Shakeeb Murtaza

I am a Postdoctoral Fellow at LIVIA, ÉTS Montreal, where I lead research on explainability and responsible AI for transformer-based models in an industry collaboration with Genetec, working with Prof. Eric Granger. I also work with the International Laboratory on Learning Systems (ILLS), collaborating with researchers across its partner institutions.

I completed my Ph.D. in Engineering at LIVIA, ÉTS Montreal (2025), in partnership with ILLS, under the guidance of Prof. Eric Granger and Prof. Marco Pedersoli. My thesis, Deep Weakly Supervised Learning Networks for Object Localization, focused on training neural networks with minimal supervision for visual recognition tasks, and I was honoured on the ÉTS Honour Roll for academic excellence.

My research interests include weakly supervised learning, explainable and trustworthy AI, vision-language models, person re-identification, and biomedical image analysis (histology and microscopy). My work has been published in venues such as Pattern Recognition, NeurIPS, WACV, Image and Vision Computing, and Knowledge-Based Systems.

news

Sep 01, 2025	Honoured on the ÉTS Honour Roll (Summer 2025) for academic excellence.
Jul 02, 2025	Started as a Postdoctoral Fellow at LIVIA Lab, ÉTS Montreal, working on explainability and responsible AI for transformer-based models in collaboration with Genetec.
Jun 30, 2025	Completed my Ph.D. in Engineering at ÉTS Montreal. Thesis: Deep Weakly Supervised Learning Networks for Object Localization.
Nov 28, 2024	WACV 2025, A Realistic Protocol for Evaluation of Weakly Supervised Object Localization. [arXiv][Code]

latest posts

Dec 01, 2024	A Realistic Protocol for Evaluation of Weakly Supervised Object Localization

selected publications

TeD-Loc: Text Distillation for Weakly Supervised Object Localization

Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, and 1 more author

Under revision at Pattern Recognition, 2026

Bib

@article{murtaza2026tedloc,
  title = {TeD-Loc: Text Distillation for Weakly Supervised Object Localization},
  author = {Murtaza, Shakeeb and Belharbi, Soufiane and Pedersoli, Marco and Granger, Eric},
  journal = {Under revision at Pattern Recognition},
  year = {2026},
}

CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos

Soufiane Belharbi, Shakeeb Murtaza, Marco Pedersoli, and 3 more authors

Pattern Recognition, 2025

Bib PDF Code

@article{belharbi2025colo,
  title = {CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos},
  author = {Belharbi, Soufiane and Murtaza, Shakeeb and Pedersoli, Marco and Ayed, Ismail Ben and McCaffrey, Luke and Granger, Eric},
  journal = {Pattern Recognition},
  year = {2025},
  publisher = {Elsevier},
}

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization

Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, and 1 more author

In WACV 2025: IEEE/CVF Winter Conf. on Applications of Computer Vision, Arizona, USA, 2025

Bib PDF Code

@inproceedings{murtaza2025realistic,
  title = {A Realistic Protocol for Evaluation of Weakly Supervised Object Localization},
  author = {Murtaza, Shakeeb and Belharbi, Soufiane and Pedersoli, Marco and Granger, Eric},
  booktitle = {WACV 2025: IEEE/CVF Winter Conf. on Applications of Computer Vision, Arizona, USA},
  year = {2025},
}

SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution

Soufiane Belharbi, Mara KM Whitford, Phuong Hoang, and 3 more authors

In NeurIPS 2024: Neural Information Processing Systems, Vancouver, Canada, 2024

Bib

@inproceedings{belharbi2024srcaco2,
  title = {SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution},
  author = {Belharbi, Soufiane and Whitford, Mara KM and Hoang, Phuong and Murtaza, Shakeeb and McCaffrey, Luke and Granger, Eric},
  booktitle = {NeurIPS 2024: Neural Information Processing Systems, Vancouver, Canada},
  year = {2024},
}

Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization

Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli, and 2 more authors

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2023

Bib Code

@inproceedings{murtaza2023discriminative,
  title = {Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization},
  author = {Murtaza, Shakeeb and Belharbi, Soufiane and Pedersoli, Marco and Sarraf, Aydin and Granger, Eric},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops},
  pages = {155--165},
  year = {2023},
}