Computer Science
HomePeopleProfile

Profile

Dr Zeyu Fu

Lecturer in Computer Vision

Email:

Visit personal website »

Background

I am a Lecturer (Assistant Professor) in Computer Vision at Department of Computer Science, University of Exeter.

Before that I was a postdoctoral researcher at the Department of Engineering Science, University of Oxford, and was a member of Oxford Biomedical Image Analysis (BioMedIA) group, advised by Prof Alison Noble and Dr Michael Suttie. I worked on a NIH funded project which is conjunction with Collaborative Initiative on Fetal Alcohol Spectrum Disorders (CIFASD), to develop a fully automated, objective evaluation of facial features associated with FASD, utilizing 3D surface modelling, deep learning and shape analysis. I also worked on an ERC funded project named Perception Ultrasound by Learning Sonographic Experience (PULSE), which aims to develop multi-modal machine learning and computer vision systems that can model the sonograher’s expertise to reduce the need for highly trained ultrasound operators.

Before Oxford I was a research assistant at the School of Engineering, Newcastle University, advised by Prof Satnam Dlay. I worked on a MRC-CiC sponsored project to apply cutting edge non-contact ocular imaging, and machine/deep learning techniques to find a means of improving diagnosis of the most common medical complication of pregnancy, pre-eclamptic toxaemia. At the same institution, I obtained the Ph.D. degree in signal processing and machine learning and was a member of Signal Processing and AI research group, advised by Prof Jonathon Chambers and Dr Mohsen Naqvi. I worked on a DSTL & EPSRC funded project of ‘Signal Processing Solutions for the Networked Battlespace’ and was part of the LSSCN Contortium of University Defence Research Collaboration (UDRC), where I developed novel data association algorithms for multiple human tracking in video.

News

  • Feb 2023, A paper named "One-shot Medical Action Recognition with A Cross-Attention Mechanism and Dynamic Time Warping" in colloboration with Newcastle University is accepted for publication in IEEE ICASSP 2023.
  • Jan 2023, A paper named "Towards Multi-sweep Ultrasound Video Understanding: Application in Detection of Breech Position using Statistical Priors" from the CALOPUS project is accepted for publication in IEEE ISBI 2023.

Research Interests

  • Computer Vision:  detection and tracking, trajectory prediction, pose estimation and bahaviour analysis for human-centred visual computing, smart city and remote sensing; anomaly detection and localization for healthcare and environment monitoring
  • Machine Learning: representation learning, incremental learning, transfer learning, multi-modal learning
  • Medical Image Analysis: neuro-facial image analysis, ultrasound imaging, segmentation,  automated imaging based screening and diagnosis 

Research Experience

A more complete publication list can be found in Google Scholar.

  • Lecturer (Assistant Professor), University of Exeter, Jun 2022 – Present, Exeter, UK

  • Postdoctoral Researcher, University of Oxford, Jan 2020 – Jun 2022, Oxford, UK

  • Research Assistant, Newcastle University, May 2019 – Jan 2020,  Newcastle Upon Tyne, UK

  • Doctoral Researcher, Newcastle University, Sep 2015 – Sep 2019,  Newcastle Upon Tyne, UK

Education

  • PhD in Signal Processing and Machine Learning, 2015-2019, Newcastle University, UK

  • BEng (first-class) in Electrical and Electronics Engineering, 2012-2015, Newcastle University, UK

For Prospective Students/Researchers

Highly self-motivated UG/MSc/PhD students, research fellows, and visiting students/scholars with any of above interests are welcomed to join my team. Please drop me email with your CV and research interests if you are interested in working with me.

Funded/Self-funded PhD Opportuinies:

Postdoc Fellowship Funding Schemes: