Dima Damen
@dimadamen.bsky.social
2.1K followers 160 following 150 posts
Professor of Computer Vision, @BristolUni. Senior Research Scientist @GoogleDeepMind - passionate about the temporal stream in our lives. http://dimadamen.github.io
Posts Media Videos Starter Packs
Pinned
dimadamen.bsky.social
🛑📢
HD-EPIC: A Highly-Detailed Egocentric Video Dataset
hd-epic.github.io
arxiv.org/abs/2502.04144
New collected videos
263 annotations/min: recipe, nutrition, actions, sounds, 3D object movement &fixture associations, masks.
26K VQA benchmark to challenge current VLMs
1/N
dimadamen.bsky.social
Also thanks Vassia Simaiaki for the chat and lunch! Nice to catch up again…

Special shout out to Vito, our test driver who took the time to introduce the technology, and suggest how to take the best picture after the tour!

p.s. a wheel moving on its own by magic is a must see!

2/2
dimadamen.bsky.social
My lucky day today to tour with the autonomous UK-based Wayve car!
I was impressed by how smooth to change from manual to full auto - was instantaneous!
The car manoeuvred the narrow lanes of west London calmly, confidently and with skill!
Thanks Ani Kembhavi for the opportunity
1/2
dimadamen.bsky.social
Always proud that our small team of 2 PIs &10 PhD students continues to feature in outstanding reviewer awards at major venues. This @iccv.bsky.social #ICCV2025, 2 students:
Siddhant Bansal and Jacob Chalk were selected. Well-done!
tinyurl.com/ICCV2025OR
2025 ICCV Program Committee
tinyurl.com
dimadamen.bsky.social
Yet another email...
I have to admit these LLMs produce good paper titles I have *not* written:

"Hi Dr. Damen...
I am applying for...
Your recent work on "Video Understanding with Transformers" (2024) and "Deep Learning for Activity Recognition" (2023) particularly resonates with my experience"
!!
dimadamen.bsky.social
When emailing for PhD positions, it's a smart move to use LLMs to avoid typos and grammatical mistakes ... but check for hallucinations!

"I am particularly drawn to your recent work on multi-view video understanding and your development of datasets .. (e.g., the Something-Something dataset). "
Reposted by Dima Damen
anandbhattad.bsky.social
So You Want to Be an Academic?

A couple of years into your PhD, but wondering: "Am I doing this right?"

Most of the advice is aimed at graduating students. But there's far less for junior folks who are still finding their academic path.

My candid takes: anandbhattad.github.io/blogs/jr_gra...
So You Want to Be an Academic? What I Wish I Knew Early in Graduate School
Blog for junior PhD students on work, visibility, community, and sanity—long before the faculty job market is on the horizon.
anandbhattad.github.io
dimadamen.bsky.social
The only thing mentioned was that acceptance rate is high. But no exact explanation to SACs either.
dimadamen.bsky.social
As an SAC for @neuripsconf.bsky.social, I don't agree with PCs approach to reject papers based on ranking.
I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers.
I was not given an explanation of why papers at the end of the rank were rejected.
dimadamen.bsky.social
Finally the dates for @cvprconference.bsky.social are public!
cvpr.thecvf.com/Conferences/...
And there's an additional week for supp videos 🥰
Reposted by Dima Damen
euripsconf.bsky.social
Congratulations to everyone who got their @neuripsconf.bsky.social papers accepted 🎉🎉🎉

At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!
Reposted by Dima Damen
astylianou.bsky.social
Super happy that QuARI: Query Adaptive Retrieval Improvement was accepted at #NeurIPS2025. You can significantly boost retrieval performance for very hard retrieval tasks by learning query-specific transformations of your encoders. w/ @jacobsn.bsky.social @pless.bsky.social arxiv.org/pdf/2505.21647
dimadamen.bsky.social
Warning to PhD students…
Even after you graduate, whenever and wherever you catch up with your supervisor… they will chase you for a catch up and photo…
@hazeldoughty.bsky.social @ekazakos.bsky.social
Reposted by Dima Damen
chriswolfvision.bsky.social
How to name your method: a comprehensive flow chart
Reposted by Dima Damen
ekazakos.bsky.social
We have released the code, checkpoints and datasets for GROVE! Grab them at github.com/ekazakos/grove.

We also provide grove-transformers — an inference-only interface for GROVE, implemented with 🤗 Transformers. You can load GROVE and try it on any video data in just a few lines of code!
dimadamen.bsky.social
When emailing for PhD positions, it's a smart move to use LLMs to avoid typos and grammatical mistakes ... but check for hallucinations!

"I am particularly drawn to your recent work on multi-view video understanding and your development of datasets .. (e.g., the Something-Something dataset). "
Reposted by Dima Damen
chriswolfvision.bsky.social
Dima Damen opens the afternoon session of #PAISS2025 with a presentation on egocentric vision.

At which point does an egg become an egg-shell and how do we deal with the fact that the egg-shell looks more like the "old egg" than the "new egg" in the pan now does? @dimadamen.bsky.social
Reposted by Dima Damen
dlarlus.bsky.social
We couldn't get more lucky with the weather last night for the #PAISS2025 gala - sponsored by @naverlabseurope.bsky.social
dimadamen.bsky.social
As I said in my message: models will be good and accurate enough "in the near future".
dimadamen.bsky.social
Yes. I think humans should stop writing surveys.. and yes I think LLMs will be able to write a survey as good as humans in the near future. The task of summarising, contrasting and organising data is better done by an infinite memory agent than a finite memory human who should focus on innovation.
dimadamen.bsky.social
I’m not an expert on position papers… however I think in the era of increasingly strong LLMs, survey papers should seize to exist, as a concept, in review and overall…. Hope I won’t get a huge backpack for this 🙉
Reposted by Dima Damen
gtolias.bsky.social
The hidden flaws in your favorite foundation model: We've uncovered how subtle image metadata (JPEG params, camera type, etc.) systematically biases visual representations and consequently affect the object recognition ability. To be presented at #ICCV2025 as a highlight paper.
stojnicv.xyz
Have you ever asked yourself how much your favorite vision model knows about image capture parameters (e.g., the amount of JPEG compression, the camera model, etc.)? Furthermore, could these parameters influence its semantic recognition abilities?
dimadamen.bsky.social
No we shouldn't... but also every metric can be optimised through shortcuts and cheating. That doesn't make an evaluation metric itself useless.
The h-index is only meaningful to compare one's career over time, not across people. When calculated (without cheating), it shows a useful trajectory.
dimadamen.bsky.social
not even for tasks such as stirring your food or washing dishes? :-)
dimadamen.bsky.social
This is one of the coolest ideas using EPIC-KITCHENS in a long while...
We've all been waiting to be replaced by robots! At least this is now done in the generative space...
Great work by Marion Lepert, Jiaying Fang and @leto--jean.bsky.social from Stanford IPRL.. congrats!
arxiv.org/abs/2508.09976
Reposted by Dima Damen
chriswolfvision.bsky.social
Vision is gen-NI !

('The shape of things unseen', Adam Zeman)
dimadamen.bsky.social
Happy Birthday Kosta… thanks for sharing the lovely pictures!
Wishing you and your adorable family the next 50 years of Happiness, Heath and Success 🥳🥳