Papers › MoViNets: Mobile Video Networks for Efficient Video Recognition

MoViNets: Mobile Video Networks for Efficient Video Recognition

21 Mar 2021CVPR 2021 1arXiv:2103.11511archive 2025-07-28

Dan Kondratyuk, Liangzhe Yuan, Yandong Li, Li Zhang, Mingxing Tan, Matthew Brown, Boqing Gong

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but require large computation and memory budgets and do not support online inference, making them difficult to work on mobile devices. We propose a three-step approach to improve computational efficiency while substantially reducing the peak memory usage of 3D CNNs. First, we design a video network search space and employ neural architecture search to generate efficient and diverse 3D CNN architectures. Second, we introduce the Stream Buffer technique that decouples memory from video clip duration, allowing 3D CNNs to embed arbitrary-length streaming video sequences for both training and inference with a small constant memory footprint. Third, we propose a simple ensembling technique to improve accuracy further without sacrificing efficiency. These three progressive techniques allow MoViNets to achieve state-of-the-art accuracy and efficiency on the Kinetics, Moments in Time, and Charades video action recognition datasets. For instance, MoViNet-A5-Stream achieves the same accuracy as X3D-XL on Kinetics 600 while requiring 80% fewer FLOPs and 65% less memory. Code will be made available at https://github.com/tensorflow/models/tree/master/official/vision.

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 (tensorflow/models) is linked to this paper; the 13 samples below come from 1 community repository. Syntology harvested code from tensorflow/models for 4 other papers.

tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 13 code samples harvested from 1 repository linked to this paper: 9 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; 1 where Syntology's instrument failed) · 4 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): 13 samples from 1 repository, 9 ran (8 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 2 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.

tensorflow/models officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Atze00/MoViNet-pytorch mentioned on GitHubpytorchSyntology: 13 samples, 9 ran (1 instrument-failed) · 4 unverified report
towhee-io/towhee pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified), LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval (arXiv:2103.08784; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified) and 9 more (every one in this page's JSON twin); 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: 9 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; 1 where Syntology's instrument failed) · 4 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
7ran
4unverified

Licence: 0 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 Atze00/MoViNet-pytorch. “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.

Atze00/MoViNet-pytorch community (archive-listed) 13 samples, 9 ran (1 instrument-failed) · 4 unverified
Conv2dBNActivation movinets/models.py ran fingerprinted MIT (permissive) · ac373f664ffe80dd · report fixture: returned Conv2dBNActivation · level recorded 2026-09-22
Conv3DBNActivation movinets/models.py ran · metamorphic tier: deterministic MIT (permissive) · 2ba2cd56ee729128 · report fixture: returned Conv3DBNActivation · level recorded 2026-09-22
ConvBlock3D movinets/models.py ran · metamorphic tier: deterministic MIT (permissive) · 131856849e049bf9 · report fixture: returned ConvBlock3D · level recorded 2026-09-22
Hardsigmoid movinets/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · d81897bae7fd5d1f · report fixture: returned Hardsigmoid · level recorded 2026-09-22
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input
movinets/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · c246a91a55da902d · report fixture: returned Swish · level recorded 2026-09-22
TemporalCGAvgPool3D movinets/models.py ran · metamorphic tier: deterministic MIT (permissive) · 90c736c9bb473ebf · report fixture: returned TemporalCGAvgPool3D · level recorded 2026-09-22
_make_divisible in 9 papers movinets/models.py ran · honoured contract fingerprinted MIT (permissive) · 0cf345647883539d · report fixture: signature v:float/0/float, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-22
same_padding in 10 papers movinets/models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 1679ae00114efb03 · report fixture: signature x:Tensor/4/float, in_height:int/0/int, in_width:int/0/int, stride_h:int/0/int, stride_w:int/0/int, filter_height:int/0/int, filter_width:int/0/int · returned Tensor · level recorded 2026-09-22
tfAvgPool3D movinets/models.py ran fingerprinted MIT (permissive) · 5262209acc985170 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
BasicBneck movinets/models.py unverified MIT (permissive) · 6cee250f62ac6745 · report
CausalModule movinets/models.py unverified MIT (permissive) · f65eda23dc445262 · report
MoViNet movinets/models.py unverified MIT (permissive) · c18a67956b8eb0ed · report
SqueezeExcitation in 5 papers movinets/models.py unverified MIT (permissive) · 633fa35c6d75c2b4 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MoViNets (graph method: MoViNets). 13 bricks; individually on a fixture: 9 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; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. MoViNet entry · level 0 · unverified · c18a67956b8eb0ed
  2. BasicBneck model · level 0 · unverified · 6cee250f62ac6745
  3. CausalModule helper · level 0 · unverified · f65eda23dc445262
  4. ConvBlock3D model · level 1 · ran · 131856849e049bf9
  5. Swish helper · level 1 · ran · c246a91a55da902d
  6. TemporalCGAvgPool3D helper · level 1 · ran · 90c736c9bb473ebf
  7. Hardsigmoid helper · level 1 · ran · d81897bae7fd5d1f
  8. SqueezeExcitation model · level 0 · unverified · 633fa35c6d75c2b4
  9. tfAvgPool3D helper · level 1 · ran · 5262209acc985170
  10. Conv2dBNActivation helper · level 1 · ran · ac373f664ffe80dd
  11. Conv3DBNActivation helper · level 1 · ran · 2ba2cd56ee729128
  12. same_padding helper · level 1 · ran; the contract check could not run (RAISES) · 1679ae00114efb03
  13. _make_divisible helper · level 1 · ran · honoured contract · 0cf345647883539d

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="2103.11511") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action ClassificationAction RecognitionComputational EfficiencyNeural Architecture SearchTemporal Action LocalizationVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Charades MoViNet-A6 MAP 63.2 #3 of 49 Archive leaderboard report
Action Classification Charades MoViNet-A4 MAP 48.5 #12 of 49 Archive leaderboard report
Action Classification Charades MoViNet-A2 MAP 32.5 #40 of 49 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A6 Acc@1 81.5 #83 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A6 FLOPs (G) x views 386x1 #83 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A5 Acc@1 80.9 #91 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A5 Acc@5 94.9 #91 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A5 FLOPs (G) x views 281x1 #91 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A4 Acc@1 80.5 #97 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A4 Acc@5 94.5 #97 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A4 FLOPs (G) x views 105x1 #97 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A3 Acc@1 78.2 #127 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A3 Acc@5 93.8 #127 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A3 FLOPs (G) x views 56.9x1 #127 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A2 Acc@1 75.0 #158 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A2 Acc@5 92.3 #158 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A2 FLOPs (G) x views 10.3x1 #158 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A1 Acc@1 72.7 #172 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A1 Acc@5 91.2 #172 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A1 FLOPs (G) x views 6.0x1 #172 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A0 Acc@1 65.8 #191 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A0 Acc@5 87.4 #191 of 207 Archive leaderboard report
Action Classification Kinetics-400 MoViNet-A0 FLOPs (G) x views 2.7x1 #191 of 207 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A5 (AutoAugment) GFLOPs 281x1 #33 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A5 (AutoAugment) Top-1 Accuracy 84.3 #33 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A5 (AutoAugment) Top-5 Accuracy 96.4 #33 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A6 GFLOPs 386x1 #38 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A6 Top-1 Accuracy 83.5 #38 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A6 Top-5 Accuracy 96.5 #38 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A5 GFLOPs 281x1 #43 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A5 Top-1 Accuracy 82.7 #43 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A5 Top-5 Accuracy 95.7 #43 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A4 GFLOPs 105x1 #48 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A4 Top-1 Accuracy 81.2 #48 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A4 Top-5 Accuracy 94.9 #48 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A3 GFLOPs 56.9x1 #50 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A3 Top-1 Accuracy 80.8 #50 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A3 Top-5 Accuracy 80.8 #50 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A2 GFLOPs 10.3x1 #57 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A2 Top-1 Accuracy 77.5 #57 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A2 Top-5 Accuracy 93.4 #57 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A1 GFLOPs 6.0x1 #59 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A1 Top-1 Accuracy 76.0 #59 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A1 Top-5 Accuracy 92.6 #59 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A0 GFLOPs 2.7x1 #62 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A0 Top-1 Accuracy 71.5 #62 of 65 Archive leaderboard report
Action Classification Kinetics-600 MoViNet-A0 Top-5 Accuracy 90.4 #62 of 65 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A6 Top-1 Accuracy 72.3 #20 of 36 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A5 Top-1 Accuracy 71.7 #21 of 36 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A4 Top-1 Accuracy 70.7 #23 of 36 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A3 Top-1 Accuracy 68.0 #26 of 36 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A2 Top-1 Accuracy 66.7 #28 of 36 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A1 Top-1 Accuracy 63.5 #29 of 36 Archive leaderboard report
Action Classification Kinetics-700 MoViNet-A0 Top-1 Accuracy 58.5 #30 of 36 Archive leaderboard report
Action Classification MiT MoViNet-A6 Top 1 Accuracy 40.2 #9 of 29 Archive leaderboard report
Action Classification MiT MoViNet-A5 Top 1 Accuracy 39.1 #10 of 29 Archive leaderboard report
Action Classification MiT MoViNet-A4 Top 1 Accuracy 37.9 #11 of 29 Archive leaderboard report
Action Classification MiT MoViNet-A3 Top 1 Accuracy 35.6 #14 of 29 Archive leaderboard report
Action Classification MiT MoViNet-A2 Top 1 Accuracy 34.3 #15 of 29 Archive leaderboard report
Action Classification MiT MoViNet-A1 Top 1 Accuracy 32.0 #19 of 29 Archive leaderboard report
Action Classification MiT MoViNet-A0 Top 1 Accuracy 27.5 #27 of 29 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A6 Action@1 47.7 #14 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A6 GFLOPs 117x1 #14 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A6 Noun@1 57.3 #14 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A6 Verb@1 72.2 #14 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A5 Action@1 44.5 #18 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A5 GFLOPs 74.9x1 #18 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A5 Noun@1 55.1 #18 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A5 Verb@1 69.1 #18 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A4 Action@1 44.4 #21 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A4 GFLOPs 42.2x1 #21 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A4 Noun@1 56.2 #21 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A4 Verb@1 68.8 #21 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A2 Action@1 41.2 #26 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A2 GFLOPs 7.59x1 #26 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A2 Noun@1 52.3 #26 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A2 Verb@1 67.1 #26 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A0 Action@1 36.8 #29 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A0 GFLOPs 1.74x1 #29 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A0 Noun@1 47.4 #29 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 MoViNet-A0 Verb@1 64.8 #29 of 32 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A2 GFLOPs 10.3x1 #98 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A2 Parameters 4.8M #98 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A2 Top-1 Accuracy 63.5 #98 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A2 Top-5 Accuracy 89.0 #98 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A1 GFLOPs 6.0x1 #101 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A1 Parameters 4.6M #101 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A1 Top-1 Accuracy 62.7 #101 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A1 Top-5 Accuracy 89.0 #101 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A0 GFLOPs 2.7x1 #110 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A0 Parameters 3.1M #110 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A0 Top-1 Accuracy 61.3 #110 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A0 Top-5 Accuracy 88.2 #110 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A3 GFLOPs 23.7x1 #122 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MoViNet-A3 Parameters 5.3M #122 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.

Methods

3D CNNMoViNet

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