New work on multi-modal domain adaptation now on Arxiv. Early insight into utilising multiple modalities for unsupervised domain adaptation in video. x.com/Deep__AI/statu…

Pandas 1.0 is here! * Read the release notes: pandas.pydata.org/pandas-docs/ve… * Read the blogpost reflecting on what 1.0 means to our project: dev.pandas.io/pandas-blog/pa… * Install with conda / PyPI: pandas.pydata.org/pandas-docs/ve… Thanks to our 300+ contributors to this release.

Camera-Ready for our paper "Multi-Modal Domain Adaptation for Fine-Grained Action Recognition" with Jonathan Munro @BristolUniEng accepted as oral #CVPR2026 #CVPR2020 now on ArXiv Project: jonmun.github.io/mmsada/ Video: youtu.be/qgd-DBgf-S0 Arxiv: arxiv.org/abs/2001.09691

Looking 4 downstream task for #self_supervised #video methods? Try action recognition/anticipation/detection/retrieval on #EPICKITCHENS. Submit for private test set leaderboards by selecting supervision level. Compete with self-supervised methods and compare to strong supervision

The EPIC-KITCHENS team is proposing 5 challenges this year: Action Recognition, A. Detection, A. Anticpation, Domain Adaptation for A. Recognition, Multi-instance Retrieval. Results will be announced at CVPR 2021. Check the details here: epic-kitchens.github.io/2021#challenges Dima Damen

📢Working on video understanding:recognition, anticipation,detection,domain adaptation or retrieval? You'll find 2021 EPIC-KITCHENS Tech report informative w 17 methods epic-kitchens.github.io/Reports/EPIC-K… Jonathan Munro Davide Moltisanti Daniel Whettam Antonino Furnari Giovanni M Farinella Fragomeni,Perrett,Wray

DL: 5 Dec... [i.e. SOON!] 4 more days to apply for this #postdoc position. The project is blue-sky research, no deliverables and plenty of scope to bring your A-game to research. DM for Qs and apply directly at: tinyurl.com/2y6swek7

📢[Pls RT] Used EPIC-KITCHENS in ur work? Contribute to our impact anonymous survey: surveymonkey.co.uk/r/epic_kitchens We are collecting data on usage from academia/industry as well as type of data used: narrations/action segments. Will u use our upcoming pixel-level segmentations?? LUK!

Check out our #CVPR2022 work on domain adaptation in video, led by Yunhua Zhang. We use audio to adjust the visual features and better recognize activities under shifts in scenery, viewpoint and actor.

🙏Final call to assist us in planning commercial usage of our dataset and upcoming annotations. Are you a researcher using EPIC-KITCHENS? #dataset #annotation #video Please consider filling our anonymous survey [3 mins of your time] surveymonkey.co.uk/r/epic_kitchens

Come talk to us at poster 31b about Ego4D ⁦#CVPR2026⁩ or explore the dataset if remotely at ego4d-data.org

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

[Pls circulate] Applications are open for up to 3 PhD positions in our group, from all nationalities, in any of the video areas: Multimodal, grounding, domain generalisation/adaptation, VOS, video-language pre-training, explainability and robustness, video manipulation. 1/N

[RTW- Great Opportunity] Looking 4 PhD student🎓 to join my group @BristolUniEng, on long-form video understanding- in collaboration with John Collomosse Fabian Caba ∞. Open to all &international students - start date from May. Open until Filled. Apply asap: tinyurl.com/BristolPhD2023

📢🥳💫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