Papers › Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal...
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization
Zhilin Li, Zilei Wang, Qinying Liu
Weakly-supervised temporal action localization (WTAL) aims to detect action instances given only video-level labels. To address the challenge, recent methods commonly employ a two-branch framework, consisting of a class-aware branch and a class-agnostic branch. In principle, the two branches are supposed to produce the same actionness activation. However, we observe that there are actually many inconsistent activation regions. These inconsistent regions usually contain some challenging segments whose semantic information (action or background) is ambiguous. In this work, we propose a novel Actionness Inconsistency-guided Contrastive Learning (AICL) method which utilizes the consistent segments to boost the representation learning of the inconsistent segments. Specifically, we first define the consistent and inconsistent segments by comparing the predictions of two branches and then construct positive and negative pairs between consistent segments and inconsistent segments for contrastive learning. In addition, to avoid the trivial case where there is no consistent sample, we introduce an action consistency constraint to control the difference between the two branches. We conduct extensive experiments on THUMOS14, ActivityNet v1.2, and ActivityNet v1.3 datasets, and the results show the effectiveness of AICL with state-of-the-art performance. Our code is available at https://github.com/lizhilin-ustc/AAAI2023-AICL.
Code
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
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 | AICL | Mean mAP | 29.9 | #2 of 19 | Archive leaderboard | report |
| Weakly Supervised Action Localization | ActivityNet-1.2 | AICL | mAP@0.5 | 49.6 | #2 of 19 | Archive leaderboard | report |
| Weakly Supervised Action Localization | ActivityNet-1.3 | AICL | mAP@0.5 | 44.2 | #3 of 17 | Archive leaderboard | report |
| Weakly Supervised Action Localization | ActivityNet-1.3 | AICL | mAP@0.5:0.95 | 27.6 | #3 of 17 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | AICL | mAP@0.1:0.5 | 56.9 | #8 of 30 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | AICL | mAP@0.1:0.7 | 46.4 | #8 of 30 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | AICL | mAP@0.5 | 36.9 | #8 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