Papers › Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
Daochang Liu, Tingting Jiang, Yizhou Wang
Temporal action localization is crucial for understanding untrimmed videos. In this work, we first identify two underexplored problems posed by the weak supervision for temporal action localization, namely action completeness modeling and action-context separation. Then by presenting a novel network architecture and its training strategy, the two problems are explicitly looked into. Specifically, to model the completeness of actions, we propose a multi-branch neural network in which branches are enforced to discover distinctive action parts. Complete actions can be therefore localized by fusing activations from different branches. And to separate action instances from their surrounding context, we generate hard negative data for training using the prior that motionless video clips are unlikely to be actions. Experiments performed on datasets THUMOS'14 and ActivityNet show that our framework outperforms state-of-the-art methods. In particular, the average mAP on ActivityNet v1.2 is significantly improved from 18.0% to 22.4%. Our code will be released soon.
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 | CMCS | mAP@0.5 | 36.8 | #17 of 19 | Archive leaderboard | report |
| Weakly Supervised Action Localization | ActivityNet-1.3 | CMCS | mAP@0.5:0.95 | 21.2 | #14 of 17 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | CMCS | mAP@0.1:0.7 | 32.4 | #20 of 30 | Archive leaderboard | report |
| Weakly Supervised Action Localization | THUMOS 2014 | CMCS | mAP@0.5 | 23.1 | #20 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