundamental Matrix Estimation: A Study of Error Criteria. Pattern Recognition Letters, 32 (2), 2011, Elsevier. doi: 10.1016/j.patrec.2010.09.019 [Preprint PDF]
    [JCR 2012 Impact Factor: 1.266]

  9. Mohammed E. Fathy, Ashraf S. Hussein, Mohammed F. Tolba. Simple, Fast and Accurate Estimation of the Fundamental Matrix Using the Extended Eight-Point Schemes. In Proc. 21st British Machine Vision Conf. (BMVC), 2010. doi: 10.5244/C.24.7 [PDF][Extended Abstract]
    [Acceptance Rate: 33.6%]

  10. Mohammed E. Fathy, Ashraf S. Hussein, Safwat A. Hamad, Amr H. Abdelaziz, Saher H. Abdelaziz, H. El-Bery. Parallel Remote Rendering of Large 3D Point-Based Models on Mobile Clients. In Proc. 2nd IEEE Int'l Conf. on Computational Intelligence, Modelling and Simulation (CIMSIM), 2010. doi: 10.1109/CIMSiM.2010.67 [Preprint PDF]

Patents

  1. Mohammed F. Tolba, Ashraf S. Hussein, Mohammed E. Fathy. Method and System for Estimating Singular Fundamental Matrices. WIPO Patent Application No. PCT/EG2011/000012, Canadian Patent No. CA2854902. Filed May 2011 (pending)