user avatar
Dima Damen @CVPR
@dimadamen
Professor of Computer Vision, @bristolcs. Senior Staff Research Scientist @GoogleDeepMind - passionate about the temporal stream in our lives.
Bristol, UK
Joined April 2013
Posts
  • Pinned
    user avatar
    🛑📢 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
    00:00
  • user avatar
    "Computer Vision is too important to be left to Machine Learning people" -- Jitendra Malik @ICCV_2021 panel
    GIF
  • user avatar
    My office for the next month as I visit @JitendraMalikCV @berkeley_ai as part of my fellowship's sabbatical. Amazing views... If you're in the Bay Area and want to catch up, let me know! Will be here throughout Feb.
  • user avatar
    To clarify, in case not obvious, this plagiarised paper will not appear at ICCV 2021 and we are accumulating evidence to pass to IEEE and CVF. Do not refer to it as ICCV2021 paper, for correctness. Authors of ICML 2021 paper have been informed. We thank them for their cooperation
    Imitation is the sincerest form of flattery 🙌🙌🙌 arxiv.org/abs/2102.07870 arxiv.org/abs/2108.05862
  • user avatar
    Replying to @RaquelUrtasun and @UofT
    0 papers accepted #ECCV2020. Still very proud of the two papers we had under review, and I certainly feel I can take summer holidays as well... if it wasn't for our workshop at ECCV, release of EPIC-KITCHENS-100 dataset and the brilliant team I lead - small and beautiful ;-)
  • user avatar
    Today, we release EPIC-KITCHENS VISOR: 10M frames of dense segmentations from 271K of manually segmented masks along with 70K of hand-object relations, for long-term reasoning Watch our 3min VISOR trailer 📽️ [music on] youtu.be/yGodQAbYW_E Project: epic-kitchens.github.io/VISOR/ 1/N
  • user avatar
    📢🥳💫We were told this was impossible! Now public - accurate camera pose estimation for EPIC-KITCHENS, fully automatically. EPIC Fields: Marrying 3D Geometry and Video Understanding Dataset: epic-kitchens.github.io/epic-fields/ Paper: arxiv.org/abs/2306.08731 Trailer: youtu.be/RcacE26eObE
  • user avatar
    I’m looking for a rising star postdoc to join my group from Jan 2021 or shortly after, for 30 months with a possible extension. A very engaging research project on video-understanding, building on our egocentric vision strength, in collaboration with Andrea and AZ @Oxford_VGG.
  • user avatar
    I do not regret going to @CVPR despite testing positive just now. I was -ve pre-flight but developed symptoms over flight and now have fever. Thanks to colleagues who informed me they tested positive - we had dinner Thur. Apologies if I passed it on! Wish you speedy recovery
  • user avatar
    Shoutout to the anonymous reviewer in my @CVPR #CVPR2024 AC pile who raised their scores from WR to WA with the comment: "I apologise that I did not notice XXX... ". Heart-warming when reviewers take their jobs seriously as scientific assessors regardless of the ego!
    GIF
  • user avatar
    📢 [New Preprint]@eccvconf #ECCV2024 paper AMEGO: Active Memory from long EGOcentric videos gabrielegoletto.github.io/AMEGO/ Semantic-free representation of all interacting objects and locations in a long egocentric video. w/ 20K VQA benchmark that uses object crops to query interactions.
    00:00
  • user avatar
    I'm starting a new role in the service of our #research #community as Associate Editor In Chief (AEIC) of IEEE TPAMI, managing the #ComputerVision queue of excellent submissions alongside Vladlen Koltun, Jiaya Jia, @jana_kosecka and @MingHsuanYang. Looking 4wrd to the challenge!
  • user avatar
    IMO you should submit a paper because you *want* the work to be accessible to others- you learnt something you wish to share. Recent trend that authors *need* the publication for grad school or job is harmful. Works you are not proud of can negatively impact career and motivation
    GIF
  • user avatar
    Keynote @CVPR... the gap is in "modelling the world, not the data"... Josh Tenenbaum