Papers › Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
Scaling Egocentric Vision: The EPIC-KITCHENS Dataset
Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray
First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict nonscripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labeled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. Dataset and Project page: http://epic-kitchens.github.io
In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | ATSN | Top 1 Accuracy - Act. | 6.00 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | ATSN | Top 1 Accuracy - Noun | 16.22 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | ATSN | Top 1 Accuracy - Verb | 31.81 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | ATSN | Top 5 Accuracy - Act. | 28.21 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | ATSN | Top 5 Accuracy - Noun | 42.15 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | ATSN | Top 5 Accuracy - Verb | 76.56 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | 2SCNN | Top 1 Accuracy - Act. | 4.32 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | 2SCNN | Top 1 Accuracy - Noun | 15.15 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | 2SCNN | Top 1 Accuracy - Verb | 29.76 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | 2SCNN | Top 5 Accuracy - Act. | 15.21 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | 2SCNN | Top 5 Accuracy - Noun | 38.56 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Seen test set (S1)) | 2SCNN | Top 5 Accuracy - Verb | 76.03 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | ATSN | Top 1 Accuracy - Act. | 2.39 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | ATSN | Top 1 Accuracy - Noun | 10.41 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | ATSN | Top 1 Accuracy - Verb | 25.30 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | ATSN | Top 5 Accuracy - Act. | 6.63 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | ATSN | Top 5 Accuracy - Noun | 29.50 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | ATSN | Top 5 Accuracy - Verb | 68.32 | #6 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | 2SCNN | Top 1 Accuracy - Act. | 2.29 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | 2SCNN | Top 1 Accuracy - Noun | 9.97 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | 2SCNN | Top 1 Accuracy - Verb | 25.23 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | 2SCNN | Top 5 Accuracy - Act. | 9.35 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | 2SCNN | Top 5 Accuracy - Noun | 27.38 | #7 of 7 | Archive leaderboard | report |
| Action Anticipation | EPIC-KITCHENS-55 (Unseen test set (S2) | 2SCNN | Top 5 Accuracy - Verb | 68.66 | #7 of 7 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections