</> Code with Papers by Syntology

Papers › Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to...

Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses

15 Dec 2020arXiv:2012.08236archive 2025-07-28

Chen Ju, Peisen Zhao, Ya zhang, Yanfeng Wang, Qi Tian

Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse single-frame labels. However, such a framework inevitably suffers from a large solution space. This paper attempts to explore the proposal-based prediction paradigm for point-level annotations, which has the advantage of more constrained solution space and consistent predictions among neighboring frames. The point-level annotations are first used as the keypoint supervision to train a keypoint detector. At the location prediction stage, a simple but effective mapper module, which enables back-propagation of training errors, is then introduced to bridge the fully-supervised framework with weak supervision. To our best of knowledge, this is the first work to leverage the fully-supervised paradigm for the point-level setting. Experiments on THUMOS14, BEOID, and GTEA verify the effectiveness of our proposed method both quantitatively and qualitatively, and demonstrate that our method outperforms state-of-the-art methods.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action LocalizationPredictionTemporal Action LocalizationWeakly Supervised Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly Supervised Action Localization BEOID Ju et al. mAP@0.1:0.7 34.9 #3 of 5 Archive leaderboard report
Weakly Supervised Action Localization BEOID Ju et al. mAP@0.5 20.9 #3 of 5 Archive leaderboard report
Weakly Supervised Action Localization GTEA Ju et al. mAP@0.1:0.7 33.7 #5 of 6 Archive leaderboard report
Weakly Supervised Action Localization GTEA Ju et al. mAP@0.5 21.9 #5 of 6 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 Ju et al. mAP@0.1:0.5 55.6 #11 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 Ju et al. mAP@0.1:0.7 44.8 #11 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 Ju et al. mAP@0.5 35.9 #11 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 Ju et al. avg-mAP (0.1-0.5) 55.6 #4 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 Ju et al. avg-mAP (0.1:0.7) 44.8 #4 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS14 Ju et al. avg-mAP (0.3-0.7) 35.4 #4 of 12 Archive leaderboard report
Weakly Supervised Action Localization THUMOS’14 Ju et al. mAP@0.5 35.9 #5 of 13 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