Papers › Large-scale weakly-supervised pre-training for video action recognition

Large-scale weakly-supervised pre-training for video action recognition

2 May 2019CVPR 2019 6arXiv:1905.00561archive 2025-07-28

Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, Dhruv Mahajan

Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using large volumes of web videos for pre-training video models for the task of action recognition. Our primary empirical finding is that pre-training at a very large scale (over 65 million videos), despite on noisy social-media videos and hashtags, substantially improves the state-of-the-art on three challenging public action recognition datasets. Further, we examine three questions in the construction of weakly-supervised video action datasets. First, given that actions involve interactions with objects, how should one construct a verb-object pre-training label space to benefit transfer learning the most? Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning? Finally, actions are generally less well-localized in long videos vs. short videos; since action labels are provided at a video level, how should one choose video clips for best performance, given some fixed budget of number or minutes of videos?

PaperPDFConference PDFCodeCode 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

Syntology 21 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 21 samples from 2 repositories, 12 ran (12 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

moabitcoin/ig65m-pytorch mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
microsoft/computervision-recipes pytorchMITSyntology: 16 samples, 8 ran (0 instrument-failed) · 8 unverified report
open-mmlab/mmaction2 pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Interlacing Network (arXiv:2001.06499; that paper's own run record: 17 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

12ran
9unverified

Licence: 0 of the 21 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 2 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

moabitcoin/ig65m-pytorch community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
blobs_from_pkl ig65m/cli/convert.py ran MIT (permissive) · 8439277e085dfc38 · report fixture: signature path:PosixPath/0/? · returned list · level recorded 2026-09-24
r2plus1d_34_32_ig65m ig65m/models.py ran MIT (permissive) · cb39d2a70fde7d87 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, progress:bool/0/bool · returned VideoResNet · level recorded 2026-09-24
r2plus1d_34_8_ig65m ig65m/models.py ran MIT (permissive) · 21dfb37daa3d5a63 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, progress:bool/0/bool · returned VideoResNet · level recorded 2026-09-24
r2plus1d_34_8_kinetics ig65m/models.py ran MIT (permissive) · ba55356a87900992 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, progress:bool/0/bool · returned VideoResNet · level recorded 2026-09-24
main in 235 papers ig65m/cli/server.py unverified MIT (permissive) · 1a80caf172692d16 · report
microsoft/computervision-recipes community (archive-listed) 16 samples, 8 ran (0 instrument-failed) · 8 unverified
convert2gray contrib/document_cleanup/light_weight_document_cleanup_ICDAR2021/model.py ran MIT (permissive) · 2ae3a0bf00128d4b · report fixture: signature in_tensor:EagerTensor/4/int · returned EagerTensor · level recorded 2026-09-24
get_optimal_threshold utils_cv/classification/model.py ran MIT (permissive) · e057f034f658dbfe · report fixture: signature metric_function:callable/0/?, y_pred:Tensor/1/float, y_true:Tensor/1/float, thresholds:list/1/float · returned float64 · level recorded 2026-09-24
get_ratio_correct_metric utils_cv/segmentation/model.py ran MIT (permissive) · f809ba52b7fe6bf7 · report fixture: signature classes:list/1/str · returned partial · level recorded 2026-09-24
gram_matrix in 45 papers
census: 7 implementations from 9 papers, 4 distinct outputs on one shared input
contrib/document_cleanup/light_weight_document_cleanup_ICDAR2021/loss_function.py ran MIT (permissive) · 24caeadc560dd7b1 · report fixture: signature input_tensor:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
hamming_accuracy utils_cv/classification/model.py ran fingerprinted MIT (permissive) · 6e3c07a22fc403cd · report fixture: signature y_pred:Tensor/2/float, y_true:Tensor/2/float, threshold:float/0/float, sigmoid:bool/0/bool · returned Tensor · level recorded 2026-09-24
is_installed in 7 papers contrib/vm_builder/vm_builder.py ran MIT (permissive) · 8baa827e7a093444 · report fixture: signature cli_app:str/0/str · returned bool · level recorded 2026-09-24
ratio_correct utils_cv/segmentation/model.py ran MIT (permissive) · c9d0ef61d7a0052a · report fixture: signature void_id:int/0/int, input:Tensor/4/float, target:Tensor/4/int · returned Tensor · level recorded 2026-09-24
zero_one_accuracy utils_cv/classification/model.py ran fingerprinted MIT (permissive) · 19b949c8e8b6cc5a · report fixture: signature y_pred:Tensor/2/float, y_true:Tensor/2/float, threshold:float/0/float, sigmoid:bool/0/bool · returned Tensor · level recorded 2026-09-24
Compute_PLoss contrib/document_cleanup/light_weight_document_cleanup_ICDAR2021/loss_function.py unverified MIT (permissive) · b79851f2da94bb38 · report
CreateModel_M16_binary contrib/document_cleanup/light_weight_document_cleanup_ICDAR2021/model.py unverified MIT (permissive) · d2e1797dd9a3e283 · report
evaluate_mot utils_cv/tracking/model.py unverified MIT (permissive) · ca5129f92643bc3e · report
get_pretrained_fasterrcnn utils_cv/detection/model.py unverified MIT (permissive) · 6f8cd1e7f213cb4a · report
get_pretrained_keypointrcnn utils_cv/detection/model.py unverified MIT (permissive) · f763516cdbd12500 · report
get_pretrained_maskrcnn utils_cv/detection/model.py unverified MIT (permissive) · 3769b815f2bf3b26 · report
res_net_block contrib/document_cleanup/light_weight_document_cleanup_ICDAR2021/model.py unverified MIT (permissive) · 6da0ad792057efe4 · report
vgg_layers contrib/document_cleanup/light_weight_document_cleanup_ICDAR2021/loss_function.py unverified MIT (permissive) · c9e8ae02d557b195 · report

Tasks

Action ClassificationAction RecognitionActivity RecognitionActivity Recognition In VideosEgocentric Activity RecognitionTemporal Action LocalizationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 irCSN-152 (IG-Kinetics-65M pretrain) Acc@1 82.8 #72 of 207 Archive leaderboard report
Egocentric Activity Recognition EPIC-KITCHENS-55 R(2+1)D-152-SE (ig) Actions Top-1 (S2) 25.6 #5 of 7 Archive leaderboard report
Egocentric Activity Recognition EPIC-KITCHENS-55 R(2+1)D-34 (kinetics) Actions Top-1 (S2) 16.8 #6 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