For a complete list of publications, please refer to Google Scholar.

Recent Publications

  1. Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
    Y Fan, G Wen, D Li, S Qiu, MD Levine
    arXiv preprint arXiv:1805.11223, 2018
  2. Contextual Bag-of-Words for Robust Visual Tracking
    F Zeng, Y Ji, MD Levine
    IEEE Transactions on Image Processing 27 (3), 1433-1447, 2018
  3. Early event detection based on dynamic images of surveillance videos
    Y Fan, G Wen, D Li, S Qiu, MD Levine
    Journal of Visual Communication and Image Representation 51, 70-75, 2018
  4. System and method for tracking moving objects in videos
    MJ Roshtkhari, MD Levine
    US Patent 9,824,281, 2017
  5. A deep neural network for real-time detection of falling humans in naturally occurring scenes
    Y Fan, MD Levine, G Wen, S Qiu
    Neurocomputing 260, 43-58, 2017
  6. Adaptive Metric Learning and Probe-Specific Reranking for Person Reidentification
    Y Xie, H Yu, X Gong, MD Levine
    IEEE Signal Processing Letters 24 (6), 853-857, 2017
  7. Multi-path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained" Hard Faces"
    Y Liu, MD Levine
    Computer and Robot Vision (CRV), 2017 14th Conference on, 183-190, 2017
  8. System and Method for Visual Event Description and Event Analysis
    MJ ROSHTKHARI, M Levine
    US Patent App. 15/388,666, 2017
  9. Person re-identification by graph-based metric fusion
    Y Xie, MD Levine, H Yu
    Electronics Letters 52 (17), 1447-1449, 2016
  10. Does “lie to me” lie to you? An evaluation of facial clues to high-stakes deception
    L Su, M Levine
    Computer Vision and Image Understanding 147, 52-68, 2016
  11. Invasive ductal breast carcinoma detector that is robust to image magnification in whole digital slides
    M Balazsi, P Blanco, P Zoroquiain, MD Levine, MN Burnier
    Journal of Medical Imaging 3 (2), 027501, 2016
  12. Robust multi-focus image fusion using multi-task sparse representation and spatial context
    Q Zhang, MD Levine
    IEEE Transactions on Image Processing 25 (5), 2045-2058, 2016
  13. Syntactic pattern recognition: paradigm issues and open problems
    M Flasiński
    Handbook of Pattern Recognition and Computer Vision, 3-25, 2016
  14. TRACKING WITHOUT APPEARANCE DESCRIPTORS
    MJ Roshtkhari, MD Levine
    Handbook of Pattern Recognition and Computer Vision, 239-254, 2016
  15. Multisensor video fusion based on higher order singular value decomposition
    Q Zhang, Y Wang, MD Levine, X Yuan, L Wang
    Information Fusion 24, 54-71, 2015
  16. High-stakes deception detection based on facial expressions
    L Su, MD Levine
    2014 22nd International Conference on Pattern Recognition (ICPR), 2519-2524, 2014
  17. Fully automated recognition of spontaneous facial expressions in videos using random forest classifiers
    MKA El Meguid, MD Levine
    IEEE Transactions on Affective Computing 5 (2), 141-154, 2014
  18. Multiple object tracking using local motion patterns
    MJ Roshtkhari, MD Levine
    Journal of Computer Vision 107 (2), 203-217, 2014
  19. Human activity recognition in videos using a single example
    MJ Roshtkhari, MD Levine
    Image and Vision Computing 31 (11), 864-876, 2013
  20. An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions
    MJ Roshtkhari, MD Levine
    Computer vision and image understanding 117 (10), 1436-1452, 2013
  21. Automated Real-Time Detection of Potentially Suspicious Behavior in Public Transport Areas.
    M Elhamod, MD Levine
    IEEE Trans. Intelligent Transportation Systems 14 (2), 688-699, 2013
  22. Visual saliency based on scale-space analysis in the frequency domain
    J Li, MD Levine, X An, X Xu, H He
    IEEE transactions on pattern analysis and machine intelligence 35 (4), 996-1010, 2013
  23. Online dominant and anomalous behavior detection in videos
    M Javan Roshtkhari, MD Levine
    Proceedings of the IEEE conference on computer vision and pattern …, 2013
  24. Computer Vision and Robotics Laboratory McGill University
    P Sicard, MD Levine
    Machine Intelligence and Knowledge Engineering for Robotic Applications 33, 355, 2012
  25. A multi-scale hierarchical codebook method for human action recognition in videos using a single example
    MJ Roshtkhari, MD Levine
    Computer and Robot Vision (CRV), 2012 Ninth Conference on, 182-189, 2012
  26. Real-time semantics-based detection of suspicious activities in public spaces
    M Elhamod, MD Levine
    Computer and Robot Vision (CRV), 2012 Ninth Conference on, 268-275, 2012
  27. Saliency detection based on frequency and spatial domain analysis
    MD Levine, X An, H He
    92 2011
  28. Secure access camera and method for camera control
    S Khan, S Khan, MD Levine
    US Patent 7,800,687, 2010
  29. Is local colour normalization good enough for local appearance-based classification?
    DH Parks, MD Levine
    Machine Vision and Applications 21 (5), 789-796, 2010
  30. Image and video region saliency based on space and motion
    J Li, M Levine, X An, Z Sun, H He
    Brain, Body and Machine, 95-109, 2010
  31. A METHOD FOR SYNTHESIS OF A 3D FACE USING A SINGLE 2D IMAGE
    MD Levine, Y Yu
    Handbook Of Pattern Recognition And Computer Vision, 595-623, 2010
  32. Multi-view object detection based on spatial consistency in a low dimensional space
    G Gill, M Levine
    Joint Pattern Recognition Symposium, 211-220, 2009
  33. Incorporating Shape Features in an Appearance-Based Object Detection System
    G Gill, M Levine
    International Conference on Computer Analysis of Images and Patterns, 269-276, 2009
  34. State-of-the-art of 3D facial reconstruction methods for face recognition based on a single 2D training image per person
    MD Levine, YC Yu
    Pattern Recognition Letters 30 (10), 908-913