iiinova — where your digital self keeps evolving

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 09/10/2026

🤗 amazing junior faculty joined us last year uob-mavi.github.io 🏆 Our research is internationally renowned - we have at least 1 Best Paper Finalist at CVPR'22, 25&26. 🏢 New fantastic spaces at SRB building (pic) Apply now: tinyurl.com/briscs2026

000

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 09/10/2026

It is the *best* time to start your own research group in AI @compscibristol.bsky.social Why? 🌟 Bristol hosts the largest supercomputer in the UK - Isambard AI, 4th greenest in the world. 🧑‍🎓 New undergrad degree CS w AI &multiple masters 6⃣ Nov DL to apply for position, Link in 🧵

153

Reposted by Dima Damen @ECCV 2026

Phillip Isola @phillipisola.bsky.social · 28/09/2026

Students sometimes ask me if it still makes sense, in this accelerating age, to pursue a PhD in AI. Perhaps counterintuitively, I think it's a great time to do so. I wrote up some thoughts on this here: web.mit.edu/phillipi/www...

web.mit.edu

On the Value of Doing a PhD in the Age of AI

18116

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 12/09/2026

It was a great week @eccv.bsky.social #ECCV2026 #Malmo for current members @compscibristol.bsky.social #MaVi group and catching up with alumni! Here's a group pic missing a few, @prajwalgatti.bsky.social @zhifan-zhu.bsky.social @ekazakos.bsky.social Siddhant, Ahmad, Jacob, Alex, Toby, Kevin.

0122

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 09/09/2026

This afternoon @eccv.bsky.social #ECCV2026 you can catch me at: 13:40 Wearables AI 2:30 Effective World Models for Embodied AI 3:40 CONTEXTUS 4:30 Force-Grounded Articulated Manipulation incl my particular 🌶️ take: Don't ask what's a world model, please ask what is an action!

071

Reposted by Dima Damen @ECCV 2026

Christian Wolf @chriswolfvision.bsky.social · 08/09/2026

Dima Damen @dimadamen.bsky.social on ego-centric vision and tracking objects and hands in the 3D Humans workshop at ECCV.

081

Reposted by Dima Damen @ECCV 2026

Christian Wolf @chriswolfvision.bsky.social · 25/08/2026

New papers on recurrent transformers: arxiv.org/pdf/2606.21562 (ours): train full Tr, distill -> rec Tr arxiv.org/pdf/2608.02870 train full and rec jointly, min. coherence arxiv.org/pdf/2606.06479 train rec Tr with predictive obj. arxiv.org/pdf/2608.08888 train full Tr, add rec latents, multi-pass

2434

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 11/08/2026

Impressive!! and amazing views! Well-done...

010

Reposted by Dima Damen @ECCV 2026

Diane Larlus @dlarlus.bsky.social · 04/08/2026

Our #ECCV2026 Whareformer paper tackles long-term object tracking in Egocentric videos 🎓https://arxiv.org/abs/2607.08537 see Dima's thread below 🔽 joint work w Jacob Chalk, @saptarshisinha.bsky.social @dimadamen.bsky.social from Bristol & @skamalas.bsky.social from @naverlabseurope.bsky.social

1194

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 24/07/2026

Thanks @elliot-eu.bsky.social for the short interview on why egocentric vision is the right place to start your exploration into understanding human actions youtu.be/DfbxlgWpKSQ

youtu.be

Why first-person AI matters, by Dima Damen

YouTube video by ELLIOT Project

171

Reposted by Dima Damen @ECCV 2026

Yannis Kalantidis @skamalas.bsky.social · 10/07/2026

Excited to share our #ECCV2026 paper introducing Whareformer, which learns to track what is where in long egocentric videos. Proud to collaborate with Jacob Chalk and @sinhasaptarshi.bsky.social and the inspiring, humbling forces that are @dlarlus.bsky.social and @dimadamen.bsky.social

0103

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 10/07/2026

Whareformer @eccv.bsky.social #ECCV2026 fantastic collab bw @compscibristol.bsky.social @naverlabseurope.bsky.social by Jacob Chalk w/ @sinhasaptarshi.bsky.social @skamalas.bsky.social & @dlarlus.bsky.social Paper, Code &models public: jacobchalk.github.io/Whareformer/ arxiv.org/abs/2607.08537 N/N

031

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 10/07/2026

Whareformer is only trained on 50 videos from EPIC-KITCHENS and evaluated thoroughly on 100+ long videos from EPIC-KITCHENS, HD-EPIC and IT3Ego consistently outperforming alternatives. Watch quali: youtu.be/tfJ1yhIE8cE 5/N

youtu.be

Whareformer: Learning to Track What is Where in Long Egocentric Videos - Qualitative Examples

YouTube video by Jacob Chalk

120

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 10/07/2026

We utilise the online DenStream algorithm to maintain persistent (recurrent viewpoints) and transient (new viewpoints) appearance micro-clusters within each track efficiently. Unlike applications in autonomous or multi-person tracking, tracks can be revisited after 30+mins 4/N

110

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 10/07/2026

We train: * embedding network g(.) to combine appearance &location diff * NT token to learn to initialise new tracks * transformer encoder to contrast assignments Memory is updated online based on assignments. No tracks are removed - in ego you reuse objects after LONG gaps 3/N

110

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 10/07/2026

Whareformer (What&Where former) tackles the OSNOM task - Out of Sight objects remain explicitly in memory so you know where objects are at all times. In natural ego videos, tracking moving objects offers a significant challenge, compared to tracking static parts of the scene. 2/N

130

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 10/07/2026

NEW Whareformer: Learning to Track What is Where in Long Egocentric Videos @eccvconf #ECCV2026 paper The first online learning approach to track dynamic objects in ego video reasoning on appearance &3D location w track memory & explicit new track token. jacobchalk.github.io/Whareformer/ 🧵

3127

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/06/2026

Explore the dataset now at: sid2697.github.io/epic-contact... As we always do: Dataset, Code & models are public already along w ArXiv and full details to reproduce in code and supplementary EPIC-Cotact Dataset: huggingface.co/datasets/Sid... HOPformer Code: github.com/Sid2697/HOPf... 6/6

010

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/06/2026

Work led by Siddhant Bansal w @zhifan-zhu.bsky.social Shashank Tripathi, Jiahe Zhao @michael-j-black.bsky.social and myself - a 16-months intense collaboration @compscibristol.bsky.social and MPI IS. [don't let anyone convince you good research can be done in a few months!] 5/6

110

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/06/2026

+ We propose HOPformer (achieves new SOTA on Arctic) & eval on EPIC-Contact, feed-forward model that utilises hand prior to cross-attend to object pose backbone & decoder that estimates both poses of hands & object (relative to canonical). + generalisable to new instances of known classes 4/6

110

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/06/2026

We release EPIC-Contact dataset - manually annotated in-contact hand vertices AND bijective annotations of corresponding object vertices. We contribute a full pipeline from hand painting to efficiently annotate objects, then fit posed hand&object meshes. Manually checked 3/6

120

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/06/2026

TL;DR we predict bi-manual hand & object pose in a single forward pass from in-the-wild ego frames. Achieved through manually-collected high-quality annotations of 2.3K video clips (62.3K frames) of functional interactions during stable grasps with objects from 9 classes 2/6

130

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/06/2026

*NEW* Our #ECCV2026 @eccv.bsky.social paper Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation Now on ArXiv w Dataset, Code&model sid2697.github.io/epic-contact/ arxiv.org/abs/2606.30598 Two contributions: 1. EPIC-Contact Dataset 2. HOPformer Method &Checkpoint 🧵 1/6

2125

Reposted by Dima Damen @ECCV 2026

Christian Wolf @chriswolfvision.bsky.social · 24/06/2026

#ECCV2026 paper: A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world 966 *REAL* nav episodes (!!) performed by S. Janny with Dino-v3, Dino-v2, DUNE, VC1, AM-RADIO encoders show that patch features can be bottlenecked to 1 value ➡️ affordances emerge. 1/8

1166

Reposted by Dima Damen @ECCV 2026

Christian Wolf @chriswolfvision.bsky.social · 23/06/2026

For your Embodied AI task you want a recurrent model with constant complexity per step, but you don't want to lose the power of transformers (which store the full obs history and attend to it)? Do not despair, we have your back. We distill transformers into recurrent transformers 1/8

23410

Reposted by Dima Damen @ECCV 2026

ELLIS @ellis.eu · 17/06/2026

Get to know @hazeldoughty.bsky.social, Asst Prof at @unileiden.bsky.social 🇳🇱 and ELLIS Member. She researches computer vision, with a focus on fine-grained video understanding under limited supervision. Her goal is to enable a deeper understanding of video content and motion. #WomenInELLIS

0142

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 15/06/2026

Congratulations @zhifan-zhu.bsky.social who passed his viva today @compscibristol.bsky.social, examined by Siyu Tang (ETH Zurich) &Andrew Calway on: Understanding 3D Dynamics of Hands, Objects and Bodies in Long Egocentric Videos zhifanzhu.github.io He is on the job market for positions in industry

090

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 09/06/2026

What can you do with a 4-hour delay at Denver after @cvprconference.bsky.social? Create a collage of this week... 🧵 to tag all those who helped shape these captured moments... it was lovely to see you all and hope to catch up again soon...

150

Reposted by Dima Damen @ECCV 2026

ELLIOT Project @elliot-eu.bsky.social · 05/06/2026

We are excited to welcome @dimadamen.bsky.social as a speaker at the Workshop on Multimodal Foundation Models!🌐🤖 Professor of Computer Vision at the University of Bristol and Senior Research Scientist at Google DeepMind, she will present: “Modelling in an Ego-Sensed World”. 🔗 Link in the comments.

393

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 28/05/2026

Many congratulations Prof Jitendra Malik elected as a Fellow of the Royal Society @royalsociety.org in 2026 - well and truly deserved! Jitendra's contributions extend to inspiring, advising and mentoring many in our community, and just being a very nice person! royalsociety.org/news/2026/05...

010

Reposted by Dima Damen @ECCV 2026

Christian Wolf @chriswolfvision.bsky.social · 24/04/2026

In my team we have two open positions on AI for robotics and in particular on manipulation, for junior and senior researchers. With us, connect fundamental research questions with real operational problems and contribute to emerging AI-driven robotics services. careers.werecruit.io/en/naver-lab...

23711

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 27/04/2026

From the V-Jepa2 presentation: Action anticipation in EPIC-KITCHENS is "a very challenging task and still there’s head room for improvement on this task". V-Jepa2 establishes a new SOTA but still <65% on both verb and noun acc. Mido Assran at the @iclr-conf.bsky.social workshop on World Models

0131

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 27/04/2026

Attending @iclr-conf.bsky.social #ICLR2026? Join us for the 2nd workshop on world models - full day 202 A/B @meng-yue-yang.bsky.social opening the workshop right now

271

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 26/04/2026

Only problem with workshops I don’t get to finish my 8k steps in the day… poster walking gets me the steps 🤣

110

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 26/04/2026

* AI (unlike humans) is trained with carefully curated data * Complementary learning systems theory gives a direction into how new knowledge is formed in the brain * Understanding the brain is one direction to make AI more efficient 3/3

010

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 26/04/2026

* People don’t just store a representation of the sentence of what was communicated to them. We also build our own representations. * The ability to organise behaviors in pursuit for goals including mastering and inventing new skills is the hallmark of what we consider Genius 2/3

100

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 26/04/2026

I so much enjoyed Jay McClelland's talk @iclr-conf.bsky.social #ICLR2026 workshop on New Frontiers in Associative Memory. Some quotes: * AI is staged until deployed and then they are frozen at inference... AI systems are not continual learners 1/3

100

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 26/04/2026

For those attending @iclr-conf.bsky.social maybe we need a reminder that a panel moderator should be "like a great referee: if they did their job perfectly, you barely noticed they were there, but the game moved beautifully because of them."

161

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 26/04/2026

Workshops are always more interesting than the main conference! @iclr-conf.bsky.social What's next in Next Token Prediction workshop @jcniebles.bsky.social starting the action,

250

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 30/03/2026

Exciting 2 weeks ahead @csail.mit.edu thanks to B Freeman for hosting.. Sad I'll be missing Antonio - but what would be a better inspirational place to stay than his office!! Already caught up with @vincentsitzmann.bsky.social @sarameghanbeery.bsky.social ... will be a fun time!

1141

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 24/03/2026

At @brics-uob.bsky.social summit today @bristoluni.bsky.social. Happy faces of users all around. I &my team are proud users thanks to national DSIT grants. I took virtual pictures with the original Isambard and the new Isambard! Thanks @simonmcs.bsky.social, Sadaf and the team for the invitation.

0102

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 17/03/2026

Congrats Ahmad Darkhalil who passed his PhD today @compscibristol.bsky.social, examined by @csprofkgd.bsky.social & @chriswolfvision.bsky.social. Thesis includes his excellent work on: VISOR, EPIC Fields, HD-EPIC, EgoPoints, &Hand-Object Detection. Check works at: ahmaddarkhalil.github.io

172

Reposted by Dima Damen @ECCV 2026

Kosta Derpanis @csprofkgd.bsky.social · 09/03/2026

Next week I’ll be in Bristol as a PhD viva examiner and to give a talk, hosted by @dimadamen.bsky.social. Looking forward to it 🤗

0132

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 27/02/2026

Thanks Bristol Centre for Supercomputing (BriCS) for featuring our work as users of the fantastic #IsambardAI w/ Michael Wray, J Chalk @prajwalgatti.bsky.social @sinhasaptarshi.bsky.social S Bansal, J Zhao @bristoluni.bsky.social @compscibristol.bsky.social www.youtube.com/watch?v=jxrn...

youtube.com

Case study - Isambard-AI: Assistive Technology

YouTube video by BriCS

061

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 24/02/2026

anyone else keeps confusing overleaf with openreview when they type? I keep typing openreview when I mean overleaf, and overleaf when I mean openreview! #overleaf #openreview Ideas to solve my brain wiring are welcome!

7160

Dima Damen @ECCV 2026 @dimadamen.bsky.social · 24/02/2026

Special thanks Ayush @ayusht.bsky.social @universitypress.cambridge.org for visiting us @bristoluni.bsky.social @compscibristol.bsky.social for a great #MaVi Seminar on "Physical Inductive Biases for World Models" and thoughtful 1-1s with the researchers. Have a good trip back &pls visit again soon,

070