Papers › ViViT: A Video Vision Transformer

ViViT: A Video Vision Transformer

29 Mar 2021ICCV 2021 10arXiv:2103.15691archive 2025-07-28

Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, Cordelia Schmid

We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of transformer layers. In order to handle the long sequences of tokens encountered in video, we propose several, efficient variants of our model which factorise the spatial- and temporal-dimensions of the input. Although transformer-based models are known to only be effective when large training datasets are available, we show how we can effectively regularise the model during training and leverage pretrained image models to be able to train on comparatively small datasets. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple video classification benchmarks including Kinetics 400 and 600, Epic Kitchens, Something-Something v2 and Moments in Time, outperforming prior methods based on deep 3D convolutional networks. To facilitate further research, we release code at https://github.com/google-research/scenic/tree/main/scenic/projects/vivit

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

No sample from the archive's official repository (google-research/scenic) is linked to this paper; the 20 samples below come from 4 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from google-research/scenic for 6 other papers.

google-research/scenic: Syntology's graph links these samples to TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? (arXiv:2106.11297; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified), Learning with Neighbor Consistency for Noisy Labels (arXiv:2202.02200; 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) · 0 unverified), Location-Aware Self-Supervised Transformers for Semantic Segmentation (arXiv:2212.02400; that paper's own run record: 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) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 21 code samples: 20 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 21: 14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 4 repositories, 13 ran (13 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 5 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. 1 of the 14 samples that ran has no recorded date.

google-research/scenic officialmentioned in papermentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? (arXiv:2106.11297; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified), Learning with Neighbor Consistency for Noisy Labels (arXiv:2202.02200; 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) · 0 unverified), Location-Aware Self-Supervised Transformers for Semantic Segmentation (arXiv:2212.02400; that paper's own run record: 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) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Abdulrahman-Adel/Real-Life-Violence-Detection mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method. report
KSonPham/ViVit-a-Pytorch-implementation mentioned on GitHubpytorchSyntology: 7 samples, 3 ran (0 instrument-failed) · 4 unverified report
SforAiDl/vformer mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
drv-agwl/ViViT-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
mx-mark/videotransformer-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
rishikksh20/ViViT-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
MS-P3/code7 mindsporeSyntology: not harvested report
keras-team/keras-io tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Forward-Forward Algorithm: Some Preliminary Investigations (arXiv:2212.13345; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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

21 samples harvested: 14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 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
1ran; the contract check could not run
12ran
7unverified

Licence: 1 of the 21 samples 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 4 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. 1 sample is listed last, in a group without a repository. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

KSonPham/ViVit-a-Pytorch-implementation community (archive-listed) 7 samples, 3 ran (0 instrument-failed) · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
models/modeling.py ran · metamorphic tier: deterministic MIT (permissive) · 9650a9a4002b76d8 · report fixture: returned Attention · level recorded 2026-09-22
Embeddings3D models/modeling.py ran · metamorphic tier: deterministic MIT (permissive) · 4a0e3dfe29d9f024 · report fixture: returned Embeddings3D · level recorded 2026-09-22
Mlp in 102 papers models/modeling.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 35965045e79a53f5 · report fixture: returned Mlp · level recorded 2026-09-22
Encoder in 278 papers models/modeling.py unverified MIT (permissive) · a13ffe0da0765ccb · report
MyViViT models/modeling.py unverified MIT (permissive) · f3febe06012a3d59 · report
Transformer in 173 papers models/modeling.py unverified MIT (permissive) · 085322a052a6aa56 · report
SforAiDl/vformer community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
BaseClassificationModel vformer/models/classification/vivit.py ran · metamorphic tier: deterministic MIT (permissive) · f7522b96704eba2a · report fixture: returned BaseClassificationModel · level recorded 2026-09-22
MLPDecoder vformer/models/classification/vivit.py ran · metamorphic tier: deterministic MIT (permissive) · f04db9370cd8032a · report fixture: returned MLPDecoder · level recorded 2026-09-22
Registry in 34 papers vformer/models/classification/vivit.py ran MIT (permissive) · 20fb836cf685bd0e · report fixture: returned Registry · level recorded 2026-09-22
pair in 101 papers vformer/models/classification/vivit.py ran · honoured contract fingerprinted MIT (permissive) · 7deb3c28da2b4c81 · report fixture: signature t:int/0/int · returned tuple · level recorded 2026-09-22
VanillaEncoder vformer/models/classification/vivit.py unverified MIT (permissive) · a639c271341e65f0 · report
ViViTModel2 vformer/models/classification/vivit.py unverified MIT (permissive) · e4a0f20e13c6ea01 · report
drv-agwl/ViViT-pytorch community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
FDATransformerEncoder models.py ran MIT (permissive) · 74f97add2ae8db6e · report fixture: returned FDATransformerEncoder · level recorded 2026-09-22
FDAttention models.py ran MIT (permissive) · f4f644381533aebd · report fixture: returned FDAttention · level recorded 2026-09-22
FSATransformerEncoder models.py ran MIT (permissive) · fc843fa02ae99869 · report fixture: returned FSATransformerEncoder · level recorded 2026-09-22
FSAttention models.py ran MIT (permissive) · 2261806fbb78432d · report fixture: returned FSAttention · level recorded 2026-09-22
ViViTBackbone models.py unverified MIT (permissive) · 893bed9821ea5367 · report
rishikksh20/ViViT-pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Transformer in 173 papers vivit.py ran · metamorphic tier: invariant MIT (permissive) · acb104726aac5d2f · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
ViViT vivit.py ran MIT (permissive) · 2aecd388beda0ef3 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
np2th in 31 papers
census: 2 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 7d8eaf5537f699e4 · report fixture: signature weights:ndarray/4/float, conv:bool/0/bool · returned Tensor · level recorded, date not recorded

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.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for ViViT (graph method: ViViT). 9 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. MyViViT entry · level 0 · unverified · f3febe06012a3d59
  2. Transformer model · level 0 · unverified · 085322a052a6aa56
  3. np2th helper · level 2 · ran; the contract check could not run (RAISES) · 7d8eaf5537f699e4
  4. Embeddings3D model · level 1 · ran · 4a0e3dfe29d9f024
  5. Encoder model · level 0 · unverified · a13ffe0da0765ccb
  6. Block model · level 0 · unverified · 3aeaa3af2d538769
  7. Attention model · level 1 · ran · 9650a9a4002b76d8
  8. Mlp model · level 1 · ran · 35965045e79a53f5
  9. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c

harvested Assembly for ViViT (graph method: ViViT). 6 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ViViTModel2 entry · level 0 · unverified · e4a0f20e13c6ea01
  2. BaseClassificationModel helper · level 1 · ran · f7522b96704eba2a
  3. MLPDecoder helper · level 1 · ran · f04db9370cd8032a
  4. VanillaEncoder helper · level 0 · unverified · a639c271341e65f0
  5. pair helper · level 1 · ran · honoured contract · 7deb3c28da2b4c81
  6. Registry helper · level 1 · ran · 20fb836cf685bd0e

harvested Assembly for ViViT (graph method: ViViT). 7 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ViViTBackbone entry · level 0 · unverified · 893bed9821ea5367
  2. FDATransformerEncoder model · level 1 · ran · 74f97add2ae8db6e
  3. FSATransformerEncoder model · level 1 · ran · fc843fa02ae99869
  4. FDAttention helper · level 1 · ran · f4f644381533aebd
  5. PreNorm helper · level 1 · ran · c40137bc5259e649
  6. FSAttention helper · level 1 · ran · 2261806fbb78432d
  7. FeedForward helper · level 1 · ran · d7f6c1668eb9259b

harvested Assembly for ViViT (graph method: ViViT). 5 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. ViViT entry · level 1 · ran · 2aecd388beda0ef3
  2. Transformer model · level 1 · ran · acb104726aac5d2f
  3. Attention helper · level 1 · ran · 411c4d270072eb2e
  4. FeedForward helper · level 1 · ran · d7f6c1668eb9259b
  5. PreNorm helper · level 1 · ran · c40137bc5259e649

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="2103.15691") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action ClassificationAction RecognitionClassificationGeneral ClassificationImage ClassificationVideo Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 ViViT-H/16x2 (JFT) Acc@1 84.9 #61 of 207 Archive leaderboard report
Action Classification Kinetics-400 ViViT-H/16x2 (JFT) Acc@5 95.8 #61 of 207 Archive leaderboard report
Action Classification Kinetics-400 ViViT-L/16x2 320 Acc@5 94.7 #203 of 207 Archive leaderboard report
Action Classification Kinetics-600 ViViT-H/16x2 (JFT) Top-1 Accuracy 85.8 #29 of 65 Archive leaderboard report
Action Classification Kinetics-600 ViViT-H/16x2 (JFT) Top-5 Accuracy 96.5 #29 of 65 Archive leaderboard report
Action Classification Kinetics-600 ViViT-L/16x2 Top-1 Accuracy 84.3 #34 of 65 Archive leaderboard report
Action Classification Kinetics-600 ViViT-L/16x2 Top-5 Accuracy 95.6 #34 of 65 Archive leaderboard report
Action Classification Kinetics-600 ViViT-L/16x2 (320x320) Top-1 Accuracy 83.0 #42 of 65 Archive leaderboard report
Action Classification Kinetics-600 ViViT-L/16x2 (320x320) Top-5 Accuracy 95.7 #42 of 65 Archive leaderboard report
Action Classification MiT ViViT-L/16x2 Top 5 Accuracy 64.9 #28 of 29 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 ViViT-L/16x2 Fact. encoder Action@1 44.0 #23 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 ViViT-L/16x2 Fact. encoder Noun@1 56.8 #23 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 ViViT-L/16x2 Fact. encoder Verb@1 66.4 #23 of 32 Archive leaderboard report
Action Recognition Something-Something V2 ViViT-L/16x2 Fact. encoder Top-1 Accuracy 65.4 #88 of 123 Archive leaderboard report
Action Recognition Something-Something V2 ViViT-L/16x2 Fact. encoder Top-5 Accuracy 89.8 #88 of 123 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