Ioanna Ntinou

I am a Postdoctoral Researcher at Queen Mary University of London, working on the RAIDO project. Within RAIDO, I contribute to the development of Distill-AI, a toolbox for energy-efficient AI models in computer vision and time-series. My research interests include computer vision, and more recently, vision–language models. I completed my PhD in Computer Science at QMUL (2020–2024), where my thesis explored efficient spatio-temporal modeling for action recognition in videos, supervised by Dr Georgios Tzimiropoulos. Before my PhD, I interned at the Samsung AI Centre, Cambridge, and I hold a BSc in Physics and an MSc in Electronics and Information Processing from the University of Patras, Greece.

Latest News

• [October 2025] Co-organiser of the Binary and Extreme Quantization for Computer Vision Workshop at ICCV 2025.
• [September 2025] Paper accepted at EMNLP 2025: Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions.
• [June 2025] Invited Panelist at IGF 2025 Open Forum: “Make your AI greener: A workshop on sustainable AI solutions”, organised by UNESCO. Watch the recording on YouTube.
• [October 2024] Oral presentation at ICIP 2024 in Abu Dhabi: MeMSVD: Long-Range Temporal Structure Capturing Using Incremental SVD.
• [July 2024] Submitted my PhD thesis: Efficient Spatio-Temporal Modeling for Action Recognition in Videos.
• [June 2024] Poster presentation at CVPR 2024 in Seattle: Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-Stage Action Localization.
• [May 2024] Started as Research Fellow on the RAIDO project.