Research map / Video / Action recognition
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Fuse softmax scores with feature-magnitude uncertainty (ablation) | Classification-only baseline · THUMOS'14 | mAP@AVG: 22.6 -> 32.5 | Helped |
| Add uncertainty modeling loss to the fused-score baseline (ablation) | Weakly supervised temporal action localization model · THUMOS'14 | mAP@AVG: 32.5 -> 40.2 | Helped |
| Add background entropy loss to uncertainty modeling (ablation) | Weakly supervised temporal action localization model · THUMOS'14 | mAP@AVG: 40.2 -> 41.9 | Helped |
| Use a too-small maximum feature magnitude m=10 instead of m=100 (ablation) | Uncertainty modeling · THUMOS'14 | mAP@AVG: 41.9 -> 39.6 | Hurt |
| Vary maximum feature magnitude among sufficiently large values (ablation) | Uncertainty modeling · THUMOS'14 | mAP@AVG: 41.8, 41.9, 41.7, 41.9, 41.6 | No clear effect |
Closest papers by meaning
- Weakly-Supervised Action Localization by Generative Attention Modeling (CVPR 2020 · similarity 0.92)
- PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization (CVPR 2023 · similarity 0.91)
- Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection (CVPR 2021 · similarity 0.91)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.90)
- Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer (CVPR 2025 · similarity 0.90)
- Similar Modality Enhancement and Action Consistency Learning for Weakly Supervised Temporal Action Localization (AAAI 2025 · similarity 0.90)
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.