Papers › Two-Stream Networks for Weakly-Supervised Temporal Action Localization With...
Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms
Yu Wang, Yadong Li, Hongbin Wang
Weakly-supervised temporal action localization aims to detect action boundaries in untrimmed videos with only video-level annotations. Most existing schemes detect temporal regions that are most responsive to video-level classification, but they overlook the semantic consistency between frames. In this paper, we hypothesize that snippets with similar representations should be considered as the same action class despite the absence of supervision signals on each snippet. To this end, we devise a learnable dictionary where entries are the class centroids of the corresponding action categories. The representations of snippets identified as the same action category are induced to be close to the same class centroid, which guides the network to perceive the semantics of frames and avoid unreasonable localization. Besides, we propose a two-stream framework that integrates the attention mechanism and the multiple-instance learning strategy to extract fine-grained clues and salient features respectively. Their complementarity enables the model to refine temporal boundaries. Finally, the developed model is validated on the publicly available THUMOS-14 and ActivityNet-1.3 datasets, where substantial experiments and analyses demonstrate that our model achieves remarkable advances over existing methods.
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-1.3 | TSN | mAP@0.5 | 41.8 | #6 of 17 | Archive leaderboard | report |
| Weakly Supervised Action Localization | ActivityNet-1.3 | TSN | mAP@0.5:0.95 | 26.3 | #6 of 17 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | TSN | mAP@0.1:0.5 | 57.2 | #9 of 30 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | TSN | mAP@0.1:0.7 | 46.2 | #9 of 30 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | TSN | mAP@0.5 | 37.1 | #9 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