Papers › End-to-end Temporal Action Detection with Transformer

End-to-end Temporal Action Detection with Transformer

18 Jun 2021arXiv:2106.10271archive 2025-07-28

Xiaolong Liu, Qimeng Wang, Yao Hu, Xu Tang, Shiwei Zhang, Song Bai, Xiang Bai

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.

PaperPDFCodeCode 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="2106.10271")

Code

Syntology Ran 2 of 3 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xlliu7/TadTR officialmentioned in papermentioned 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

3 samples harvested; 2 ran; 0 honoured the contract we drafted; 1 has 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 · our draft was wrong
1unverified

Licence: 0 of the 3 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 xlliu7/TadTR. “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.

get_classes xlliu7/TadTR/Evaluation/eval_detection.py official repository ran · our draft was wrong Apache-2.0 (permissive) · f4bbeee84bc07a00 · report
setup_logger xlliu7/TadTR/Evaluation/eval_detection.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 483d79f60d8148d2 · report
compute_average_precision_detection xlliu7/TadTR/Evaluation/eval_detection.py official repository unverified Apache-2.0 (permissive) · 2795b6049353a54d · report

Tasks

Action DetectionTemporal Action LocalizationVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization ActivityNet-1.3 TadTR (TSP features) mAP 36.75 #14 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 TadTR (TSP features) mAP IOU@0.5 53.62 #14 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 TadTR (TSP features) mAP IOU@0.75 37.52 #14 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 TadTR (TSP features) mAP IOU@0.95 10.56 #14 of 33 Archive leaderboard report
Temporal Action Localization HACS TadTr (I3D RGB) Average-mAP 32.09 #10 of 12 Archive leaderboard report
Temporal Action Localization HACS TadTr (I3D RGB) mAP@0.5 47.14 #10 of 12 Archive leaderboard report
Temporal Action Localization HACS TadTr (I3D RGB) mAP@0.75 32.11 #10 of 12 Archive leaderboard report
Temporal Action Localization HACS TadTr (I3D RGB) mAP@0.95 10.94 #10 of 12 Archive leaderboard report
Temporal Action Localization THUMOS’14 TadTR Avg mAP (0.3:0.7) 56.7 #16 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TadTR mAP IOU@0.3 74.8 #16 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TadTR mAP IOU@0.4 69.1 #16 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TadTR mAP IOU@0.5 60.1 #16 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TadTR mAP IOU@0.6 46.6 #16 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TadTR mAP IOU@0.7 32.8 #16 of 42 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 EncodingsAdamAttentionBPEDeformable Attention ModuleDense 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