Papers › Weakly Supervised Temporal Action Localization Using Deep Metric Learning
Weakly Supervised Temporal Action Localization Using Deep Metric Learning
Ashraful Islam, Richard J. Radke
Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and time-consuming to annotate both action labels and temporal boundaries of videos. To this end, we propose a weakly supervised temporal action localization method that only requires video-level action instances as supervision during training. We propose a classification module to generate action labels for each segment in the video, and a deep metric learning module to learn the similarity between different action instances. We jointly optimize a balanced binary cross-entropy loss and a metric loss using a standard backpropagation algorithm. Extensive experiments demonstrate the effectiveness of both of these components in temporal localization. We evaluate our algorithm on two challenging untrimmed video datasets: THUMOS14 and ActivityNet1.2. Our approach improves the current state-of-the-art result for THUMOS14 by 6.5% mAP at IoU threshold 0.5, and achieves competitive performance for ActivityNet1.2.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 |
|---|---|---|---|---|---|---|---|
| Temporal Action Localization | ActivityNet-1.2 | DeepMetricLearner | mAP IOU@0.1 | 60.5 | #1 of 1 | Archive leaderboard | report |
| Temporal Action Localization | ActivityNet-1.2 | DeepMetricLearner | mAP IOU@0.3 | 48.4 | #1 of 1 | Archive leaderboard | report |
| Temporal Action Localization | ActivityNet-1.2 | DeepMetricLearner | mAP IOU@0.5 | 35.2 | #1 of 1 | Archive leaderboard | report |
| Temporal Action Localization | ActivityNet-1.2 | DeepMetricLearner | mAP IOU@0.7 | 16.3 | #1 of 1 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | DeepMetricLearner | mAP IOU@0.1 | 62.3 | #33 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | DeepMetricLearner | mAP IOU@0.3 | 46.8 | #33 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | DeepMetricLearner | mAP IOU@0.5 | 29.6 | #33 of 42 | Archive leaderboard | report |
| Temporal Action Localization | THUMOS’14 | DeepMetricLearner | mAP IOU@0.7 | 9.7 | #33 of 42 | 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