Suhail Mohammed
About Me
I am a PhD student at University of British Columbia advised by Prof. Leonid Sigal. Before that I did my Master in Computer Science at UBC and Bachelors in Electrical Engineering at Indian Institute of Technology Guwahati. My research interest mostly intersect with structured representation learning and neural rendering.
Publications
-
Associating Objects and their Effects in Unconstrained Monocular Video
M. Suhail, E. Lu, Z. Li, N. Snavely, L. Sigal and F. Cole
Accepted to CVPR 2023
Paper / Code -
Generalizable Patch-Based Neural Rendering
M. Suhail, C. Esteves, L. Sigal and A. Makadia
[Oral] European Conference on Computer Vision(ECCV) 2022
Project Page / Code / Video -
Light Field Neural Rendering
M. Suhail, C. Esteves, L. Sigal and A. Makadia
[Oral] Conference on Computer Vision and Pattern Recognition(CVPR), 2022
(Top 33 finalist for best paper award)
Paper / Code / Project Page / Video -
Energy-Based Learning for Scene Graph Generation
M. Suhail, A. Mittal, B. Siddiquie, C. Broaddus, J. Eledath, G. Medioni and L. Sigal
Conference on Computer Vision and Pattern Recognition(CVPR), 2021.
(Selected as one of the best 32 papers)
Paper / Code / Video -
Segmentation-grounded Scene Graph Generation
S. Khandelwal*, M. Suhail*, Leonid Sigal
[Oral] IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Paper / Code / Video -
Mixture Kernel Graph Attention Networks for Situation Recognition
M. Suhail and L. Sigal
IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
Paper / Blog
Work Experience
Google Research | Cambrdige, MA
- (05/2022 - 03/2023) Research Intern / Student Researcher
- Host: Erika Lu and Forrester Cole
- Working on a novel neural rendering method.
Google Research | New York, NY
- (05/2021 - 03/2022) Research Intern / Student Researcher
- Host: Carlos Esteves and Ameesh Makadia
- Worked on light field based neural rendering models.
- Works accepted to CVPR 2022 and ECCV 2022.
Amazon | Seattle, WA
- (05/2020 - 08/2020) Applied Scientist Intern
- Host: Behjat Siddiquie
- Developed a novel energy based learning framerwork for scene graph generation. Work published at CVPR 2021.