Papers › Temporal Action Localization with Enhanced Instant Discriminability

Temporal Action Localization with Enhanced Instant Discriminability

11 Sep 2023arXiv:2309.05590archive 2025-07-28

Dingfeng Shi, Qiong Cao, Yujie Zhong, Shan An, Jian Cheng, Haogang Zhu, DaCheng Tao

Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action boundaries by existing methods. To resolve this issue, we propose a one-stage framework named TriDet. First, we propose a Trident-head to model the action boundary via an estimated relative probability distribution around the boundary. Then, we analyze the rank-loss problem (i.e. instant discriminability deterioration) in transformer-based methods and propose an efficient scalable-granularity perception (SGP) layer to mitigate this issue. To further push the limit of instant discriminability in the video backbone, we leverage the strong representation capability of pretrained large models and investigate their performance on TAD. Last, considering the adequate spatial-temporal context for classification, we design a decoupled feature pyramid network with separate feature pyramids to incorporate rich spatial context from the large model for localization. Experimental results demonstrate the robustness of TriDet and its state-of-the-art performance on multiple TAD datasets, including hierarchical (multilabel) TAD datasets.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

dingfengshi/tridetplus officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
dingfengshi/tridet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TriDet: Temporal Action Detection with Relative Boundary Modeling (arXiv:2303.07347; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
sssste/tridet mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action DetectionAction LocalizationTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization HACS TriDet (VideoMAEv2) Average-mAP 43.1 #5 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (VideoMAEv2) mAP@0.5 62.4 #5 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (VideoMAEv2) mAP@0.75 44.1 #5 of 12 Archive leaderboard report
Temporal Action Localization HACS TriDet (VideoMAEv2) mAP@0.95 13.1 #5 of 12 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (VideoMAEv2) Average mAP 37.5 #1 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (VideoMAEv2) mAP IOU@0.2 57.7 #1 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (VideoMAEv2) mAP IOU@0.5 42.7 #1 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (VideoMAEv2) mAP IOU@0.7 24.3 #1 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (I3D-rgb) Average mAP 30.7 #3 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (I3D-rgb) mAP IOU@0.2 49.1 #3 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (I3D-rgb) mAP IOU@0.5 34.3 #3 of 8 Archive leaderboard report
Temporal Action Localization MultiTHUMOS TriDet (I3D-rgb) mAP IOU@0.7 17.8 #3 of 8 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (VideoMAE v2-g feature) Avg mAP (0.3:0.7) 70.1 #6 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (VideoMAE v2-g feature) mAP IOU@0.3 84.8 #6 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (VideoMAE v2-g feature) mAP IOU@0.4 80.0 #6 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (VideoMAE v2-g feature) mAP IOU@0.5 73.3 #6 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (VideoMAE v2-g feature) mAP IOU@0.6 63.8 #6 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 TriDet (VideoMAE v2-g feature) mAP IOU@0.7 48.8 #6 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