I am an assistant professor in Ontario Tech University leading the Image and Video Understanding (IVU) lab. Previously I was a Postdoctoral researcher working with Professor Richard Wildes in York University. I am currently focused on video understanding, fewshot video understanding, fewshot video segmentation and spatiotemporal models interpretability. I was also a vector affiliate. I obtained my PhD in 2021 under Professor Martin Jagersand supervision working in vision for robotics. My thesis was focused on learning video object segmentation from limited labelled data, where I was working on the intersection between video object segmentation and fewshot object segmentation. I did internships in Huawei HiSilicon research (2019), Nvidia Deep Learning for Autonomous Vehicles Research (2018), and Valeo Vision Systems (2017). I was a member in a team of 4 in the KUKA Innovation Challenge 2018, where our team was one of the top 5 finalists. Previously I finished my Masters degree in Informatics from Nile University, Egypt, 2013. I also received an Honours BSc in Computer Science from Ainshams University, Egypt, 2010.
Research Interests: Computer Vision, Deep Learning, Fewshot Learning, Video Object Segmentation, Video Understanding, Spatiotemporal Models Interpretability.

News

July 2023: I started as an assistant professor in Ontario Tech University
June 2023: I am a WACV 2024 Area Chair.
February 2023: Our paper on Multiscale Video Transformers for Video Object Segmentation is accepted in CVPR 2023.
December 2022: Co-organizing 2nd Workshop on L3D-IVU: Learning with Limited Labelled Data for Image and Video Understanding in CVPR 2023.
November 2022: I was a Keynote speaker in Black in AI workshop co-located with Neurips 2022 on Learning Scene and Video Understanding with Limited Labelled Data.
September 2022: I am guest editor in the special issue on "Signal Processing and Machine Learning for Autonomous Driving" in Remote Sensing Journal.
April 2022: Gave a talk on few-shot learning and its extension beyond single images to videos in Samsung AI.
March 2022: Our paper on the interpretability of Spatiotemporal models has been accepted in CVPR2022.
December 2021: Co-organizing Workshop on L3D-IVU: Learning with Limited Labelled Data for Image and Video Understanding in CVPR 2022.
December 2021: Our short paper in Machine Learning for Autonomous Driving Workshop in Neurips 2021 was accepted.
July 2021: Officially Started my Postdoc in York University under supervision from Prof. Richard Wildes and Kostas Derpanis,
May 2021: I officially finished my PhD and graduated from University of Alberta convocation in Fall 2021, Thesis.

Publications

MED-VT: Multiscale Encoder-Decoder Video Transformer with Application to Object Segmentation

Rezaul Karim, He Zhao, Richard P. Wildes, Mennatullah Siam

CVPR 2023.

Paper Project Webpage Code

Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation

Mennatullah Siam, Rezaul Karim, He Zhao, Richard P. Wildes

Arxiv.

Paper Code

A Deeper Dive into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information

Matthew Kowal, Mennatullah Siam, Md Amirul Islam, Neil D. B. Bruce, Richard P. Wildes, Konstantinos G. Derpanis

CVPR 2022.

Paper Video Demo Project Webpage Code Interpretability Code AVOS

Temporal Transductive Inference for Fewshot Video Object Segmentation

Mennatullah Siam, Konstantinos G. Derpanis, Richard P. Wildes

ML4AD Workshop, Neurips 2021.

Full Paper Paper Video Demo

Weakly Supervised Few-shot Object Segmentation using Co-attention with Visual and Semantic Embeddings

Mennatullah Siam*, Naren Doraiswamy*, Boris N. Oreshkin*, Hengshuai Yao, Martin Jagersand (equally contributing)

IJCAI 2020.

Paper

AMP: Adaptive Masked Proxies for Few-Shot Segmentation

Mennatullah Siam, Boris N. Oreshkin, Martin Jagersand

ICCV 2019.

Paper Code

Video Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting

Mennatullah Siam, Chen Jiang, Steve Lu, Laura Petrich, Mosta Gamal, Mohamed Elhoseiny, Martin Jagersand

ICRA 2019.

Paper Dataset

Online Object and Task Learning via Human Roboti Interaction

Masood Dehghan*, Zichen Zhang*, Mennatullah Siam*, Jun Jin, Laura Petrich, Martin Jagersand (equally contributing)

ICRA 2019.

Paper Video Demo

Real-time Segmentation with Appearance, Motion and Geometry

Mennatullah Siam, Sara Eikerdawy, Mostafa Gamal, Moemen Abdel-Razek, Martin Jagersand, Hong Zhang

IROS 2018.