Papers › VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video...

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

23 Mar 2022arXiv:2203.12602archive 2025-07-28

Zhan Tong, Yibing Song, Jue Wang, LiMin Wang

Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired by the recent ImageMAE and propose customized video tube masking with an extremely high ratio. This simple design makes video reconstruction a more challenging self-supervision task, thus encouraging extracting more effective video representations during this pre-training process. We obtain three important findings on SSVP: (1) An extremely high proportion of masking ratio (i.e., 90% to 95%) still yields favorable performance of VideoMAE. The temporally redundant video content enables a higher masking ratio than that of images. (2) VideoMAE achieves impressive results on very small datasets (i.e., around 3k-4k videos) without using any extra data. (3) VideoMAE shows that data quality is more important than data quantity for SSVP. Domain shift between pre-training and target datasets is an important issue. Notably, our VideoMAE with the vanilla ViT can achieve 87.4% on Kinetics-400, 75.4% on Something-Something V2, 91.3% on UCF101, and 62.6% on HMDB51, without using any extra data. Code is available at https://github.com/MCG-NJU/VideoMAE.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 13 code samples harvested from 3 repositories linked to this paper: 10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 2 repositories, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

MCG-NJU/VideoMAE officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
MCG-NJU/VideoMAE-Action-Detection officialmentioned on GitHubpytorchSyntology: 10 samples, 9 ran (2 instrument-failed) · 1 unverified report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
innat/VideoMAE mentioned on GitHubtfApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MS-P3/code7 mindsporeSyntology: not harvested report
MindCode-4/code-1 mindsporeSyntology: not harvested report
MindSpore-scientific/code-13 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SVGDreamer: Text Guided SVG Generation with Diffusion Model (arXiv:2312.16476; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-7 Syntology: not harvested report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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

13 samples harvested: 10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
2ran · our draft was wrong
7ran
3unverified

Licence: 12 of the 13 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. 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.

MCG-NJU/VideoMAE official repository 2 samples, 0 ran · 2 unverified
PretrainVisionTransformer in 6 papers modeling_pretrain.py unverified licence not identified · pointer only · de43f6cdccf9a26b · report
PretrainVisionTransformerEncoder in 5 papers modeling_pretrain.py unverified licence not identified · pointer only · 0b10363b9191132c · report
MCG-NJU/VideoMAE-Action-Detection official repository 10 samples, 9 ran (2 instrument-failed) · 1 unverified
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
modeling_finetune.py ran · metamorphic tier: deterministic licence not identified · pointer only · 3510cd2667e7b0ec · report fixture: returned PatchEmbed · level recorded 2026-09-22
Pooler3d modeling_finetune.py ran · metamorphic tier: deterministic licence not identified · pointer only · b4a6e4ea06502d03 · report fixture: returned Pooler3d · level recorded 2026-09-22
ROIAlign3d modeling_finetune.py ran · metamorphic tier: deterministic licence not identified · pointer only · 81bb1c42f767f787 · report fixture: returned ROIAlign3d · level recorded 2026-09-22
ROIPool3d modeling_finetune.py ran · metamorphic tier: deterministic licence not identified · pointer only · 2648ece3ee513f86 · report fixture: returned ROIPool3d · level recorded 2026-09-22
ROIPoolingCfg modeling_finetune.py ran · metamorphic tier: deterministic licence not identified · pointer only · 6589a88b092ff9b4 · report fixture: returned ROIPoolingCfg · level recorded 2026-09-22
_ROIPool3d modeling_finetune.py ran licence not identified · pointer only · 095c2b760f9d3919 · report fixture: returned _ROIPool3d · level recorded 2026-09-22
get_sinusoid_encoding_table in 51 papers modeling_finetune.py ran · honoured contract fingerprinted licence not identified · pointer only · da651e3979a18f84 · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22
interpolate_pos_embed_online modeling_finetune.py ran · our draft was wrong licence not identified · pointer only · b8c0a309c689d127 · report fixture: signature pos_embed:Tensor/3/float, orig_size:tuple/1/int, new_size:tuple/1/int, num_extra_tokens:int/0/int · returned Tensor · level recorded 2026-09-22
make_3d_pooler modeling_finetune.py ran · our draft was wrong licence not identified · pointer only · 0a01080f8a3a31e8 · report fixture: signature head_cfg:HeadConfig/0/? · returned Pooler3d · level recorded 2026-09-22
VisionTransformer in 53 papers modeling_finetune.py unverified licence not identified · pointer only · 15190c9e8134c543 · report
innat/VideoMAE community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_sinusoid_encoding_table_tf videomae/utils/sinusoid_encoding_table.py ran Apache-2.0 (permissive) · 2a5af7ff657cc9fd · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned EagerTensor · level recorded 2026-09-24

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for VideoMAE (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for VideoMAE (graph method: VideoMAE). 14 bricks; individually on a fixture: 13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. VisionTransformer entry · level 0 · unverified · 15190c9e8134c543
  2. Block model · level 1 · ran · 2fdd988be47b01b8
  3. PatchEmbed model · level 1 · ran · 3510cd2667e7b0ec
  4. ROIPoolingCfg helper · level 1 · ran · 6589a88b092ff9b4
  5. get_sinusoid_encoding_table helper · level 1 · ran · honoured contract · da651e3979a18f84
  6. interpolate_pos_embed_online helper · level 1 · ran · our draft was wrong · b8c0a309c689d127
  7. make_3d_pooler helper · level 1 · ran · our draft was wrong · 0a01080f8a3a31e8
  8. Attention model · level 1 · ran · e6117615a833f3b6
  9. DropPath model · level 1 · ran · ea7880551588ee9f
  10. Mlp model · level 1 · ran · e71525ebf968c4c3
  11. Pooler3d helper · level 1 · ran · b4a6e4ea06502d03
  12. ROIAlign3d helper · level 1 · ran · 81bb1c42f767f787
  13. ROIPool3d helper · level 1 · ran · 2648ece3ee513f86
  14. _ROIPool3d helper · level 1 · ran · 095c2b760f9d3919

harvested Assembly for VideoMAE (graph method: VideoMAE). 10 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. PretrainVisionTransformer entry · level 0 · unverified · de43f6cdccf9a26b
  2. PretrainVisionTransformerDecoder model · level 0 · unverified · 1c888f413c1310c5
  3. PretrainVisionTransformerEncoder model · level 0 · unverified · 0b10363b9191132c
  4. get_sinusoid_encoding_table helper · level 1 · ran · honoured contract · 672ebe50dee3907a
  5. trunc_normal_ helper · level 0 · unverified · 08b4b321d2acf3db
  6. Block helper · level 1 · ran · 2fdd988be47b01b8
  7. PatchEmbed helper · level 1 · ran · 59f1eed28e030f58
  8. Attention helper · level 1 · ran · e6117615a833f3b6
  9. DropPath helper · level 1 · ran · ea7880551588ee9f
  10. Mlp helper · level 1 · ran · e71525ebf968c4c3

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2203.12602") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

4kAction ClassificationAction RecognitionSelf-Supervised Action RecognitionSelf-Supervised Action Recognition LinearVideo ReconstructionVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-H, 32x320x320) Acc@1 87.4 #36 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-H, 32x320x320) Acc@5 97.6 #36 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-H) Acc@1 86.6 #46 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-H) Acc@5 97.1 #46 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-L, 32x320x320) Acc@1 86.1 #50 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-L, 32x320x320) Acc@5 97.3 #50 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-L, 16x4) Acc@1 85.2 #57 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-L, 16x4) Acc@5 96.8 #57 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-B, 16x4) Acc@1 81.5 #82 of 207 Archive leaderboard report
Action Classification Kinetics-400 VideoMAE (no extra data, ViT-B, 16x4) Acc@5 95.1 #82 of 207 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K400 pretrain+finetune, ViT-H, 16x4) mAP 39.5 #10 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K700 pretrain+finetune, ViT-L, 16x4) mAP 39.3 #11 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K400 pretrain+finetune, ViT-L, 16x4) mAP 37.8 #13 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K400 pretrain, ViT-H, 16x4) mAP 36.5 #15 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K700 pretrain, ViT-L, 16x4) mAP 36.1 #16 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K400 pretrain, ViT-L, 16x4) mAP 34.3 #19 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K400 pretrain+finetune, ViT-B, 16x4) mAP 31.8 #23 of 38 Archive leaderboard report
Action Recognition AVA v2.2 VideoMAE (K400 pretrain, ViT-B, 16x4) mAP 26.7 #33 of 38 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 32x2) GFLOPs 1436x3 #9 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 32x2) Parameters 305 #9 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 32x2) Top-1 Accuracy 75.4 #9 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 32x2) Top-5 Accuracy 95.2 #9 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 16frame) GFLOPs 597x6 #15 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 16frame) Parameters 305 #15 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 16frame) Top-1 Accuracy 74.3 #15 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-L, 16frame) Top-5 Accuracy 94.6 #15 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-B, 16frame) GFLOPs 180x6 #36 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-B, 16frame) Parameters 87 #36 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-B, 16frame) Top-1 Accuracy 70.8 #36 of 123 Archive leaderboard report
Action Recognition Something-Something V2 VideoMAE (no extra data, ViT-B, 16frame) Top-5 Accuracy 92.4 #36 of 123 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 VideoMAE Frozen false #5 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 VideoMAE Pre-Training Dataset Kinetics400 #5 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 VideoMAE Top-1 Accuracy 73.3 #5 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 VideoMAE(no extra data) Frozen false #22 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 VideoMAE(no extra data) Pre-Training Dataset no extra data #22 of 48 Archive leaderboard report
Self-Supervised Action Recognition HMDB51 VideoMAE(no extra data) Top-1 Accuracy 62.6 #22 of 48 Archive leaderboard report
Self-Supervised Action Recognition UCF101 VideoMAE 3-fold Accuracy 96.1 #6 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 VideoMAE Frozen false #6 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 VideoMAE Pre-Training Dataset Kinetics400 #6 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 VideoMAE(no extra data) 3-fold Accuracy 91.3 #20 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 VideoMAE(no extra data) Frozen false #20 of 53 Archive leaderboard report
Self-Supervised Action Recognition UCF101 VideoMAE(no extra data) Pre-Training Dataset no extra data #20 of 53 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