Mohamed Abdelfattah

I am a computer vision Ph.D. student at EPFL VITA lab, advised by Alexandre Alahi. In my Ph.D. journey, I enjoy tweaking transformer-based models for self-supervised action recognition. Before that, I was a deep learning visiting research student at Boston University where I worked with Sarah Adel Bargal. I also worked with Mohamed Elhoseiny at the KAUST Vision-Cair group as computer vision research intern. I received my B.Sc. in Computer Engineer from The American University in Cairo (highest honors, Dean's list) in 2022.

Email / CV / LinkedIn / Google Scholar / Github

I am actively looking for internship positions in computer vision and deep learning. Feel free to reach out to me!

Publications

S-JEPA: Joint Embedding Predictive Architecture for Self-Supervised Skeletal Action Recognition
Mohamed Abdelfattah, Alexandre Alahi
ECCV, 2024

Project page

Paper

@inproceedings{abdelfattah2024sjepa, 
            author={Abdelfattah, Mohamed and Alahi, Alexandre}, 
            booktitle={European Conference on Computer Vision (ECCV)}, 
            title={S-JEPA: Joint Embedding Predictive Architecture for Self-Supervised Skeletal Action Recognition}, 
            year={2024}, 
            organization={Springer}, 
            }

In one sentence: S-JEPA is an instatiation of the Joint Embedding Predictive Architecture (JEPA) for self-supervised skeletal action recognition.

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
Mohamed Abdelfattah, Mariam Hassan, Alexandre Alahi
CVPR, 2024

Project page

Paper

@inproceedings{abdelfattah2024maskclr,
    title={MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning},
    author={Abdelfattah, Mohamed and Hassan, Mariam and Alahi, Alexandre},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
    pages={18678--18687},
    year={2024}
  }

In one sentence: MaskCLR improves the robustness of transformer-based action recognition methods against noisy and incomplete skeletons.

Toward contactless human thermal monitoring: A framework for Machine Learning-based human thermo-physiology modeling augmented with computer vision
Mohamad Rida, Mohamed Abdelfattah, Alexandre Alahi, Dolaana Khovalyg
Building and Environment, 2023

Paper

@article{rida2023toward,
            title={Toward contactless human thermal monitoring: A framework for Machine Learning-based human thermo-physiology modeling augmented with computer vision},
            author={Rida, Mohamad and Abdelfattah, Mohamed and Alahi, Alexandre and Khovalyg, Dolaana},
            journal={Building and Environment},
            volume={245},
            pages={110850},
            year={2023},
            publisher={Elsevier}
          }

In one sentence: A machine-learning human thermo-physiology model (ML-HTPM) developed to predict thermal response.

Non-intrusive physiological parameters sensing for personalized human thermal comfort prediction
Mohamad Rida, Mohamed Abdelfattah, Alexandre Alahi, Dolaana Khovalyg
18th Healthy Buildings Europe Conference, 2023

Paper

@article{rida2023toward,
            title={Toward contactless human thermal monitoring: A framework for Machine Learning-based human thermo-physiology modeling augmented with computer vision},
            author={Rida, Mohamad and Abdelfattah, Mohamed and Alahi, Alexandre and Khovalyg, Dolaana},
            journal={Building and Environment},
            volume={245},
            pages={110850},
            year={2023},
            publisher={Elsevier}
          }

In one sentence: In this study, we applied multi-modal non-intrusive computer vision algorithms to extract personal features such as the clothing ensemble, activity level, posture, sex, age, and skin temperature as a human’s thermal comfort defining parameters.

ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture
Youssef Mohamed, Mohamed Abdelfattah, Shyma Alhuwaider, Feifan Li, Xiangliang Zhang, Kenneth Ward Church, Mohamed Elhoseiny
EMNLP, 2022

Project Page

Code

Dataset

arXiv

@InProceedings{mohamed2022artelingo,
            title={ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis
                   on Diversity over Language and Culture},
            author={Mohamed, Youssef and Abdelfattah, Mohamed and Alhuwaider, Shyma and Li, Feifan
                    and Zhang, Xiangliang and Church, Kenneth Ward and Elhoseiny, Mohamed},
            booktitle = {Proceedings of the 2022 Conference on Empirical Methods
                         in Natural Language Processing (EMNLP)}
            year={2022}}

In one sentence: This paper introduces ArtELingo, a new benchmark and dataset, designed to encourage work on diversity across languages and cultures.

ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes
Dina Bashkirova, Mohamed Abdelfattah, Ziliang Zhu, James Akl, Fadi Alladkani, Ping Hu, Vitaly Ablavsky, Berk Calli, Sarah Adel Bargal, Kate Saenko
CVPR, 2022

Project Page

Code

Dataset

arXiv

@inproceedings{bashkirova2022zerowaste,
            title={Zerowaste dataset: Towards deformable object segmentation in cluttered scenes},
            author={Bashkirova, Dina and Abdelfattah, Mohamed and Zhu, Ziliang and Akl, James and Alladkani, Fadi and Hu, Ping and Ablavsky, Vitaly and Calli, Berk and Bargal, Sarah Adel and Saenko, Kate},
            booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
            pages={21147--21157},
            year={2022}
          }

In one sentence: we take a step towards computer-aided waste detection and present the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste.

Teaching

[2023 & 2024] Head Teaching Assistant (TA) of Deep Learning for Autonomous Vehicles at EPFL.
[2022] Deep Learning Teaching Assistant at AUC
[2021 & 2022] Computer Architecture Teaching Assistant at AUC

Awards

[2022] Awarded the AUC PA Cup for the class of 2022 for top academic and extracurricular achievements.
[2022] High Academic Achievement (Top 10 % of Graduating Class) in SSE Honours Assembly | AUC.
[2021] Undergraduate Research Award, 4,000 USD | AUC.
[2019] Ranked among the top 10 ROV teams in the Middle East | MATE ROV Regional Competition.
[2018] Ranked 1st in the CSCE programming contest | AUC.
[2018] Named Highest Achiever and Reader of the Year | AUC.

Template adapted from Jon Barron's and Siwei Zhang's websites.