Papers › Temporal-Relational CrossTransformers for Few-Shot Action Recognition

Temporal-Relational CrossTransformers for Few-Shot Action Recognition

15 Jan 2021CVPR 2021 1arXiv:2101.06184archive 2025-07-28

Toby Perrett, Alessandro Masullo, Tilo Burghardt, Majid Mirmehdi, Dima Damen

We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set. Distinct from previous few-shot works, we construct class prototypes using the CrossTransformer attention mechanism to observe relevant sub-sequences of all support videos, rather than using class averages or single best matches. Video representations are formed from ordered tuples of varying numbers of frames, which allows sub-sequences of actions at different speeds and temporal offsets to be compared. Our proposed Temporal-Relational CrossTransformers (TRX) achieve state-of-the-art results on few-shot splits of Kinetics, Something-Something V2 (SSv2), HMDB51 and UCF101. Importantly, our method outperforms prior work on SSv2 by a wide margin (12%) due to the its ability to model temporal relations. A detailed ablation showcases the importance of matching to multiple support set videos and learning higher-order relational CrossTransformers.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2101.06184")

Code

Syntology Ran 2 of 5 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 4 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tobyperrett/trx officialmentioned in papermentioned on GitHubpytorch report
tobyperrett/few-shot-action-recognition mentioned on GitHubpytorch 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

5 samples harvested; 2 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
3unverified

Licence: 1 of the 5 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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 “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

TemporalCrossTransformer tobyperrett/TRX/model.py official repository ran no licence file found · pointer only · aeea130033d03d70 · report
PositionalEncoding tobyperrett/few-shot-action-recognition/model.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · 7a7f13875a559f13 · report
CNN_FSHead tobyperrett/few-shot-action-recognition/model.py community (archive-listed) unverified MIT (permissive) · 6bd0a764fe5fd045 · report
CNN_TRX tobyperrett/few-shot-action-recognition/model.py community (archive-listed) unverified MIT (permissive) · 5395da485f228630 · report
TemporalCrossTransformer tobyperrett/few-shot-action-recognition/model.py community (archive-listed) unverified MIT (permissive) · 78bb275b16ade682 · report

Tasks

Action RecognitionFew Shot Action RecognitionFew-Shot action recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few Shot Action Recognition HMDB51 TRX 1:1 Accuracy 75.6 #4 of 7 Archive leaderboard report
Few Shot Action Recognition Kinetics-100 TRX Accuracy 85.9 #5 of 8 Archive leaderboard report
Few Shot Action Recognition Something-Something-100 TRX 1:1 Accuracy 64.6 #3 of 5 Archive leaderboard report
Few Shot Action Recognition UCF101 TRX 1:1 Accuracy 96.1 #3 of 7 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

CrossTransformers

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