Saeed Ghorbani

Ph.D. Student

Department of Electrical Engineering and Computer Science

York University

Toronto, Canada

I am a third-year Ph.D. student in Electrical Engineering and Computer Science at York University, Toronto, advised by Dr. Niko Troje. I am also a VISTA and CVR trainee. My research interests are machine learning, computer vision, computer graphics, and computer animation. My current research focus is on leveraging novel deep probabilistic models for realistic human motion modelling.

Highlights

Apr 8, 2021 Our paper “Estimating Pose from Pressure Data for Smart Beds withDeep Image-based Pose Estimators” was accepted at Journal of Applied Intelligence, Springer
Jan 27, 2021 Our paper “In-bed Pressure-based Pose Estimation using Image Space Representation Learning” was accepted at ICASSP2021
Oct 10, 2020 Our paper “Gait Recognition using Multi-Scale Partial Representation Transformation with Capsules” was accepted at ICPR2020
Oct 1, 2020 Our new paper on Motion Modelling is now published at Computer Graphics Forum. Watch the short and long presentations.
Mar 6, 2020 MoVi: We just published a BIG new data set of human motion data. 9h mocap + 17h calibrated video + 7h of IMU + MoSh reconstructed body shape. Check the website

Selected Publications

  1. CGF
    Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
    Computer Graphics Forum (Symposium on Computer Aanimation) 2020
  2. arXiv
    MoVi: A Large Multipurpose Motion and Video Dataset
    Ghorbani, Saeed, Mahdaviani, Kimia, Thaler, Anne, Kording, Konrad, Cook, Douglas James, Blohm, Gunnar, and Troje, Nikolaus F.
    arXiv:2003.01888 2020
  3. CGI Best Paper Award
    Auto-labelling of markers in optical motion capture by permutation learning
    Ghorbani, Saeed, Etemad, Ali, and Troje, Nikolaus F
    In Computer Graphics International 2019