Papers › Rescaling Egocentric Vision

Rescaling Egocentric Vision

23 Jun 2020arXiv:2006.13256archive 2025-07-28

Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action detection and evaluating the "test of time" - i.e. whether models trained on data collected in 2018 can generalise to new footage collected two years later. The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repositories (epic-kitchens/epic-kitchens-100-narrator, epic-kitchens/epic-kitchens-100-annotations) were not harvested; the 18 samples below come from 3 community repositories.

Syntology 18 code samples harvested from 3 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 3 repositories, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

epic-kitchens/epic-kitchens-100-narrator officialmentioned in papermentioned on GitHubSyntology: not harvested report
epic-kitchens/epic-kitchens-100-annotations officialmentioned on GitHubNOASSERTIONSyntology: not harvested report
dibschat/tempAgg mentioned on GitHubpytorchMITSyntology: 11 samples, 4 ran (0 instrument-failed) · 7 unverified report
epic-kitchens/C1-Action-Recognition-TSN-TRN-TSM mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
epic-kitchens/epic-kitchens-slowfast mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
jonmun/EPIC-KITCHENS-100_UDA_TA3N mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 unverified report
mustafa1728/TA3N-Lightning mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report

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

18 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
7ran
8unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

dibschat/tempAgg community (archive-listed) 11 samples, 4 ran (0 instrument-failed) · 7 unverified
make_model_name main_anticipation.py ran MIT (permissive) · 481ceff3110252df · report fixture: signature arg_save:ArgSave/0/? · returned str · level recorded 2026-09-24
make_model_name main_recognition.py ran MIT (permissive) · f9e70bd3cf7e4279 · report fixture: signature arg_save:ArgSave/0/? · returned str · level recorded 2026-09-24
topk_accuracy in 14 papers utils.py ran MIT (permissive) · 901f2b8ac3a2558b · report fixture: signature scores:ndarray/2/float, labels:ndarray/1/int, ks:tuple/1/int, selected_class:NoneType/0/? · returned list · level recorded 2026-09-24
topk_recall utils.py ran MIT (permissive) · 787d631ad7f43bca · report fixture: signature scores:ndarray/2/float, labels:ndarray/1/int, k:int/0/int, classes:ndarray/1/int · returned float64 · level recorded 2026-09-24
get_max_pooled_features dataset_anticipation.py unverified MIT (permissive) · 3d14b3a869d72152 · report
get_max_pooled_features dataset_recognition.py unverified MIT (permissive) · 70543185f5aef44d · report
read_data in 132 papers dataset_anticipation.py unverified MIT (permissive) · adc4610bbdea3c1f · report
read_data in 132 papers dataset_recognition.py unverified MIT (permissive) · 3cc8434056c80ba0 · report
read_representations dataset_anticipation.py unverified MIT (permissive) · 196b563c9b99f47a · report
read_representations dataset_recognition.py unverified MIT (permissive) · a11c28a80fd0f7cb · report
topk_accuracy_save_validation_pred utils.py unverified MIT (permissive) · 48e6e656ed8d5dae · report
jonmun/EPIC-KITCHENS-100_UDA_TA3N community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
attentive_entropy in 6 papers loss.py ran · our draft was wrong fingerprinted MIT (permissive) · 5dafc748f41191f5 · report fixture: signature pred:Tensor/2/float, pred_domain:Tensor/2/float · returned Tensor · level recorded 2026-09-24
cross_entropy_soft in 6 papers loss.py ran · our draft was wrong fingerprinted MIT (permissive) · b1e8dce608f3f658 · report fixture: signature pred:Tensor/2/float · returned Tensor · level recorded 2026-09-24
dis_MCD in 5 papers loss.py ran · our draft was wrong fingerprinted MIT (permissive) · 0c3c2aa9cf2ac2f0 · report fixture: signature out1:Tensor/2/float, out2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
randSelectBatch utils/utils.py ran fingerprinted MIT (permissive) · 8651bcfb1198f96d · report fixture: signature input:Tensor/2/float, num:int/0/int · returned tuple · level recorded 2026-09-25
mustafa1728/TA3N-Lightning community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
get_aggregated_metrics_from_dict model.py ran MIT (permissive) · 0fb3b659d41d4031 · report fixture: signature input_metric_dict:dict/0/? · returned dict · level recorded 2026-09-24
removeDummy model.py ran MIT (permissive) · 0fb8066818796998 · report fixture: signature attn:Tensor/3/float, out_1:tuple/1/Tensor, out_2:Tensor/2/float, pred_domain:list/1/Tensor, feat:list/1/Tensor, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
get_aggregated_metrics model.py unverified MIT (permissive) · 5fb564b0af4ab527 · report

Tasks

Action AnticipationAction DetectionAction RecognitionCross-Modal RetrievalDomain AdaptationRetrievalUnsupervised Domain Adaptation

Datasets

Introduced by this paper, per the archive.

EPIC-KITCHENS-100

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Anticipation EPIC-KITCHENS-100 RU-LSTM Recall@5 13.94 #9 of 9 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TSM Action@1 37.39 #27 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 SlowFast Action@1 36.81 #28 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TBN Action@1 35.55 #30 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TRN Action@1 35.28 #31 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TSN Action@1 33.57 #32 of 32 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