|
Soroush Mehraban I'm a third-year PhD student at University of Toronto, advised by Dr. Babak Taati , and Faculty Affiliate Researcher at Vector institute . My research focuses on analyzing videos for human motion analysis including 3D human pose estimation, 3D human mesh recovery, action recognition, and gait assessment. Email / CV / Scholar / Twitter / Linkedin / YouTube / Github |
|
ResearchI'm interested in computer vision, Self-supervised learning, generative models, and their application to a range of problems. Currently I'm focusing on 3D human pose/mesh estimation from monocular videos. Some of my works are mentioned below. |
|
STARS: Self-supervised 3D Action Recognition with Contrastive Tuning
Soroush Mehraban, Mohammad Javad Rajabi, Babak Taati arxiv project page / arXiv STARS enhances the Mask Autoencoder (MAE) approach in self-supervised learning by applying contrastive tuning. We also show that MAE approaches fail in few-shot settings and achieve improved performance by using the proposed method. |
|
Benchmarking Skeleton-based Motion Encoder Models for Clinical
Applications: Estimating Parkinson's Disease Severity in Walking Sequences
Vida Adeli, Soroush Mehraban, Irene Ballester, Yasamin Zarghami, Andrea Sabo, Andrea Iaboni, Babak Taati FG, 2024 Code / arXiv Evaluating recent motion encoders for the task of parkinsonism severity estimation (UPDRS III gait) |
|
MotionAGFormer: Enhancing 3D Pose Estimation with a Transformer-GCNFormer
Network
Soroush Mehraban Vida Adeli, Babak Taati WACV, 2024 Code / video / arXiv Estimating 3D locations of 17 main joints from a monocular video. |
|
|
