Papers › Relational Self-Attention: What's Missing in Attention for Video Understanding

Relational Self-Attention: What's Missing in Attention for Video Understanding

2 Nov 2021NeurIPS 2021 12arXiv:2111.01673archive 2025-07-28

Manjin Kim, Heeseung Kwon, Chunyu Wang, Suha Kwak, Minsu Cho

Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks, has revealed the limitation of stationary convolution kernels and opened the door to the era of dynamic feature transforms. The existing dynamic transforms, including self-attention, however, are all limited for video understanding where correspondence relations in space and time, i.e., motion information, are crucial for effective representation. In this work, we introduce a relational feature transform, dubbed the relational self-attention (RSA), that leverages rich structures of spatio-temporal relations in videos by dynamically generating relational kernels and aggregating relational contexts. Our experiments and ablation studies show that the RSA network substantially outperforms convolution and self-attention counterparts, achieving the state of the art on the standard motion-centric benchmarks for video action recognition, such as Something-Something-V1 & V2, Diving48, and FineGym.

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 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 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.

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

KimManjin/RSA officialpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result. “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

Licence: 1 of the 1 sample 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 KimManjin/RSA. “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.

KimManjin/RSA official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RSA ops/rsa.py ran no licence file found · pointer only · 17dc37e26f9a98c6 · report fixture: returned RSA · level recorded 2026-09-22

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 Relational Self-Attention (RSA) (graph method: Relational Self-Attention (RSA)). 1 brick; individually on a fixture: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. RSA entry · level 1 · ran · 17dc37e26f9a98c6

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="2111.01673") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action RecognitionTemporal Action LocalizationVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition Diving-48 RSANet-R50 (16 frames, ImageNet pretrained, a single clip) Accuracy 84.2 #12 of 18 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips) Top 1 Accuracy 56.1 #23 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips) Top 5 Accuracy 82.8 #23 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (8+16 frames, ImageNet pretrained, a single clip) Top 1 Accuracy 55.5 #25 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (8+16 frames, ImageNet pretrained, a single clip) Top 5 Accuracy 82.6 #25 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (16 frames, ImageNet pretrained, a single clip) Top 1 Accuracy 54.0 #34 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (16 frames, ImageNet pretrained, a single clip) Top 5 Accuracy 81.1 #34 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (8 frames, ImageNet pretrained, a single clip) Top 1 Accuracy 51.9 #46 of 74 Archive leaderboard report
Action Recognition Something-Something V1 RSANet-R50 (8 frames, ImageNet pretrained, a single clip) Top 5 Accuracy 79.6 #46 of 74 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips Top-1 Accuracy 67.7 #62 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips Top-5 Accuracy 91.1 #62 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8+16 frames, ImageNet pretrained, a single clip) Top-1 Accuracy 67.3 #67 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8+16 frames, ImageNet pretrained, a single clip) Top-5 Accuracy 90.8 #67 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (16 frames, ImageNet pretrained, a single clip) Top-1 Accuracy 66 #83 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (16 frames, ImageNet pretrained, a single clip) Top-5 Accuracy 89.8 #83 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8 frames, ImageNet pretrained, a single clip) Top-1 Accuracy 64.8 #92 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8 frames, ImageNet pretrained, a single clip) Top-5 Accuracy 89.1 #92 of 123 Archive leaderboard report
Action Recognition Something-Something V2 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips) Top-5 Accuracy 91.1 #121 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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