Research map / Video / Action recognition
Proposal Score Realignment Guided by Semantic Completeness for Weakly Supervised Temporal Action Localization
Maodong Li, Zhihao Wang, Jingxiong Wang, Jian Wang, Bing Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add semantic-completeness loss L_SC to MIL loss (ablation) | DDG-Net + SCLR · THUMOS14 test | avg mAP@0.1:0.7: 47.0 -> 48.6 | Improved |
| add generic-center loss L_G (ablation) | MIL+SC · THUMOS14 test | avg mAP@0.1:0.7: 48.6 -> 49.5 | Improved |
| add specific-center loss L_S alone (ablation) | MIL+SC · THUMOS14 test | avg mAP@0.1:0.7: 48.6 -> 48.6 | No clear effect |
| add decorrelation loss L_perp to L_G+L_S (ablation) | SCLR · THUMOS14 test | avg mAP@0.1:0.7: 49.4 -> 50.4 | Improved |
| add SCLR realignment for pseudo-label training (ablation) | localization head · THUMOS14 test | avg mAP@0.1:0.7: 49.1 -> 53.2 | Improved |
| use SCLR alone over baseline (ablation) | DDG-Net · THUMOS14 test | avg mAP@0.1:0.7: 47.3 -> 50.4 | Improved |
| add phi_S(CSE) specific component (ablation) | class-center reconstruction · THUMOS14 test | avg mAP@0.1:0.7: 48.7 -> 50.4 | Improved |
| add EMA on generic component (ablation) | class-center reconstruction · THUMOS14 test | avg mAP@0.1:0.7: 49.7 -> 50.4 | Improved |
| add balancing coefficient delta (ablation) | class-center reconstruction · THUMOS14 test | avg mAP@0.1:0.7: 49.7 -> 50.4 | Improved |
| use discrete argmax(J) anchor instead of Soft-argmax(J) (ablation) | SCLR · THUMOS14 test | avg mAP@0.1:0.7: 49.0 -> 50.4 | Improved |
| use joint anchor instead of Top-A (ablation) | SCLR · THUMOS14 test | avg mAP@0.1:0.7: 47.9 -> 50.4 | Improved |
| add k_cen and k_time cues in fusion weights (ablation) | SCLR · THUMOS14 test | avg mAP@0.1:0.7: 49.2 -> 50.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DDG-Net — DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization (ICCV 2023) · better on 3 of 3 shared results
- PivoTAL — PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization (CVPR 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer (CVPR 2025 · similarity 0.91)
- Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization (CVPR 2024 · similarity 0.89)
- HR-Pro: Point-Supervised Temporal Action Localization via Hierarchical Reliability Propagation (AAAI 2024 · similarity 0.89)
- Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction (AAAI 2025 · similarity 0.89)
- HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding (NeurIPS 2026 · similarity 0.88)
- Similar Modality Enhancement and Action Consistency Learning for Weakly Supervised Temporal Action Localization (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
