Datasets › EPIC-KITCHENS-55
EPIC-KITCHENS-55
The EPIC-KITCHENS-55 dataset comprises a set of 432 egocentric videos recorded by 32 participants in their kitchens at 60fps with a head mounted camera. There is no guiding script for the participants who freely perform activities in kitchens related to cooking, food preparation or washing up among others. Each video is split into short action segments (mean duration is 3.7s) with specific start and end times and a verb and noun annotation describing the action (e.g. ‘open fridge‘). The verb classes are 125 and the noun classes 331. The dataset is divided into one train and two test splits.
Source: Egocentric Hand Track and Object-based Human Action Recognition Image Source: https://epic-kitchens.github.io/2020-100
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Egocentric Activity Recognition | EPIC-KITCHENS-55 | DEEP-HAL with ODF+SDF (AssembleNet++) Actions Top-1 (S1) 35.8 | Self-supervising Action Recognition by Statistical... | — | 7 | Compare |
| Action Recognition | EPIC-KITCHENS-55 | TSM+W3 - full res Top-1 Accuracy 34.2 | Knowing What, Where and When to Look: Efficient Video... | — | 1 | Compare |
| Video Object Detection | EPIC-KITCHENS-55 | Ours (Faster RCNN) mAP@.5 41.7 | Objects do not disappear: Video object detection by... | l-kid/video-object-detection-by-location-anticipation +1 | 1 | Compare |
Papers archive 2025-07-28
8 shown of 8 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 42. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Objects do not disappear: Video object detection by single-frame object location anticipation | 2 | 1 | 9 Aug 2023 | not harvested |
| Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention | 0 | 1 | 2 Apr 2020 | not harvested |
| Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors | 0 | 1 | 14 Jan 2020 | not harvested |
| EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition | 1 | 1 | 22 Aug 2019 | not harvested |
| What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention | 2 | 1 | 22 May 2019 | not harvested |
| Large-scale weakly-supervised pre-training for video action recognition | 3 | 2 | 2 May 2019 | ran 0 of 21 samples (21 unverified) |
| Long-Term Feature Banks for Detailed Video Understanding | 4 | 1 | 12 Dec 2018 | ran 0 of 8 samples (8 unverified) |
| LSTA: Long Short-Term Attention for Egocentric Action Recognition | 1 | 1 | 26 Nov 2018 | not harvested |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- EPIC-KITCHENS-55
1 variant name, as the archive lists them.
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