
Site: Old Road Campus
Research Building: Old Road Campus Research Building
Hala Lamdouar is a postdoctoral researcher at the IBME, University of Oxford, working with Professor Alison Noble. Her research combines multimodal learning with vision-language models for video understanding, with a focus on capturing clinical skill. She is developing systems that learn from ultrasound video how experienced sonographers scan, and use that to give trainees clear, actionable feedback. She also co-organises the MICCAI Workshop on Human-AI Collaboration in Healthcare (HAIC), which ran in 2025 and 2026.
Hala completed her DPhil (PhD) at the Visual Geometry Group (VGG), University of Oxford, advised by Professor Andrew Zisserman and Professor Weidi Xie. Her research addressed video understanding in challenging settings such as camouflaged and minimally visible moving objects. She was also a member of the Centre for Doctoral Training in Autonomous Intelligent Machines & Systems (AIMS).
Originally from Rabat, Morocco, Hala completed her engineering degree in signal and image processing at ENSEIRB-MATMECA in Bordeaux, France, followed by a Master’s degree in applied mathematics with a focus on machine learning and computer vision (MVA) at École Normale Supérieure Paris-Saclay. She then worked as a research engineer on perception solutions for autonomous driving at Valeo.
Personal webpage: hlamdouar.github.io
Hala Lamdouar, Wang A.F, Guo X, Men Q, Lander J, Papageorghiou A, Noble A. FOCUS: Towards Fetal Obstetric Corrective Ultrasound Guidance. MICCAI, 2026.
Wang A.F, Hala Lamdouar, Lander J, Papageorghiou A, Noble A. A3F: Anatomy-Aware Actionable Feedback for Fetal Ultrasound. HAIC Workshop, MICCAI, 2026.
Hala Lamdouar, Weidi Xie, and Andrew Zisserman. “The making and breaking of camouflage.” Proceedings of the IEEE/CVF international conference on computer vision. 2023.
Hala Lamdouar, Weidi Xie, and Andrew Zisserman. “Segmenting invisible moving objects.” In Proceedings of the British machine vision conference (2021).
Yang Charig, Hala Lamdouar, Erika Lu, Andrew Zisserman, and Weidi Xie. “Self-supervised video object segmentation by motion grouping.” In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7177-7188. 2021.
Hala Lamdouar, Charig Yang, Weidi Xie, and Andrew Zisserman. “Betrayed by motion: Camouflaged object discovery via motion segmentation.” In Proceedings of the Asian conference on computer vision. 2020.
Professor Alison Noble - Academic