"Slow-Fast Auditory Streams for Audio Recognition" by Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, & Dima Damen ieeexplore.ieee.org/document/94133… #ICASSP2021

Too many workshops #CVPR2026? Here's an invite to spend a relaxing Sunday in 1 full-day workshop with variety: challenge winners, invited keynotes, accepted abstracts and highlighted papers accepted #CVPR2021. 8th EPIC workshop is LIVE all day (from 10:00EDT). eyewear-computing.org/EPIC_CVPR21/pr…

📢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

📢📢3-year postdoc on video understanding in my group tinyurl.com/2y6swek7 DM or apply directly by 5 Dec U can choose your topic-of-focus within multi-modal video understanding We are *proudly* influential but also a cohesive and supportive environment to work within. Pls r/w

CFP #CVPR2026 2-Day Joint 1st #Ego4D &10th #EPIC workshop. Papers &Challenges [thread 1/N] **Published proceedings #IEEE #CVF deadline** 21 Mar Peer-Reviewed novel contributions Submission details: eyewear-computing.org/EPIC_CVPR22/su…

📢[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!

⛳️📢⏯️🏅 #Ego4D Challenges are OPEN w June 1st deadline 6 challenges with winners announced #CVPR2026 Joint EGO4D&EPIC 2-Day Workshop Leaderboards on #EvalAI with code&baseline models now public. #be_a_leader and participate in the first round of #Ego4D challenges [1/8]

⛳️*5 weeks to go* - Server closes 1 June 2022 Your chance to participate and win🥇 one or more of the EPIC-KITCHENS challenges. Results #CVPR2026 Action Recognition Action Anticipation Action Detection Multi-Instance Retrieval UDA for Recognition Details: epic-kitchens.github.io/2022#challenges

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

Congratulations to all winners, On behalf of myself and this year's challenges team: Giovanni M Farinella Antonino Furnari Davide Moltisanti Daniel Whettam Adriano Fragomeni Toby Perrett, Bin Zhu, Michael Wray

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

[RT] Summer Research Visit @BristolUniEng Apply for a 3-months research visit (June-Sep 2023) at the Machine Learning and Computer Vision group to work with *myself* or *any of my fantastic colleagues*. DL: 13 Jan 2023 uob-mavi.github.io/[email protected]…

📢 Now Open For Submissions - all EPIC-KITCHENS Leaderboards for #CVPR2025 #CVPR2023 Challenges. Winners announced at Joint Ego4D and EPIC workshop: sites.google.com/view/ego4d-epi… **Nine** open challenges inc. 4 new ones (see 🧵) Leaderboards close 1st of June 2023. 🧵 1/7

For anyone interested in audio-visual learning, this challenge will be of interest! EPIC-100 and EPIC-SOUNDS is a step towards multi-modal methods where one modality does not rely on the timestamps or label set of another! We look forward to seeing what this challenge brings!

Very excited the EPIC-SOUNDS dataset is finally released! We’ve all worked incredibly hard on this and I can be proud to say that this is my first publication! Looking forward to what this dataset can bring to the deep learning community!

(1) Good news! I've had a paper accepted (with Cian has gone to Bluesky and Mastodon, Nathan Lepora, and Matt W. Jones), and I'll be giving a talk on it at The AAMAS Conference this year 🥳🥳🥳🧠🤖🐀🥳🥳🥳

New paper: a big 90-page intro to AI and its likely effects from ten perspectives, ten camps. The whole gamut: ML, scientific applications, social applications, access, safety and alignment, economics, AI ethics, governance, and classical philosophy of life. 1/18

Good post from Balaji on the "verification gap". You could see it as there being two modes in creation. Borrowing GAN terminology: 1) generation and 2) discrimination. e.g. painting - you make a brush stroke (1) and then you look for a while to see if you improved the

After a year of review, our paper is now out in Nature Communications ! I really think our model/theory offers one of the most promising frameworks yet for learning in neocortical circuits - perhaps not in its final form, but the core principle of ssl feels right. Hoping experimentalists

Our new ICML 2025 oral paper proposes a new unified theory of both Double Descent and Grokking, revealing that both of these deep learning phenomena can be understood as being caused by prime numbers in the network parameters 🤯🤯 🧵[1/8]