Papers › HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation

HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation

24 Aug 2023arXiv:2308.12608archive 2025-07-28

Huaxin Zhang, Xiang Wang, Xiaohao Xu, Zhiwu Qing, Changxin Gao, Nong Sang

Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully supervised methods. Code will be available at https://github.com/pipixin321/HR-Pro.

PaperPDFCode

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

Code

pipixin321/hr-pro 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

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

Tasks

Action LocalizationTemporal Action LocalizationWeakly Supervised Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly Supervised Action Localization BEOID HR-Pro mAP@0.1:0.7 59.4 #1 of 5 Archive leaderboard report
Weakly Supervised Action Localization BEOID HR-Pro mAP@0.5 55.3 #1 of 5 Archive leaderboard report
Weakly Supervised Action Localization GTEA HR-Pro mAP@0.1:0.7 47.3 #2 of 6 Archive leaderboard report
Weakly Supervised Action Localization GTEA HR-Pro mAP@0.5 37.3 #2 of 6 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 HR-Pro mAP@0.1:0.5 71.6 #1 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 HR-Pro mAP@0.1:0.7 60.3 #1 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 HR-Pro mAP@0.5 52.2 #1 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 HR-Pro avg-mAP (0.1-0.5) 71.6 #1 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 HR-Pro avg-mAP (0.1:0.7) 60.3 #1 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 HR-Pro avg-mAP (0.3-0.7) 51.1 #1 of 12 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

Focus

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