News

What is EPIC-KITCHENS-100?

The large-scale dataset in first-person (egocentric) vision; multi-faceted, audio-visual, non-scripted recordings in native environments - i.e. the wearers' homes, capturing all daily activities in the kitchen over multiple days. Annotations are collected using a novel 'Pause-and-Talk' narration interface.

Characteristics

  • 45 kitchens - 4 cities
  • Head-mounted camera
  • 100 hours of recording - Full HD
  • 20M frames
  • Multi-language narrations
  • 90K action segments
  • 20K unique narrations
  • 97 verb classes, 300 noun classes
  • 5 challenges

Previous versions...

EPIC-KITCHENS-100 Stats and Figures

Some graphical representations of our dataset and annotations

Annotation Pipeline

Automatic Annotations

Download

Dataset publicly available for research purposes

Data and Download Script


Erratum [Important]: We have recently detected an error in our pre-extracted RGB and Optical flow frames for two videos in our dataset. This does not affect the videos themselves or any of the annotations in this github. However, if you've been using our pre-extracted frames, you can fix the error at your end by following the instructions in this link.


Extended Sequences (+RGB Frames, Flow Frames, Gyroscope + accelerometer data): Available at Data.Bris servers (740GB zipped) or via Academic Torrents

Original Sequences (+RGB and Flow Frames): Available at Data.Bris servers (1.1TB zipped) or via Academic Torrents

Automatic annotations (masks, hands and objects): Available for download at Data.Bris server (10 GB). We also have two Repos that will allow you to visualise and utilise these automatic annotations for hand-objects as well as masks.

We also offer a python script to download various parts of the dataset

Annotations and Pipeline

All annotations (Train/Val/Test) for all challenges are available at EPIC-KITCHENS-100-annotations repo

Code to visualise and utilise automatic annotations is available for both object masks and hand-object detections.

The EPIC Narrator, used to collect narrations for EPIC-KITCHENS-100 is open-sourced at EPIC-Narrator repo

Publication(s)

Cite our IJCV paper (Open Access 2021 - Published 2022): PDF or Arxiv:

@ARTICLE{Damen2022RESCALING,
           title={Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100},
           author={Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria  and and Furnari, Antonino 
           and Ma, Jian and Kazakos, Evangelos and Moltisanti, Davide and Munro, Jonathan 
           and Perrett, Toby and Price, Will and Wray, Michael},
           journal   = {International Journal of Computer Vision (IJCV)},
           year      = {2022},
           volume = {130},
           pages = {33–55},
           Url       = {https://doi.org/10.1007/s11263-021-01531-2}
} 

Additionally, cite the original paper (available now on Arxiv and the CVF):


   @INPROCEEDINGS{Damen2018EPICKITCHENS,
   title={Scaling Egocentric Vision: The EPIC-KITCHENS Dataset},
   author={Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria  and Fidler, Sanja and 
           Furnari, Antonino and Kazakos, Evangelos and Moltisanti, Davide and Munro, Jonathan 
           and Perrett, Toby and Price, Will and Wray, Michael},
   booktitle={European Conference on Computer Vision (ECCV)},
   year={2018}
} 

An extended journal paper is avaliable at: (available now on IEEE and a preprint on Arxiv and ):


   @ARTICLE{Damen2021PAMI,
   title={The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines},
   author={Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria  and Fidler, Sanja and 
           Furnari, Antonino and Kazakos, Evangelos and Moltisanti, Davide and Munro, Jonathan 
           and Perrett, Toby and Price, Will and Wray, Michael},
   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
   year={2021},
   volume={43},
   number={11},
   pages={4125-4141},
   doi={10.1109/TPAMI.2020.2991965}
} 

Disclaimer

EPIC-KITCHENS-55 and EPIC-KITCHENS-100 were collected as a tool for research in computer vision. The dataset may have unintended biases (including those of a societal, gender or racial nature).

Copyright Creative Commons License

All datasets and benchmarks on this page are copyright by us and published under the Creative Commons Attribution-NonCommercial 4.0 International License. This means that you must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. You may not use the material for commercial purposes.

For commercial licenses of EPIC-KITCHENS and any of its annotations, email us at uob-epic-kitchens@bristol.ac.uk

EPIC-KITCHENS-100 2022 Challenges

Challenge Details with links to ★NEW★ Codalab Leaderboards

2022 Challenges are now closed (read the report), the leaderboards are open for testing models and paper submissions. Check the results of the 2022 chalenge results below

EPIC-Kitchens 2022 Open testing Phase

July 14th 2022,
All leaderboards are re-opened
Nov 21st 2022,
Server Submission will close at 23:59:59 GMT, to prepare for 2023 challenges

EPIC-Kitchens 2022 Challenges

Jan 17th 2022,
All leaderboards are open
June 1st 2022,
Server Submission Deadline at 23:59:59 GMT
June 6th 2022,
Deadline for Submission of Technical Reports on CMT (see guidelines below)
June 19-24 2022,
Results announced at 10th EPIC@CVPR2022 workshop

Open Testing Phase Guidelines

The five leaderboards are available for testing. This is not a formal challenge. Please revisit the website next January for 2023 challenge guideilnes. The CodaLab server pages detail submission format and evaluation metrics.

To submit to any of the five competitions, you need to register an account for that challenge using a valid institute (university/company) email address and fill this form with your team's details. A single registration per research team is allowed. We perform a manual check for each submission, and expect to accept registrations within 2 working days.

For all challenges the maximum submissions per day is limited to 1, and the overall maximum number of submissions per team is limited to 50 overall, submitted once a day. This includes any failed submissions due to formats - please do not contact us to ask for increasing this limit.

To submit your results, follow the JSON submission format, upload your results and give time for the evaluation to complete (in the order of several minutes). Note our new rules on declaring the supervision level, given our proposed scale, for each submission. After the evaluation is complete, the results automatically appear on the public leaderboards but you are allowed to withdraw these at any point in time.

Challenges/Leaderboard Details

Splits. The dataset is split in train/validation/test sets, with a ratio of roughly 75/10/15.
The action recognition, detection and anticipation challenges use all the splits.
The unsupservised domain adaptation and action retrieval challenges use different splits as detailed below.
You can download all the necessary annotations here.
You can find more details about the splits in our paper.

Evaluation. All challenges are evaluated considering all segments in the Test split. The action recognition and anticipation challenges are additionally evaluated considering unseen participants and tail classes. These are automatically evaluated in the scripts and you do not need to do anything specific to report these.
Unseen participants. The validation and test sets contain participants that are not present in the train set. There are 2 unseen participants in the validation set, and another 3 participants in the test set. The corresponding action segments are 1,065 and 4,110 respectively.
Tail classes. These are the set of smallest classes whose instances account for 20% of the total number of instances in training. A tail action class contains either a tail verb class or a tail noun class.

Action Recognition

Task. Assign a (verb, noun) label to a trimmed segment.
Training input (strong supervision). A set of trimmed action segments, each annotated with a (verb, noun) label.
Training input (weak supervision). A set of untrimmed videos, each annotated with a list of (timestamp, verb, noun) labels. Note that for each action you are given a single, roughly aligned timestamp, i.e. one timestamp located around the action. Timestamps may be located over background frames or frames belonging to another action.
Testing input. A set of trimmed unlabelled action segments.
Splits. Train and validation for training, evaluated on the test split.
Evaluation metrics. Top-1/5 accuracy for verb, noun and action (verb+noun), calculated for all segments as well as unseen participants and tail classes.

Submit your results on CodaLab website

Sample qualitative results from the challenge's baseline
Action Detection

Task. Detect the start and the end of each action in an untrimmed video. Assign a (verb, noun) label to each detected segment.
Training input. A set of trimmed action segments, each annotated with a (verb, noun) label.
Testing input. A set of untrimmed videos. Important: You are not allowed to use the knowledge of trimmed segments in the test set when reporting for this challenge.
Splits. Train and validation for training, evaluated on the test split.
Evaluation metrics. Mean Average Precision (mAP) @ IOU 0.1 to 0.5.

Submit your results on CodaLab website

Sample qualitative results from the challenge's baseline
Action Anticipation

Task. Predict the (verb, noun) label of a future action observing a segment preceding its occurrence.
Training input. A set of trimmed action segments, each annotated with a (verb, noun) label.
Testing input. During testing you are allowed to observe a segment that ends at least one second before the start of the action you are testing on.
Splits. Train and validation for training, evaluated on the test split.
Evaluation metrics. Top-5 recall averaged for all classes, as defined here, calculated for all segments as well as unseen participants and tail classes.

Submit your results on CodaLab website

Sample qualitative results from the challenge's baseline
Unsupervised Domain Adaptation for Action Recognition

Task. Assign a (verb, noun) label to a trimmed segment, following the Unsupervised Domain Adaptation paradigm: a labelled source domain is used for training, and the model needs to adapt to an unlabelled target domain.
Training input. A set of trimmed action segments, each annotated with a (verb, noun) label.
Testing input. A set of trimmed unlabelled action segments.
Splits. Videos recorded in 2018 (EPIC-KITCHENS-55) constitute the source domain, while videos recorded for EPIC-KITCHENS-100's extension constitute the unlabelled target domain. This challenge uses custom train/validation/test splits, which you can find here.
Evaluation metrics. Top-1/5 accuracy for verb, noun and action (verb+noun), on the target test set.

Submit your results on CodaLab website

Sample qualitative results from the challenge's baseline
Multi-Instance Retrieval

Tasks. Video to text: given a query video segment, rank captions such that those with a higher rank are more semantically relevant to the action in the query video segment. Text to video: given a query caption, rank video segments such that those with a higher rank are more semantically relevant to the query caption.
Training input. A set of trimmed action segments, each annotated with a caption. Captions correspond to the narration in English from which the action segment was obtained.
Testing input. A set of trimmed action segments with captions. Important: You are not allowed to use the known correspondence in the Test set
Splits. This challenge has its own custom splits, available here.
Evaluation metrics. normalised Discounted Cumulative Gain (nDCG) and Mean Average Precision (mAP). You can find more details in our paper.

Submit your results on CodaLab website

Sample qualitative results from the challenge's baseline

The Team

We are a group of researchers working in computer vision from the University of Bristol and University of Catania. The original dataset was collected in collaboration with Sanja Fidler, University of Toronto

Dima Damen

Principal Investigator
University of Bristol, United Kingom

Giovanni Maria Farinella

Co-Investigator
University of Catania, Italy

Michael Wray

(Apr 2017 - )
University of Bristol

Toby Perrett

(Apr 2017 - )
University of Bristol

Antonino Furnari

(Jul 2017 - )
University of Catania

Jian Ma

(Sep 2019 - )
University of Bristol

Evangelos Kazakos

(Sep 2017 - )
University of Bristol

Daniel Whettam

(July 2020 - )
University of Bristol

Adriano Fragomeni

(Oct 2020 - )
University of Bristol

Bin Zhu

(Jan 2022 - )
University of Bristol

Davide Moltisanti

(Apr 2017 - 2020)
(prev.) University of Bristol
(curr.) Nanyang Tech University

Hazel Doughty

(Apr 2017 - 2020)
(prev.) University of Bristol
(curr.) University of Amsterdam

Jonathan Munro

(Sep 2017 - 2021)
(prev.) University of Bristol

Will Price

(Oct 2017 - 2021)
(prev.) University of Bristol

Research Funding

The work on extending EPIC-KITCHENS was supported by the following research grants

Results - 2022 Challenges (June 2022)

EPIC-Kitchens Challenges @CVPR2022, Hybrid CVPR, New Orleans

Jan 12, 2022
EPIC-Kitchens Challenges 2022 Launched
June 1, 2022
Server Submission Deadline at 23:59:59 GMT
Jun 4, 2022
Deadline for Submission of Technical Reports
June 20, 2022
Results announced at 10th EPIC@CVPR2022 Workshop (watch session recording here)

2022 Challenge Winners

Action Recognition Challenge - 2022

Action Anticipation Challenge - 2022

Action Detection Challenge - 2022

Unsupervised Domain Adaptation for Action Recognition Challenge - 2022

Multi-Instance Retrieval Challenge - 2022