Papers › ReAct: Temporal Action Detection with Relational Queries

ReAct: Temporal Action Detection with Relational Queries

14 Jul 2022arXiv:2207.07097archive 2025-07-28

Dingfeng Shi, Yujie Zhong, Qiong Cao, Jing Zhang, Lin Ma, Jia Li, DaCheng Tao

This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if directly applied to TAD: the insufficient exploration of inter-query relation in the decoder, the inadequate classification training due to a limited number of training samples, and the unreliable classification scores at inference. To this end, we first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Moreover, we propose two losses to facilitate and stabilize the training of action classification. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries. The proposed method, named ReAct, achieves the state-of-the-art performance on THUMOS14, with much lower computational costs than previous methods. Besides, extensive ablation studies are conducted to verify the effectiveness of each proposed component. The code is available at https://github.com/sssste/React.

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="2207.07097")

Code

Syntology Ran 2 of 12 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 12 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.

sssste/react officialmentioned in paperpytorchMIT 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

12 samples harvested; 2 ran; 0 honoured the contract we drafted; 10 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
10unverified

Licence: 0 of the 12 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 sssste/React. “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.

all_gather sssste/React/React/utill/misc.py official repository ran MIT (permissive) · aa6da43d05cfaf65 · report
reduce_dict sssste/React/React/utill/misc.py official repository ran MIT (permissive) · 05992505df9ef0cd · report
collate_fn sssste/React/React/utill/misc.py official repository unverified MIT (permissive) · 8afa631a846ef588 · report
embeddingto2d sssste/React/React/utill/viz.py official repository unverified MIT (permissive) · 958ce3808938e30f · report
find_match_gt sssste/React/React/utill/temporal_box_producess.py official repository unverified MIT (permissive) · 5334c4d83d9da129 · report
load_proposal_file sssste/React/React/thumos_dataset.py official repository unverified MIT (permissive) · 45fddd2562b43511 · report
mid_dis2start_end sssste/React/React/utill/temporal_box_producess.py official repository unverified MIT (permissive) · 533a2025d10b811b · report
register_hooks sssste/React/React/utill/bad_grad_viz.py official repository unverified MIT (permissive) · 55db86fcc85cb96d · report
sigmoid_focal_loss sssste/React/React/model/React.py official repository unverified MIT (permissive) · 2043ee96aadac29d · report
start_end2mid_dis sssste/React/React/utill/temporal_box_producess.py official repository unverified MIT (permissive) · 6e92295b5b0a88ac · report
vis_1d_box sssste/React/React/utill/viz.py official repository unverified MIT (permissive) · f0b9c93da8e4c2bb · report
vis_2d_scatter sssste/React/React/utill/viz.py official repository unverified MIT (permissive) · ea5b8dccd6161c45 · report

Tasks

Action ClassificationAction DetectionClassificationDecoderObject DetectionTemporal Action Localizationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization THUMOS’14 ReAct (TSN features) Avg mAP (0.3:0.7) 55.0 #17 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 ReAct (TSN features) mAP IOU@0.3 69.2 #17 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 ReAct (TSN features) mAP IOU@0.4 65.0 #17 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 ReAct (TSN features) mAP IOU@0.5 57.1 #17 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 ReAct (TSN features) mAP IOU@0.6 47.8 #17 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 ReAct (TSN features) mAP IOU@0.7 35.6 #17 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.

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