Research map / Video / Action recognition
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
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 |
|---|---|---|---|
| Directly classify candidate proposals instead of scoring them with S-MIL (ablation) | P-MIL · THUMOS14 test | AVG mAP: +2.9% | Helped |
| Add background proposals during training (ablation) | P-MIL · THUMOS14 test | AVG mAP: 41.2% -> 46.5% | Helped |
| Add boundary extension and surrounding contrastive feature extraction (ablation) | P-MIL · THUMOS14 test | AVG mAP: 41.0% -> 46.5% | Helped |
| Extend proposal boundaries and concatenate left, inner, and right region features (ablation) | P-MIL · THUMOS14 test | AVG mAP: +0.9% | Helped |
| Add Proposal Completeness Evaluation (ablation) | P-MIL · THUMOS14 test | AVG mAP: +0.7% | Helped |
| Add Instance-level Rank Consistency loss (ablation) | P-MIL · THUMOS14 test | AVG mAP: +0.8% | Helped |
| Add PCE and IRC together (ablation) | P-MIL · THUMOS14 test | AVG mAP: +1.3% | Helped |
| Fuse P-MIL and S-MIL detection results (ablation) | P-MIL · THUMOS14 test | AVG mAP: 46.5% -> 47.0% | Helped |
Closest papers by meaning
- ASM-Loc: Action-Aware Segment Modeling for Weakly-Supervised Temporal Action Localization (CVPR 2022 · similarity 0.92)
- A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization (AAAI 2021 · similarity 0.91)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (AAAI 2024 · similarity 0.90)
- Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization (CVPR 2024 · similarity 0.89)
- Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer (CVPR 2025 · 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)
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.