Papers › Temporal Structure Mining for Weakly Supervised Action Detection
Temporal Structure Mining for Weakly Supervised Action Detection
Tan Yu, Zhou Ren, Yuncheng Li, Enxu Yan, Ning Xu, Junsong Yuan
Different from the fully-supervised action detection problem that is dependent on expensive frame-level annotations, weakly supervised action detection (WSAD) only needs video-level annotations, making it more practical for real-world applications. Existing WSAD methods detect action instances by scoring each video segment (a stack of frames) individually. Most of them fail to model the temporal relations among video segments and cannot effectively characterize action instances possessing latent temporal structure. To alleviate this problem in WSAD, we propose the temporal structure mining (TSM) approach. In TSM, each action instance is modeled as a multi-phase process and phase evolving within an action instance, i.e., the temporal structure, is exploited. Meanwhile, the video background is modeled by a background phase, which separates different action instances in an untrimmed video. In this framework, phase filters are used to calculate the confidence scores of the presence of an action's phases in each segment. Since in the WSAD task, frame-level annotations are not available and thus phase filters cannot be trained directly. To tackle the challenge, we treat each segment's phase as a hidden variable. We use segments' confidence scores from each phase filter to construct a table and determine hidden variables, i.e., phases of segments, by a maximal circulant path discovery along the table. Experiments conducted on three benchmark datasets demonstrate the state-of-the-art performance of the proposed TSM.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Weakly Supervised Action Localization | ActivityNet-1.2 | TSM | mAP@0.5 | 28.3 | #18 of 19 | Archive leaderboard | report |
| Weakly Supervised Action Localization | ActivityNet-1.3 | TSM | mAP@0.5 | 30.3 | #16 of 17 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | TSM | mAP@0.1:0.7 | - | #25 of 30 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | TSM | mAP@0.5 | 24.5 | #25 of 30 | 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