Scholar
Mennatullah Siam
Google Scholar ID: AVPds3kAAAAJ
University of British Columbia
Few-shot Learning
Pixel-level Image and Video Understanding
Computer Vision
Deep Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,677
H-index
17
i10-index
20
Publications
20
Co-authors
4
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
5 items
PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
2025
Cited
0
Multiscale Video Transformers for Class Agnostic Segmentation in Autonomous Driving
2025
Cited
0
A Vision Centric Remote Sensing Benchmark
2025
Cited
0
The Power of One: A Single Example is All it Takes for Segmentation in VLMs
2025
Cited
0
PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?
2025
Cited
0
Resume (English only)
Academic Achievements
Area Chair for WACV 2026 (as of June 2025).
Multiple papers accepted at top venues including CVPR, NeurIPS, WACV, TPAMI, IJCV, and IEEE Geoscience and Remote Sensing Letters.
Delivered 'Segmentation with Transformers Tutorial' at Ro'ya Workshop, Deep Learning Indaba 2024.
Keynote speaker at Black in AI @ NeurIPS 2022; talks at UBC (2022), CVPR Doctoral Consortium (2021), and Samsung AI (2022).
Finalist award in KUKA Innovation Challenge 2018 as part of a team of four.
Outstanding Reviewer at ICCV 2023.
Recipient of VISTA Fellowship, AITF, Verna Tate Graduate Scholarship, and Alberta Graduate Excellence Scholarship.
Co-authors
4 total
Martin Jagersand
University of Alberta
Senthil Yogamani
Engineering Director, Data-centric AI for Autonomous Driving at Qualcomm Inc
Boris N. Oreshkin
Principal Scientist at Amazon
Hong Zhang
Chair Professor, SUSTech; Professor Emeritus, University of Alberta
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up