Lecturer/Assistant Professor at the University of Bristol. Interested in (Egocentric) Video Understanding and Language.
Bristol
Joined November 2012
- Tweets146
- Following100
- Followers315
- Likes697
Michael Wray retweeted
Our #ECCV2026 @eccvconf paper
Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition
now on ArXiv w/ code&data&models
prajwalgatti.github.io/gen2b…
Can we fill imbalanced action recognition datasets with generative images to outperform long-tail SOTA?
Yes we can
🧵
Michael Wray retweeted
*NEW PAPER&MODEL*
HOI-DETR for detecting hands, object in-hand, &object-interacted-with (through a tool).
This is the foundation model you've been waiting for! One that works off-the-shelf, single-image, using strong detectors, generalises and is stable
ahmaddarkhalil.github.io/HOI…
🧵
Michael Wray retweeted
Last few days to submit your work to the #EgoVis workshop - proceedings track, which will be held at @CVPR 2026!
Check all info below 👇
📢 call for submissions!
Submit your work to the 3rd Joint EgoVis Workshop @ CVPR 2026 and publish in the CVPR Workshop Proceedings.
Deadline: Feb 27, 2026
More info on the website: egovis.github.io/cvpr26/
#CVPR2026 #EgocentricVision #ComputerVision
📡Only TWO days left to apply to the #MaVi Summer 2026 visit. Open to all PhD students and a chance to work with me or my colleagues as part of the Machine Learning and Computer Vision Group in Bristol. Partial funding available, see the link for details: uob-mavi.github.io/Summer@Ma…
Michael Wray retweeted
📢Applications are now open for PhD visiting students @bristolcs @BristolUni in 2026 - DL 29 Jan.
Would you like to work with any of the Faculty working in Machine Learning and Computer Vision #mavi as part of our summer of research @ Bristol program?
uob-mavi.github.io/Summer@Ma…
A Video is Not Worth a Thousand Words!
Our new Paper on ArXiv explores how VLMs deal with different modalities for Video Question Answering using Shapley Values.
Read the paper: arxiv.org/abs/2510.23253
Website: github.com/sjpollard/a-video…
For more information and results, go to Sam's website: sjpollard.github.io/a-video-…
We include code and test sets for reproducibility and the ability to evaluate your own method's attribution scores across the different modalities!
Work done by Sam Pollard as first author.
Finally, Sam will be giving a presentation of the work at @TheBMVA Symposium on "Multimodal Large Models: Bridging Vision, Language, and Beyond" next week!
Thanks also to IsambardAI for providing computational resources for the project.
Michael Wray retweeted
Fantastic two days with François visiting our MaVi group! Inspiring discussions, engaging talks, and great exchanges on the latest research. Big congrats to Dr. Kevin on a successful viva and to @mwray0 on a career milestone!
Many thanks 2 Francois Bremond (@inria_sophia) for a 2-day #Bristol visit @BristolUni #MaVi (Machine Learning &Computer Vision) research group hosted by @WayHomeLi. Great presentation incl. #CVPR2025 & #ICCV2025 papers from Francois's group, insights and future directions.
1/2
Michael Wray retweeted
Many thanks @PascalMettes @UvA_IvI for visiting us @BristolUni to examine (now Dr) Adriano Fragomeni (supervised by myself and @mwray0) and give a great talk on hyperbolic deep learning. Enjoyed your visit
Michael Wray retweeted
@SiyuTang3 on "Towards an egocentric multimodal foundation model" now at the #EGOVIS workshop at #CVPR2025!
📢 Our paper "Video, How Do Your Tokens Merge?" is now on ArXiv, to be presented at eLVM @CVPR 2025!
We explore Training-Free token merging for video understanding models across datasets with differing granularities.
arxiv.org/abs/2506.03885
sjpollard.github.io/video-ho…
By evaluating across Kinetics, Something-Something, and EPIC-Kitchens-100, we investigate how action granularity and first/third person viewpoints affect the token merging process and performance.
Code can be found on Github: github.com/sjpollard/video-h…
Work by Sam Pollard.
Want More Details? We both will be at CVPR 2025 next week to present the work and answer Qs!
Thanks @hubertshum for visiting us today at Bristol and giving a great talk as part of the #MaVi seminar series!
Michael Wray retweeted
BMVA Computer Vision School 2025 Aberdeen - Registration @TheBMVA @CVPRConf @eccvconf. We have a great lineup of world-leading scientists who will deliver 16 lectures over 5 days. Also poster competition, school dinner, social event etc.!
👇
Registration: cvss.bmva.org/attending/regi…