Fatemeh N. Nokabadi

I am a data scientist with a focus on document intelligence and computer vision. I work on OCR and document understanding systems at Employment and Social Development Canada (ESDC). I have expertise in adversarial robustness research and biometric verification for high-value objects. I provide vision-based AI systems that operate dependably in real-world environments by collaborating on model design, evaluation, and production integration.

I completed a Ph.D. in Electrical Engineering, specializing in computer vision, at Université Laval and Mila. My research focused on object tracking and the robustness of learning-based trackers. I was supervised by Professor Christian Gagné and Professor Jean-François Lalonde. I published my work in Transactions on Machine Learning Research (TMLR) and the Conference on Robots and Vision (CRV). I also presented my research at NeurIPS and ICML, sharing my contributions with the academic community.

Prior to this, I researched single-object tracking using deep reinforcement learning algorithms at Laboratoire de vision et systèmes numériques (LVSN), Université Laval. Also, I have gained nine months of industry experience through internships, reinforcing my skills and learning from professional teammates.

For any inquiries, feel free to reach out to me via mail!

Mail Twitter Scholar Github LinkedIn

Publications

Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
Fatemeh Nourilenjan Nokabadi, Jean-Francois Lalonde, Christian Gagné
Transactions on Machine Learning Research (TMLR), 2024
Accepted in ML Reproducibility Challenge , 2023
Presented in Conference on Neural Information Processing Systems (NeurIPS) 2024
Project Page / Code / Poster / Slides /

@article{nokabadi2024reproducibility,
	    title={Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers},
	    author={Fatemeh Nourilenjan Nokabadi and Jean-Francois Lalonde and Christian Gagne},
	    journal={Transactions on Machine Learning Research},
	    issn={2835-8856},
	    year={2024},
	    url={https://openreview.net/forum?id=FEEKR0Vl9s},
	    note={Reproducibility Certification}
	}

TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers
Fatemeh Nourilenjan Nokabadi, Yann Batiste Pequignot, Jean-Francois Lalonde, Christian Gagné
Presented in NeurIPS 2024 in 3rd Workshop on New Frontiers in Adversarial Machine Learning
Published at Proceedings of the 22nd Conference on Robots and Vision, 2025
Project Page / Code / Poster / Slides /

@inproceedings{nokabadi2024trackpgd,
	title={Track{PGD}: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers},
	author={Fatemeh Nourilenjan Nokabadi and Yann Batiste Pequignot and Jean-Francois Lalonde and Christian Gagn{\'e}},
	booktitle={The Third Workshop on New Frontiers in Adversarial Machine Learning},
	year={2024},
	url={https://openreview.net/forum?id=niCzJh1cbP}
	}

Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers
Fatemeh Nourilenjan Nokabadi, Jean-Francois Lalonde, Christian Gagné
NeurIPS 2024 in 3rd Workshop on New Frontiers in Adversarial Machine Learning
Project Page / Code / Poster / Slides /

@inproceedings{nokabadi2024adversarial,
	title={Adversarial Bounding Boxes Generation ({ABBG}) Attack against Visual Object Trackers},
	author={Fatemeh Nourilenjan Nokabadi and Jean-Francois Lalonde and Christian Gagn{\'e}},
	booktitle={The Third Workshop on New Frontiers in Adversarial Machine Learning},
	year={2024},
	url={https://openreview.net/forum?id=PRQFtvakYN}
	}

β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames
Fatemeh Nourilenjan Nokabadi, Setareh Rezaee Oshternian
ICML 2024 Workshop WiML
Poster / Slides / Code /

@article{nourilenjan_nokabadi_-multivariational_2024, 
		author = {Fatemeh Nourilenjan Nokabadi, Setareh Rezaee Oshternian}, 
		title = {β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames}, 
		booktitle = {ICML 2024 Workshop WiML}, 
		year = {2024}, 
		}

Salient object detection method using random graph
Fatemeh Nouri, Kamran Kazemi, Habibollah Danyali
Multimedia Tools and Applications, 2018
Project Page /

@InProceedings{nouri_salient_2018, 
	author = {Fatemeh Nouri and Kamran Kazemi and Habibollah Danyali}, 
	title = {Salient object detection method using random graph}, 
	booktitle = {Multimedia Tools and Applications}, 
	year = {2018}, 
}

Salient object detection using local, global and high contrast graphs
Fatemeh Nouri, Kamran Kazemi, Habibollah Danyali
Signal, Image and Video Processing, 2018
Project Page /

@InProceedings{nouri_salient_2018-1, 
	author = {Fatemeh Nouri and Kamran Kazemi and Habibollah Danyali}, 
	title = {Salient object detection using local, global and high contrast graphs}, 
	booktitle = {Signal, Image and Video Processing}, 
	year = {2018}, 
}

Salient object detection via global contrast graph
Fatemeh Nouri, Kamran Kazemi, Habibollah Danyali
Signal Processing and Intelligent Systems Conference (SPIS), 2015
Project Page / Poster /

@InProceedings{nouri_salient_2015, 
	author = {Fatemeh Nouri and Kamran Kazemi and Habibollah Danyali}, 
	title = {Salient object detection via global contrast graph}, 
	booktitle = {Signal Processing and Intelligent Systems Conference (SPIS)}, 
	year = {2015}, 
}

Website template adopted from Michael Niemeyer.