Papers › TAda! Temporally-Adaptive Convolutions for Video Understanding

TAda! Temporally-Adaptive Convolutions for Video Understanding

12 Oct 2021ICLR 2022 4arXiv:2110.06178archive 2025-07-28

Ziyuan Huang, Shiwei Zhang, Liang Pan, Zhiwu Qing, Mingqian Tang, Ziwei Liu, Marcelo H. Ang Jr

Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions (TAdaConv) for video understanding, which shows that adaptive weight calibration along the temporal dimension is an efficient way to facilitate modelling complex temporal dynamics in videos. Specifically, TAdaConv empowers the spatial convolutions with temporal modelling abilities by calibrating the convolution weights for each frame according to its local and global temporal context. Compared to previous temporal modelling operations, TAdaConv is more efficient as it operates over the convolution kernels instead of the features, whose dimension is an order of magnitude smaller than the spatial resolutions. Further, the kernel calibration brings an increased model capacity. We construct TAda2D and TAdaConvNeXt networks by replacing the 2D convolutions in ResNet and ConvNeXt with TAdaConv, which leads to at least on par or better performance compared to state-of-the-art approaches on multiple video action recognition and localization benchmarks. We also demonstrate that as a readily plug-in operation with negligible computation overhead, TAdaConv can effectively improve many existing video models with a convincing margin.

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

The archive's official repository (alibaba-mmai-research/pytorch-video-understanding) was not harvested; the 1 sample below comes from 1 community repository.

Syntology 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

By repository: community (archive-listed): 1 sample from 1 repository, 0 ran (0 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.

alibaba-mmai-research/pytorch-video-understanding officialmentioned in papermentioned on GitHubpytorchMITSyntology: not harvested report
alibaba-mmai-research/TAdaConv mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 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.

Code Syntology ran Syntology

1 sample harvested: 0 ran · 1 unverified. 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.

1unverified

Licence: 0 of the 1 sample 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 alibaba-mmai-research/TAdaConv. “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. “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.

alibaba-mmai-research/TAdaConv community (archive-listed) 1 sample, 0 ran · 1 unverified
TAdaConv2d tadaconv/models/module_zoo/ops/tadaconv.py unverified Apache-2.0 (permissive) · cf623eebda41b1bf · 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 TAdaConv (graph method: TAdaConv). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. TAdaConv2d entry · level 0 · unverified · cf623eebda41b1bf

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="2110.06178") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action ClassificationAction RecognitionTemporal Action LocalizationVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 TAdaConvNeXt-T Acc@1 79.1 #120 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAdaConvNeXt-T Acc@5 93.7 #120 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAda2D-En (ResNet-50, 8+16 frames) Acc@1 78.2 #128 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAda2D-En (ResNet-50, 8+16 frames) Acc@5 93.5 #128 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAda2D (ResNet-50, 16 frames) Acc@1 77.4 #139 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAda2D (ResNet-50, 16 frames) Acc@5 93.1 #139 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAda2D (ResNet-50, 8 frames) Acc@1 76.7 #146 of 207 Archive leaderboard report
Action Classification Kinetics-400 TAda2D (ResNet-50, 8 frames) Acc@5 92.6 #146 of 207 Archive leaderboard report
Action Recognition Something-Something V2 TAda2D-En (ResNet-50, 8+16 frames) Top-1 Accuracy 67.2 #69 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAda2D-En (ResNet-50, 8+16 frames) Top-5 Accuracy 89.8 #69 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAdaConvNeXt-T Top-1 Accuracy 67.1 #71 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAdaConvNeXt-T Top-5 Accuracy 90.4 #71 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAda2D (ResNet-50, 16 frames) Top-1 Accuracy 65.6 #87 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAda2D (ResNet-50, 16 frames) Top-5 Accuracy 89.2 #87 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAda2D (ResNet-50, 8 frames) Top-1 Accuracy 64.0 #97 of 123 Archive leaderboard report
Action Recognition Something-Something V2 TAda2D (ResNet-50, 8 frames) Top-5 Accuracy 88.0 #97 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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