Research map / Video / Video-language understanding
Structured Multi-Level Interaction Network for Video Moment Localization via Language Query
Check 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 |
|---|---|---|---|
| Use SMIN instead of LGI | Video moment localization · Charades-STA | R@1, IoU=0.5: 59.46 -> 64.06 | Helped |
| Use SMIN instead of LGI | Video moment localization · Charades-STA | R@1, IoU=0.7: 35.48 -> 40.75 | Helped |
| Use SMIN instead of DPIN | Video moment localization · ActivityNet-Captions | R@1, IoU=0.7: 28.31 -> 30.34 | Helped |
| Use SMIN instead of DPIN | Video moment localization · TACoS | R@1, IoU=0.5: 32.92 -> 35.24 | Helped |
| Add the boundary unit (ablation) | SMIN · Charades-STA | R@1, IoU=0.5: 61.99 -> 64.06 | Helped |
| Add the boundary unit (ablation) | SMIN · Charades-STA | R@1, IoU=0.7: 37.20 -> 40.75 | Helped |
| Add the content unit (ablation) | SMIN · Charades-STA | R@1, IoU=0.5: 62.22 -> 64.06 | Helped |
| Add the content unit (ablation) | SMIN · TACoS | R@1, IoU=0.5: 44.91 -> 48.01 | Helped |
| Add both boundary and content units (ablation) | SMIN · Charades-STA | R@1, IoU=0.5: 58.65 -> 64.06 | Helped |
| Add both boundary and content units (ablation) | SMIN · TACoS | R@1, IoU=0.5: 43.53 -> 48.01 | Helped |
| Add fine-grained vision-language interaction in the boundary unit (ablation) | SMIN boundary unit · Charades-STA | R@1, IoU=0.5: 62.31 -> 64.06 | Helped |
| Add boundary-moment interaction (ablation) | SMIN boundary unit · Charades-STA | R@1, IoU=0.7: 37.87 -> 40.75 | Helped |
Closest papers by meaning
- Transferable Video Moment Localization by Moment-Guided Query Prompting (AAAI 2024 · similarity 0.91)
- Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language (AAAI 2024 · similarity 0.88)
- Boundary-Aware Temporal Dynamic Pseudo-Supervision Pairs Generation for Zero-Shot Natural Language Video Localization (AAAI 2025 · similarity 0.88)
- Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval (AAAI 2024 · similarity 0.87)
- Localizing Events in Videos with Multimodal Queries (CVPR 2025 · similarity 0.87)
- Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models (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.