Prof. Ioannis (Yiannis) Patras

Professor in Computer Vision and Human Sensing
Director of Graduate Studies Research
School of Electronic Engineering and Computer Science
Queen Mary University of London
Tel: +44 20 7882 7523

My research is in the area of Human Centered Machine Learning, using Machine Learning, Computer Vision and Signal Processing methodologies to learn from multiple sources concepts that enable Intelligent Systems to understand, communicate and collaborate with humans. Currently it evolves around three themes:

  • Learning to recognise behaviour, emotions and cognitive states of people by analysing their images, video and neuro-physiological signals
  • Learning across modalities, and in particular at the intersections of language and vision, using large, pretrained language and audio-visual models
  • Learning from generative models and learning to control generation for privacy, interpretability and control purposes.

I have more than 300 publications in the most selective Journals and conferences in the field of Computer Vision, an h-index of 43, and more than 11000 citations. I am (or have been) associate editor in the journals of Pattern Recognition; Computer Vision and Image Understanding; Image and Vision Computing, and area chair or in the programme committee of all the major conferences in the field. My research has been funded by the EPSRC, EU FP7, HORIZON 2020, InnovateUK, and direct bilateral collaborations with research institutes and the industry.

I lead a team of around 15 PhD students and Postdoctorate researchers.


Mar 7, 2024 2 papers accepted at CVPR 2024: 1) LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition, Zhonglin Sun, Chen Feng, Ioannis Patras and Georgios Tzimiropoulos; 2) Self-Supervised Facial Representation Learning with Facial Region Awareness, Zheng Gao, Ioannis Patras
Nov 10, 2023 “A Simple Baseline for Knowledge-Based Visual Question Answering”, Alexandros Xenos, Themos Stafylakis, Ioannis Patras, and Georgios Tzimiropoulos, accepted at EMNLP 2023
Nov 8, 2023 Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features, Zheng Gao, Chen Feng, Ioannis Patras, accepted at WACV 2024.
Nov 8, 2023 Improving Fairness using Vision-Language Driven Image Augmentation, Moreno D’Incà, Christos Tzelepis, Ioannis Patras, Nicu Sebe, accepted at WACV 2024.
Sep 22, 2023 Parts of Speech-Grounded Subspaces in Vision-Language Models James Oldfield and Christos Tzelepis and Yannis Panagakis and Mihalis A. Nicolaou and Ioannis Patras accepted at NeurIPS 2023
Aug 21, 2023 “Prompting Visual-Language Models for Dynamic Facial Expression Recognition”, Zengqun Zhao, Ioannis Patras, accepted at BMVC 2023
Jul 14, 2023 HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces, Stella Bounareli, Christos Tzelepis, Vasileios Argyriou, Ioannis Patras, Georgios Tzimiropoulos, accepted at ICCV 2023
Mar 17, 2023 3 papers accepted at CVPR 2023 (one top-10%)
Feb 28, 2023 Invited talk at International AI Doctoral Academy (AIDA) on Generative Models: Controllable Generation and Learning (abstract and video)
Feb 1, 2023 PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs, James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras accepted at ICLR 2023
Jan 19, 2023 Call-for-Papers: ACM TOMM SI on Realistic Synthetic Data: Generation, Learning, Evaluation