Fatemeh N. Nokabadi

Machine Learning Scientist • Computer Vision • Vision-Language Models

Email LinkedIn GitHub Scholar Publications
Fatemeh N. Nokabadi

About

I am a Machine Learning Scientist specializing in computer vision and modern AI systems. My work focuses on building reliable, high-impact models that perform in real-world conditions, not just benchmarks. I currently work as a Data Scientist at Employment and Social Development Canada (ESDC).

I hold a Ph.D. in Electrical Engineering from Université Laval and Mila, supervised by Prof. Christian Gagné and Prof. Jean-François Lalonde. My doctoral research focused on adversarial robustness of learning-based object trackers; designing attack frameworks that expose critical vulnerabilities in state-of-the-art transformer trackers.

Prior to my PhD, I conducted research on single-object tracking via deep reinforcement learning at LVSN, Université Laval, and built computer vision systems for real-world industry applications.

Projects

Intelligent Document Understanding System
  • Built an end-to-end system for extracting structured information from complex documents using VLMs.
  • Handled diverse data types and real-world variability at scale.
  • Delivered reliable performance in production workflows.
Robustness Evaluation of Vision Models
  • Developed frameworks to evaluate failure modes of modern vision models.
  • Exposed critical weaknesses under adversarial conditions.
  • Improved understanding of model reliability in safety-critical scenarios.
Reproducibility Study Webpage Paper Code Presentation

TrackPGD Webpage Paper Code Presentation

ABBG Paper Code Presentation

Transactions on Machine Learning Research 2024 · Proceedings of the 22nd Conference on Robots and Vision 2025 · Journal-to-conference track & AdvML Frontiers at NeurIPS2024

Representation Learning for Video Understanding
  • Framed single-object tracking as a reinforcement-learning episodic task with a Soft-Actor-Critic agent learning a motion policy from video frames.
  • Proposed the β-Multivariational Autoencoder (βMVAE) and a U-Net variant (βMVUNet) to learn an entangled Multivariate Gaussian prior (mean vector and covariance matrix) over the tracker's correlated motion parameters directly from frame patches.
  • Jointly trained the decoder to predict the target's binary segmentation mask, so a single network learns the motion distribution and the per-frame object mask used by the tracker.
Paper Code Presentation

WiML at ICML 2024

Visual Authentication System
  • Built models for fine-grained visual verification tasks.
  • Leveraged subtle visual cues for authenticity detection.
  • Achieved high accuracy in real-world scenarios.
Graph-Based Salient Object Detection
  • Developed graph-based saliency detection algorithms using local, global, and mixed feature representations.
  • Proposed multiple methods including random graph and global contrast graph approaches for salient object detection in images.
Paper 1 Paper 2 Paper 3

Multimedia Tools and Applications 2018 · Signal, Image and Video Processing 2018 · SPIS 2015

Real-Time Multi-Object Tracking for Moving Cameras
  • Researched and implemented real-time multi-object tracking algorithms for cluttered video frames, incorporating salient object detection to prioritize targets.
  • Designed and deployed a MATLAB and C++ tracking system using OpenCV for moving-camera video streams, improving tracking speed by 30%.

Academic Service