Fatemeh N. Nokabadi

Machine Learning Scientist | Computer Vision, VLMs & Video Understanding

Fatemeh N. Nokabadi

I am a Machine Learning Scientist with over a decade of experience developing computer vision and machine learning solutions, spanning original algorithm development, deep learning research, and applied AI systems. I hold a Ph.D. in Electrical Engineering from Université Laval, where I conducted doctoral research in collaboration with Mila – Quebec AI Institute, under the supervision of Prof. Christian Gagné and Prof. Jean-François Lalonde.

My expertise spans video understanding, object detection and tracking, adversarial robustness, and multimodal vision-language models. I have developed novel learning algorithms, trained and evaluated deep learning architectures, and explored generative approaches to improve the robustness and reliability of visual systems.

Currently, I work at Employment and Social Development Canada, focusing on multimodal AI and document intelligence. My work involves fine-tuning vision-language and recognition models, developing training and evaluation pipelines, and building synthetic-data generation workflows for privacy-sensitive applications.

I enjoy working at the intersection of research and engineering: translating challenging problems into effective learning systems through rigorous experimentation, model optimization, and practical implementation.

Expertise

Video Understanding & Detection Multimodal GenAI & VLMs Adversarial Robustness Privacy-Preserving Synthetic Data Efficient Real-Time Vision PyTorch & Hugging Face

Multimodal Document Intelligence

ESDCVision-Language ModelsDocument AIOCRSynthetic Data
  • Fine-tuned vision-language models, including Qwen2.5-VL, for understanding complex, privacy-sensitive documents, from dataset design through training and evaluation.
  • Built training, validation, and evaluation pipelines for handwriting and text recognition with Hugging Face Transformers, integrating Qwen-based models and TrOCR into an existing multi-model OCR system.
  • Designed field-level prompting strategies to reduce hallucinations, and custom training objectives to improve recognition of challenging text, including French accented characters.
  • Created an automatically annotated synthetic-data pipeline that reduces reliance on manually labeled sensitive documents.

Adversarial Robustness of Visual Object Trackers

TMLR 2024NeurIPS 2024CRV 2025Adversarial MLVision Transformers
  • Evaluated the adversarial robustness of transformer-based visual object trackers across multiple architectures and benchmarks, including GOT-10k, VOT2022, and UAV123.
  • Developed TrackPGD, a white-box adversarial attack built on object binary masks that targets mask-based trackers earlier attacks could not.
  • Proposed ABBG, an adversarial bounding-box generation attack that remains effective across transformer trackers where prior methods fail.
  • Conducted a reproducibility study of adversarial attacks across perturbation budgets and tracker architectures, awarded the TMLR Reproducibility Certification.
  • Investigated diffusion-based adversarial purification for video, characterizing the temporal-consistency limits of frame-wise approaches.

Visual Authentication and Fine-Grained Recognition

ORIGYN FoundationFine-Grained RecognitionComputer VisionAWS
  • Developed computer vision pipelines for luxury-product authentication, combining signal-processing features with deep-learning-based texture and fine-detail representations.
  • Explored fine-grained visual cues for distinguishing authentic products from counterfeits.
  • Automated model-integration on AWS to streamline deployment processes.

Real-Time Multi-Object Tracking

Computer VisionObject TrackingC++MATLABOpenCV
  • Designed and implemented real-time multi-object tracking algorithms for cluttered video scenes and moving-camera environments.
  • Developed a MATLAB/C++ tracking framework using OpenCV and visual saliency techniques to prioritize targets and improve computational efficiency.

Graph-Based Salient Object Detection

MTAP 2018SIVP 2018SPIS 2015Graph-Based VisionSaliency Detection
  • Developed graph-based salient object detection methods using local, global, and high-contrast visual representations.
  • Proposed random-graph and global-contrast approaches, demonstrating improved performance over existing unsupervised methods on standard saliency benchmarks, including MSRA10K, SED2, and ECSSD.
BCNC 2015 certificate

2025

Adversarial robustness of learning-based single object trackers
Fatemeh Nourilenjan Nokabadi

Ph.D. Thesis · Université Laval / Mila · 2025

Thesis
TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers
Fatemeh Nourilenjan Nokabadi, Yann Batiste Pequignot, Jean-François Lalonde, Christian Gagné

22nd Conference on Robots and Vision (CRV) 2025

Paper Code Project Page

2024

Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
Fatemeh Nourilenjan Nokabadi, Jean-François Lalonde, Christian Gagné

Transactions on Machine Learning Research (TMLR) · Reproducibility Certification

Paper Code Project Page NeurIPS Presentation Poster Slides
TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers
Fatemeh Nourilenjan Nokabadi, Yann Batiste Pequignot, Jean-François Lalonde, Christian Gagné

Third Workshop on New Frontiers in Adversarial Machine Learning (AdvML-Frontiers) @ NeurIPS 2024

Paper Code Project Page Presentation Poster Slides
Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers
Fatemeh Nourilenjan Nokabadi, Jean-François Lalonde, Christian Gagné

Third Workshop on New Frontiers in Adversarial Machine Learning (AdvML-Frontiers) @ NeurIPS 2024

Paper Code Presentation Poster Slides
β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames
Fatemeh Nourilenjan Nokabadi, Setareh Rezaee Oshternian

Women in Machine Learning Workshop (WiML) @ ICML 2024

Code Presentation Poster

2023

β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames
Fatemeh Nourilenjan Nokabadi, Robert Bergevin

SSRN Scholarly Paper · Preprint

Paper DOI Code PDF Poster

2018

Salient object detection method using random graph
Fatemeh Nouri, Kamran Kazemi, Habibollah Danyali

Multimedia Tools and Applications, vol. 77(19), pp. 24681–24699

Paper
Salient object detection using local, global and high contrast graphs
Fatemeh Nouri, Kamran Kazemi, Habibollah Danyali

Signal, Image and Video Processing, vol. 12(4), pp. 659–667

Paper

2015

Salient object detection via global contrast graph
Fatemeh Nouri, Kamran Kazemi, Habibollah Danyali

Signal Processing and Intelligent Systems Conference (SPIS), pp. 159–163

Paper Poster
  • Peer Reviewer – BMVC 2026, CVPR 2025, Transactions on Machine Learning Research (TMLR), Springer Nature
  • Teaching & Mentoring – Taught and mentored students in C/C++ Programming, Image Processing, Stochastic Processes and Digital Communications at Shiraz University of Technology

Awards & Honors

  • 2024TMLR Reproducibility CertificationML Reproducibility Challenge 2023; presented at NeurIPS 2024
  • 2022REPARTI–FRQNT Scholarship
  • 2021Adobe Research FellowshipShortlisted among the top 30 candidates worldwide and interviewed
  • 2021CIFAR Deep Learning + Reinforcement Learning Summer SchoolSelected participant; organized by CIFAR with Mila, Vector Institute and Amii
  • 2021Otis-Lalonde Scholarship in Computer VisionUniversité Laval
  • 2016M.Sc. Thesis ScholarshipCognitive Science & Technologies Council

Talks

  • 2026Data Day 2026, ESDCPresented the team’s vision and document-intelligence work
  • 2026AI Infrastructure for Agentic SystemsSeminar for the ESDC data science team, synthesizing insights from the Agentic AI Summit (UC Berkeley)SlidesPlaylist
  • 2024NeurIPS 2024Reproducibility Study (journal-to-conference track), TrackPGD and ABBG (AdvML-Frontiers workshop)
  • 20154th Basic and Clinical Neuroscience Congress (BCNC)Oral presentation, “Graph-based salient object detection using color and edge features”