Mojtaba Marvasti, PhD
Computer Vision Scientist
Canada · 1 connectionNot on Unlinked · Imported profile. Is this you? Claim it
Is this about you? Request removal
About
• 10+ years of research experience across a spectrum of advanced topics: - Multi-modal perception systems (e.g., Object detection & tracking, Object segmentation, SAR detection & segmentation), Multimodal LLMs, Vision Foundation Models, Semi-supervised learning (SSL), Neural architecture search (NAS), Diffusion models, Generative adversarial networks (GANs), Explainable AI (XAI), Domain adaptation, Information fusion, Context modeling, Monocular 3D reconstruction, and more. • Significant Publications: - Over 25 research papers at leading ML, CV, and RS venues, such as WACV, ECCV, BMVC, ACCV, ICPR, and GRSL. - First-authored comprehensive review papers in prestigious journals: + IEEE Transactions on Intelligent Transportation Systems (Impact Factor: 7.9, cited over 400 times), + ACM Computing Surveys (Impact Factor: 23.8, ranked 1/143 in Computer Science Theory & Methods). • Educational Background: - Ph.D. in Computer Vision and Deep Learning, focusing on bridging theoretical concepts with practical applications. • Technical Proficiency & Experience: - Proficient in PyTorch, TensorFlow-Keras for deep learning development; OpenCV for computer vision applications. - Advanced proficien
Experience
May 2024 to Dec 2025
Dec 2021 to Feb 2024
Jun 2019 to Dec 2019
Education
Ph.D. Computer Vision
2015 to 2021
M.Sc. Digital Video Processing
2011 to 2014