Scholar
Michael Wray
Google Scholar ID: gFQcKZMAAAAJ
Lecturer, University of Bristol
Citations & Impact
Citations
5,003
H-index
13
i10-index
13
Publications
20
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- October 2025: New paper 'A Video Is Not Worth a Thousand Words' on ArXiv.
- August 2025: Paper 'Evaluating Compositional Generalisation in VLMs and Diffusion Models' accepted at *SEM 2025.
- August 2025: Paper 'Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval' accepted at BMVC 2025.
- August 2025: Paper 'Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos' published in IJCV.
- July 2025: Invited lecture at BMVA SS 2025 on Egocentric Vision.
- June 2025: Paper 'Video, How Do Your Tokens Merge?' to be presented at eLVM workshop at CVPR 2025.
- June 2025: New survey paper 'Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review' on ArXiv.
- April 2025: New paper 'Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval' on ArXiv.
Research Experience
- After his PhD, he stayed in the same lab as a Post-Doc working on Vision and Language and the collection of the Ego4D Dataset. He has led the organization of the EPIC workshop series since 2021, is an organizer of the Ego4D workshop series, and is an ELLIS member.
Education
- Completed his PhD titled 'Verbs and Me: an Investigation into Verbs as Labels for Action Recognition in Video Understanding' in 2019 under the supervision of Professor Dima Damen.
Background
- Lecturer/Assistant Professor of Computer Vision at the School of Computer Science at the University of Bristol. Research interests lie in multi-modal video understanding, particularly for egocentric videos — focusing on how both vision and language can be tied together towards tasks such as cross-modal retrieval, grounding, and captioning.
Miscellany
- Teaches Applied Deep Learning, Computer Systems A, and Individual Projects.
