Youssef Mohamed

About Me

Hello there! I’m a passionate machine learning researcher, currently working on my Ph.D. at King Abdullah University of Science and Technology (KAUST). I’ve been lucky enough to study at some great places - I earned my Master’s degree in Computer Science from the University of Tartu and my Bachelor’s degree in Communication and Information Engineering from Zewail City of Science and Technology. I’m really into Multimodal Deep Learning, Affective Image Captioning, and Multicultural Modeling, and I’ve had the chance to share my work at some good conferences and journals. Beyond the research, I like to swim and hoop.

Research Interests

Multicultural Modeling: Developing AI models that respect and understand cultural diversity, with an emphasis on language and culture.
Affective Computing: Emotion recognition and explanation in multimodal settings.
Multimodal Deep Learning: Integration of multiple data types, exploring how to combine different data sources effectively.

Publications

EMNLP

No Culture Left Behind: ArtELingo-28, a benchmark of Wikiart with Captions in 28 Languages

Youssef Mohamed, Runjia Li, Ibrahim Said Ahmad, Kilichbek Haydarov, Philip Torr, Kenneth Ward Church, Mohamed Elhoseiny

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.

PDF Code Project Page BibTex

ICLR

Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation

Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip Torr, Adel Bibi, Mohamed Elhoseiny

International Conference on Learning Representations (ICLR), 2024.

PDF Code Project Page BibTex

EMNLP

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

International Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.

PDF Code Project Page BibTex

CVPR

It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection

Youssef Mohamed, Faizan Farooq Khan, Kilichbek Haydarov, Mohamed Elhoseiny

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

PDF Code Project Page BibTex

Journal

Interpretability in healthcare: A comparative study of local machine learning interpretability techniques

Radwa ElShawi, Youssef Mohamed, Mouaz Al‐Mallah, Sherif Sakr

International Journal on Computational Intelligence, Volume37, Issue4, 2021.

PDF Code Project Page BibTex

TMLR

Did I do that? Blame as a means to identify controlled effects in reinforcement learning

Oriol Corcoll, Youssef Mohamed, Raul Vicente

Transactions of Machine Learning Research (TMLR).

PDF Project Page

Frontiers

Modelling the Impact of Robotics on Infectious Spread Among Healthcare Workers

Raul Vicente, Youssef Mohamed, Victor M Eguíluz, Emal Zemmar, Patrick Bayer, Joseph S Neimat, Juha Hernesniemi, Bradley J Nelson, Ajmal Zemmar

Frontiers in Robotics and AI, Volume 8 - 2021

PDF Project Page

EDBT

Towards Automated Concept-based Decision Tree Explanations for CNNs

Radwa ElShawi, Youssef Mohamed, Sherif Sakr

International Conference on Extending Database Technology (EDBT), 2021.

PDF Code Project Page

ADBIS

ILIME: Local and Global Interpretable Model-Agnostic Explainer of Black-Box Decision

Radwa ElShawi, Youssef Mohamed, Mouaz Al‐Mallah, Sherif Sakr

European Conference on Advances in Databases and Information Systems (ADBIS), 2019.

PDF Project Page

News

[Oct. 2024] Our paper “Towards AI-Assistive Psychotherapy with Emotion-Guided Generative Interventions” has been submitted at NAACL 25.
[Sept. 2024] Our paper “No Culture Left Behind:ArtELingo-28, a benchmark of Wikiart with Captions in 28 Languages” has been Accepted at EMNLP 24.
[Jan. 2024] Our paper “Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation” has been Accepted at ICLR 24.
[Nov. 2023] Our paper “Towards No Culture Left Behind: Large Scale Multilingual Affective Vision and Language Understanding” has been submitted to CVPR 24.
[Oct. 2023] I completed my Multimodal AI Internship at ELM, Riyadh.
[Oct. 2023] We organized the 1st Workshop On Emotionally And Culturally Intelligent AI (WECIA) at ICCV 23.
[Sept. 2023] Our paper “Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation” is under review at ICLR 24.
[Jun. 2023] Complete my KAUST M.Sc. Thesis “Multicultural Emotional reasoning in Vision Language Models”
[Dec. 2022] Our paper “ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture” was presented at EMNLP 22.
[Aug. 2022] Successfully completed my M.Sc. Thesis “Did I do that? Blame as a means to identify controlled effects in reinforcement learning”, which was published in TMLR journal.
[Jun. 2022] Our paper “It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection” was presented at CVPR 22.
[Oct. 2021] Started my research at Vision-CAIR group, focusing on Multimodal Deep Learning, Affective Image Captioning, and Multicultural Modeling.
[Mar. 2021] Our paper “Automatic Concept-based Decision Tree Explanation” was published in EDBT 2021.
[Sept. 2019] Our paper “ILIME: Local and Global Interpretable Model-Agnostic Explainer of Black-Box Decision” was published in ADBIS 2019.
[Jun. 2019] Our paper “Interpretability in Healthcare: A Comparative Study of Local Machine Learning Interpretability Techniques” was published in CBMS 2019. An extended version was published in the Journal of Computational Intelligence.