Papers › Multiscale Vision Transformers

Multiscale Vision Transformers

22 Apr 2021ICCV 2021 10arXiv:2104.11227archive 2025-07-28

Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https://github.com/facebookresearch/SlowFast

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 (facebookresearch/SlowFast) is linked to this paper; the 26 samples below come from 2 community repositories. Syntology harvested code from facebookresearch/SlowFast for another paper.

facebookresearch/SlowFast: Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 26 code samples harvested from 2 repositories linked to this paper: 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) · 13 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 26 samples from 2 repositories, 13 ran (11 with no instrument failure; 2 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 6 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.

facebookresearch/SlowFast officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
facebookresearch/hiera mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles (arXiv:2306.00989; that paper's own run record: 5 ran (of which 0 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) · 1 unverified); nothing checks that they implement this paper's method. report
facebookresearch/pytorchvideo mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PyTorchVideo: A Deep Learning Library for Video Understanding (arXiv:2111.09887; that paper's own run record: 5 ran (of which 0 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) · 2 unverified); nothing checks that they implement this paper's method. report
junweiliang/multitrain mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-dataset Training of Transformers for Robust Action Recognition (arXiv:2209.12362; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
rohanshad/cmr_transformer mentioned on GitHubpytorchSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
wangjk666/stts mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to id 136950068 (not an arXiv id) (that paper's own run record: 3 ran (of which 0 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) · 1 unverified); nothing checks that they implement this paper's method. report
facebookresearch/mvit pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
towhee-io/towhee pytorchSyntology: 21 samples, 11 ran (2 instrument-failed) · 10 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.

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

26 samples harvested: 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) · 13 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; the contract check could not run
10ran
13unverified

Licence: 5 of the 26 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”. For 3 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.

rohanshad/cmr_transformer community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
MultiscaleVisionTransformers arch/mvit.py ran · metamorphic tier: deterministic licence not identified · pointer only · 73d46d814f26bc08 · report fixture: returned MultiscaleVisionTransformers · level recorded 2026-09-22
SpatioTemporalClsPositionalEncoding arch/mvit.py ran · metamorphic tier: deterministic licence not identified · pointer only · 8e8401b5c2cbe9af · report fixture: returned SpatioTemporalClsPositionalEncoding · level recorded 2026-09-22
_init_vit_weights in 9 papers arch/mvit.py unverified licence not identified · pointer only · 31c2f4da4c4a0948 · report
init_net_weights arch/mvit.py unverified licence not identified · pointer only · 081229a28d5f0e17 · report
set_attributes arch/mvit.py unverified licence not identified · pointer only · f69f7538b6980470 · report
towhee-io/towhee community (archive-listed) 21 samples, 11 ran (2 instrument-failed) · 10 unverified
AttentionPool towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · aabc00fba35e5b60 · report fixture: returned AttentionPool · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
towhee/models/multiscale_vision_transformers/mvit.py ran fingerprinted Apache-2.0 (permissive) · 8eadaa524165fa27 · report fixture: returned DropPath · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · 137b894a55248107 · report fixture: returned LayerNorm · level recorded 2026-09-22
MaxPool3d towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · 11bb9021dd0d5f1d · report fixture: returned MaxPool3d · level recorded 2026-09-22
Mlp in 102 papers towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · 9220e80dfcec043a · report fixture: returned Mlp · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · 56cfb3a853df70e9 · report fixture: returned PatchEmbed · level recorded 2026-09-22
Sigmoid towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · ca6f8c79a4ba5eea · report fixture: returned Sigmoid · level recorded 2026-09-22
TransformerBasicHead towhee/models/multiscale_vision_transformers/mvit.py ran Apache-2.0 (permissive) · a84009ea4b4e7411 · report fixture: returned TransformerBasicHead · level recorded 2026-09-22
drop_path_func towhee/models/multiscale_vision_transformers/mvit.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 63080b2b0157a638 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
find_most_h_w towhee/models/multiscale_vision_transformers/mvit.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · fa1b9bbe882fd839 · report fixture: signature all_layer_matrices:list/1/Tensor · returned tuple · level recorded 2026-09-22
round_width in 7 papers towhee/models/multiscale_vision_transformers/mvit.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · c828b94ed536888e · report fixture: signature width:int/0/int, multiplier:float/0/float, min_width:int/0/int, divisor:int/0/int · returned int · level recorded 2026-09-22
Add towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · e085e89664c8c8f1 · report
Clone towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · c8f04d0354d412d8 · report
Conv3d towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · f51d56342db748dc · report
IndexSelect towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · c6b33d8045bad24a · report
MViT towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · b3cb3600d1ec619e · report
MultiScaleAttention towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · d0c301eed0a9217c · report
MultiScaleBlock towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · 2e7ddef56b034315 · report
align_scale towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · 4038555957e35d15 · report
compute_rollout_attention in 9 papers towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · 59e53e1981813f80 · report
resize_last_dim_to_most towhee/models/multiscale_vision_transformers/mvit.py unverified Apache-2.0 (permissive) · a6b157934033010d · report

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 Multiscale Vision Transformers (MViT) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

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

one of 2 siblings

  1. MultiscaleVisionTransformers entry · level 1 · ran · 73d46d814f26bc08
  2. init_net_weights helper · level 0 · unverified · 081229a28d5f0e17
  3. set_attributes helper · level 0 · unverified · f69f7538b6980470
  4. _init_vit_weights helper · level 0 · unverified · 31c2f4da4c4a0948
  5. SpatioTemporalClsPositionalEncoding model · level 1 · ran · 8e8401b5c2cbe9af

harvested Assembly for Multiscale Vision Transformers (MViT) (graph method: Multiscale Vision Transformers (MViT)). 31 bricks; individually on a fixture: 18 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MViT entry · level 0 · unverified · b3cb3600d1ec619e
  2. Add helper · level 0 · unverified · e085e89664c8c8f1
  3. IndexSelect helper · level 0 · unverified · c6b33d8045bad24a
  4. LayerNorm helper · level 1 · ran · 137b894a55248107
  5. MultiScaleBlock model · level 0 · unverified · 2e7ddef56b034315
  6. PatchEmbed model · level 1 · ran · 56cfb3a853df70e9
  7. TransformerBasicHead model · level 1 · ran · a84009ea4b4e7411
  8. compute_rollout_attention helper · level 0 · unverified · 59e53e1981813f80
  9. round_width helper · level 1 · ran · honoured contract · c828b94ed536888e
  10. RelPropSimple helper · level 0 · unverified · 1bc2938f5a5b8e2e
  11. safe_divide helper · level 1 · ran · honoured contract · 507e144112f81dc6
  12. RelProp helper · level 0 · unverified · e04c66afc6a652b1
  13. AttentionPool helper · level 1 · ran · aabc00fba35e5b60
  14. Clone helper · level 0 · unverified · c8f04d0354d412d8
  15. DropPath model · level 1 · ran · 8eadaa524165fa27
  16. GELU helper · level 1 · ran · d4114dbf5943332c
  17. Linear helper · level 1 · ran · 82f963c4eb1876d4
  18. MaxPool3d helper · level 1 · ran · 11bb9021dd0d5f1d
  19. Mlp model · level 1 · ran · 9220e80dfcec043a
  20. MultiScaleAttention model · level 0 · unverified · d0c301eed0a9217c
  21. Conv2d helper · level 1 · ran · 18583975af70b0aa
  22. Conv3d helper · level 0 · unverified · f51d56342db748dc
  23. Sigmoid helper · level 1 · ran · ca6f8c79a4ba5eea
  24. Softmax helper · level 1 · ran · 15c57dc641cf3d74
  25. align_scale helper · level 0 · unverified · 4038555957e35d15
  26. forward_hook helper · level 0 · unverified · f1b1138b372a9b03
  27. drop_path_func helper · level 1 · ran; the contract check could not run (RAISES) · 63080b2b0157a638
  28. Dropout helper · level 1 · ran · 6b2146395f61d804
  29. Einsum helper · level 1 · ran · d2f31546ef368292
  30. find_most_h_w helper · level 1 · ran; the contract check could not run (RAISES) · fa1b9bbe882fd839
  31. resize_last_dim_to_most helper · level 0 · unverified · a6b157934033010d

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="2104.11227") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action ClassificationAction RecognitionImage ClassificationVideo Recognitionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Charades MViT-B-24, 32x3 (Kinetics-600 pretraining) MAP 47.7 #14 of 49 Archive leaderboard report
Action Classification Charades MViT-B, 32x3 (Kinetics-600 pretraining) MAP 47.1 #16 of 49 Archive leaderboard report
Action Classification Charades MViT-B-24, 32x3 (Kinetics-400 pretraining) MAP 46.3 #17 of 49 Archive leaderboard report
Action Classification Charades MViT-B, 32x3 (Kinetics-400 pretraining) MAP 44.3 #19 of 49 Archive leaderboard report
Action Classification Charades MViT-B, 16x4 (Kinetics-600 pretraining) MAP 43.9 #21 of 49 Archive leaderboard report
Action Classification Charades MViT-B, 16x4 (Kinetics-400 pretraining) MAP 40 #33 of 49 Archive leaderboard report
Action Classification Kinetics-400 MViT-B, 64x3 Acc@1 81.2 #87 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-B, 64x3 Acc@5 95.1 #87 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-B, 32x3 Acc@1 80.2 #103 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-B, 32x3 Acc@5 94.4 #103 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-B, 16x4 Acc@1 78.4 #126 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-B, 16x4 Acc@5 93.5 #126 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-S Acc@1 76 #151 of 207 Archive leaderboard report
Action Classification Kinetics-400 MViT-S Acc@5 92.1 #151 of 207 Archive leaderboard report
Action Classification Kinetics-600 MViT-B-24, 32x3 Top-1 Accuracy 83.8 #36 of 65 Archive leaderboard report
Action Classification Kinetics-600 MViT-B-24, 32x3 Top-5 Accuracy 96.3 #36 of 65 Archive leaderboard report
Action Classification Kinetics-600 MViT-B, 32x3 Top-1 Accuracy 83.4 #39 of 65 Archive leaderboard report
Action Classification Kinetics-600 MViT-B, 32x3 Top-5 Accuracy 96.3 #39 of 65 Archive leaderboard report
Action Classification Kinetics-600 MViT-B, 16x4 Top-1 Accuracy 82.1 #44 of 65 Archive leaderboard report
Action Classification Kinetics-600 MViT-B, 16x4 Top-5 Accuracy 95.7 #44 of 65 Archive leaderboard report
Action Recognition AVA v2.2 MViT-B-24, 32x3 (Kinetics-600 pretraining) mAP 28.7 #27 of 38 Archive leaderboard report
Action Recognition AVA v2.2 MViT-B, 32x3 (Kinetics-500 pretraining) mAP 27.5 #28 of 38 Archive leaderboard report
Action Recognition AVA v2.2 MViT-B, 64x3 (Kinetics-400 pretraining) mAP 27.3 #30 of 38 Archive leaderboard report
Action Recognition AVA v2.2 MViT-B, 32x3 (Kinetics-400 pretraining) mAP 26.8 #32 of 38 Archive leaderboard report
Action Recognition AVA v2.2 MViT-B, 16x4 (Kinetics-600 pretraining) mAP 26.1 #35 of 38 Archive leaderboard report
Action Recognition AVA v2.2 MViT-B, 16x4 (Kinetics-400 pretraining) mAP 24.5 #36 of 38 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B-24, 32x3 GFLOPs 236x3 #49 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B-24, 32x3 Parameters 53.2M #49 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B-24, 32x3 Top-1 Accuracy 68.7 #49 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B-24, 32x3 Top-5 Accuracy 91.5 #49 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B, 32x3(Kinetics600 pretrain) GFLOPs 170x3 #57 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B, 32x3(Kinetics600 pretrain) Parameters 36.6 #57 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B, 32x3(Kinetics600 pretrain) Top-1 Accuracy 67.8 #57 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B, 32x3(Kinetics600 pretrain) Top-5 Accuracy 91.3 #57 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B, 16x4 Top-1 Accuracy 66.2 #82 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MViT-B, 16x4 Top-5 Accuracy 90.2 #82 of 123 Archive leaderboard report
Image Classification ImageNet MViT-B-24 GFLOPs 32.7 #287 of 1060 Archive leaderboard report
Image Classification ImageNet MViT-B-24 Number of params 72.9M #287 of 1060 Archive leaderboard report
Image Classification ImageNet MViT-B-24 Top 1 Accuracy 84.8% #287 of 1060 Archive leaderboard report
Image Classification ImageNet MViT-B-16 GFLOPs 7.8 #479 of 1060 Archive leaderboard report
Image Classification ImageNet MViT-B-16 Number of params 37M #479 of 1060 Archive leaderboard report
Image Classification ImageNet MViT-B-16 Top 1 Accuracy 83.0% #479 of 1060 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.

Methods

Introduced by this paper: MViT

MViT

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