Papers › TriDet: Temporal Action Detection with Relative Boundary Modeling

TriDet: Temporal Action Detection with Relative Boundary Modeling

13 Mar 2023CVPR 2023 1arXiv:2303.07347archive 2025-07-28

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

In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action boundaries in videos. To alleviate this problem, we propose a novel Trident-head to model the action boundary via an estimated relative probability distribution around the boundary. In the feature pyramid of TriDet, we propose an efficient Scalable-Granularity Perception (SGP) layer to mitigate the rank loss problem of self-attention that takes place in the video features and aggregate information across different temporal granularities. Benefiting from the Trident-head and the SGP-based feature pyramid, TriDet achieves state-of-the-art performance on three challenging benchmarks: THUMOS14, HACS and EPIC-KITCHEN 100, with lower computational costs, compared to previous methods. For example, TriDet hits an average mAP of 69.3% on THUMOS14, outperforming the previous best by 2.5%, but with only 74.6% of its latency. The code is released to https://github.com/sssste/TriDet.

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="2303.07347")

Code

Syntology Ran 5 of 15 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dingfengshi/tridet officialmentioned in papermentioned on GitHubpytorchMIT 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

15 samples harvested; 5 ran; 1 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.

1ran · honoured contract
2ran · fixture could not drive it
2ran
10unverified

Licence: 0 of the 15 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 dingfengshi/TriDet. “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.

drop_path dingfengshi/TriDet/libs/modeling/blocks.py official repository ran · fixture could not drive it MIT (permissive) · a34c005ba2203f35 · report
get_sinusoid_encoding dingfengshi/TriDet/libs/modeling/blocks.py official repository ran · honoured contract fingerprinted MIT (permissive) · 3531df7b0c9b0791 · report
sigmoid_focal_loss dingfengshi/TriDet/libs/modeling/losses.py official repository ran MIT (permissive) · 54293ea22bd4f952 · report
trunc_normal_ dingfengshi/TriDet/libs/modeling/weight_init.py official repository ran · fixture could not drive it MIT (permissive) · 02566da69866c48c · report
truncate_feats dingfengshi/TriDet/libs/datasets/data_utils.py official repository ran MIT (permissive) · fbd46ea8e0501851 · report
ctr_diou_loss_1d dingfengshi/TriDet/libs/modeling/losses.py official repository unverified MIT (permissive) · 12d8ba65aabcb2b4 · report
ctr_giou_loss_1d dingfengshi/TriDet/libs/modeling/losses.py official repository unverified MIT (permissive) · 66693d03280664b1 · report
load_config dingfengshi/TriDet/libs/core/config.py official repository unverified MIT (permissive) · e2efca9389531bc8 · report
make_data_loader dingfengshi/TriDet/libs/datasets/datasets.py official repository unverified MIT (permissive) · 635369f63ec96b89 · report
make_dataset dingfengshi/TriDet/libs/datasets/datasets.py official repository unverified MIT (permissive) · ffebfbb8094c0dcc · report
register_backbone dingfengshi/TriDet/libs/modeling/models.py official repository unverified MIT (permissive) · cee845f405ecf37e · report
register_dataset dingfengshi/TriDet/libs/datasets/datasets.py official repository unverified MIT (permissive) · 2ee0df0825339a6e · report
register_generator dingfengshi/TriDet/libs/modeling/models.py official repository unverified MIT (permissive) · 3db1c5ab5f3f0198 · report
register_neck dingfengshi/TriDet/libs/modeling/models.py official repository unverified MIT (permissive) · e5ef13b176081594 · report
trivial_batch_collator dingfengshi/TriDet/libs/datasets/data_utils.py official repository unverified MIT (permissive) · 0c250bf03b8c9311 · report

Tasks

Action DetectionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization ActivityNet-1.3 TriDet (TSP features) mAP 36.8 #13 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 TriDet (TSP features) mAP IOU@0.5 54.7 #13 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 TriDet (TSP features) mAP IOU@0.75 38.0 #13 of 33 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 TriDet (TSP features) mAP IOU@0.95 8.4 #13 of 33 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 TriDet (verb) Avg mAP (0.1-0.5) 25.4 #2 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 TriDet (verb) mAP IOU@0.1 28.6 #2 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 TriDet (verb) mAP IOU@0.2 27.4 #2 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 TriDet (verb) mAP IOU@0.3 26.1 #2 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 TriDet (verb) mAP IOU@0.4 24.2 #2 of 6 Archive leaderboard report
Temporal Action Localization EPIC-KITCHENS-100 TriDet (verb) mAP IOU@0.5 20.8 #2 of 6 Archive leaderboard report
Temporal Action Localization HACS TriDet (SlowFast) Average-mAP 38.6 #8 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (SlowFast) mAP@0.5 56.7 #8 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (SlowFast) mAP@0.75 39.3 #8 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (SlowFast) mAP@0.95 11.7 #8 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (I3D RGB) Average-mAP 36.8 #9 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (I3D RGB) mAP@0.5 54.5 #9 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (I3D RGB) mAP@0.75 36.8 #9 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (I3D RGB) mAP@0.95 11.5 #9 of 12 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (I3D features) Avg mAP (0.3:0.7) 69.3 #9 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (I3D features) mAP IOU@0.3 83.6 #9 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (I3D features) mAP IOU@0.4 80.1 #9 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (I3D features) mAP IOU@0.5 72.9 #9 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (I3D features) mAP IOU@0.6 62.4 #9 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (I3D features) mAP IOU@0.7 47.4 #9 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