Papers › HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

7 Jun 2019ICCV 2019 10arXiv:1906.03327archive 2025-07-28

Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, Josef Sivic

Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations. The contributions of this work are three-fold. First, we introduce HowTo100M: a large-scale dataset of 136 million video clips sourced from 1.22M narrated instructional web videos depicting humans performing and describing over 23k different visual tasks. Our data collection procedure is fast, scalable and does not require any additional manual annotation. Second, we demonstrate that a text-video embedding trained on this data leads to state-of-the-art results for text-to-video retrieval and action localization on instructional video datasets such as YouCook2 or CrossTask. Finally, we show that this embedding transfers well to other domains: fine-tuning on generic Youtube videos (MSR-VTT dataset) and movies (LSMDC dataset) outperforms models trained on these datasets alone. Our dataset, code and models will be publicly available at: www.di.ens.fr/willow/research/howto100m/.

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 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

antoine77340/MIL-NCE_HowTo100M mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
antoine77340/S3D_HowTo100M mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
antoine77340/milnce_howto100m mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Learning of Visual Representations from Uncurated Instructional Videos (arXiv:1912.06430; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
roudimit/AVLnet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

1 sample harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

1ran · our draft was wrong

Licence: 1 of the 1 sample is 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 antoine77340/MIL-NCE_HowTo100M. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

antoine77340/MIL-NCE_HowTo100M community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_last_checkpoint in 22 papers main_distributed.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 4d241892c1ca731a · report fixture: signature checkpoint_dir:str/0/str · returned str · level recorded 2026-09-22

Tasks

Action LocalizationLong Video Retrieval (Background Removed)RetrievalText to Video RetrievalVideo Retrieval

Datasets

Introduced by this paper, per the archive.

HowTo100M

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long Video Retrieval (Background Removed) YouCook2 Text-Video Embedding Cap. Avg. R@1 46.6 #5 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 Text-Video Embedding Cap. Avg. R@10 83.7 #5 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 Text-Video Embedding Cap. Avg. R@5 74.3 #5 of 6 Archive leaderboard report
Temporal Action Localization CrossTask Text-Video Embedding Recall 33.6 #4 of 7 Archive leaderboard report
Video Retrieval LSMDC Text-Video Embedding text-to-video Median Rank 40 #36 of 38 Archive leaderboard report
Video Retrieval LSMDC Text-Video Embedding text-to-video R@1 7.2 #36 of 38 Archive leaderboard report
Video Retrieval LSMDC Text-Video Embedding text-to-video R@10 27.9 #36 of 38 Archive leaderboard report
Video Retrieval LSMDC Text-Video Embedding text-to-video R@5 19.6 #36 of 38 Archive leaderboard report
Video Retrieval MSR-VTT Text-Video Embedding text-to-video Median Rank 9 #34 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Text-Video Embedding text-to-video R@1 14.9 #34 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Text-Video Embedding text-to-video R@10 52.8 #34 of 40 Archive leaderboard report
Video Retrieval MSR-VTT Text-Video Embedding video-to-text R@5 40.2 #34 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT-Pretrained text-to-video Median Rank 9 #57 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT-Pretrained text-to-video R@1 14.9 #57 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT-Pretrained text-to-video R@10 52.8 #57 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT-Pretrained text-to-video R@5 40.2 #57 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT text-to-video Median Rank 12 #58 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT text-to-video R@1 12.1 #58 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT text-to-video R@10 48.0 #58 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA HT text-to-video R@5 35.0 #58 of 63 Archive leaderboard report
Video Retrieval YouCook2 Text-Video Embedding text-to-video Median Rank 24 #11 of 16 Archive leaderboard report
Video Retrieval YouCook2 Text-Video Embedding text-to-video R@1 8.2 #11 of 16 Archive leaderboard report
Video Retrieval YouCook2 Text-Video Embedding text-to-video R@10 35.3 #11 of 16 Archive leaderboard report
Video Retrieval YouCook2 Text-Video Embedding text-to-video R@5 24.5 #11 of 16 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