Research map / Video / Video-language understanding
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos
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 |
|---|---|---|---|
| Add reference-aware grounding and reference-based relaxation (full RA-MIL rather than DVSA) | Weakly supervised visual grounding · YouCookII | Top-1 accuracy: 20.7% -> 26.7% | Helped |
| Add reference-based relaxation in negative selection (ablation) | RA-MIL visual grounding · YouCookII YC-All | Top-1 accuracy: 25.2% -> 26.7% | Helped |
| Add reference-aware grounding and reference-based relaxation (full RA-MIL rather than DVSA) | Weakly supervised visual grounding · RoboWatch | Top-1 accuracy: 17.5% -> 19.8% | Helped |
| Add reference-based relaxation in negative selection (ablation) | RA-MIL visual grounding · RoboWatch RW-All | Top-1 accuracy: 18.0% -> 19.8% | Helped |
| Add reference-based relaxation in negative selection (ablation) | RA-MIL visual grounding · RoboWatch RW-Misc | Top-1 accuracy: 10.4% -> 14.3% | Helped |
| Use the full RA-MIL approach rather than its no-relaxation variant (ablation) | Visual grounding · RoboWatch RW-Cook | Top-1 accuracy: 23.8% -> 26.8% | Helped |
Closest papers by meaning
- Comprehensive Visual Grounding for Video Description (AAAI 2024 · similarity 0.90)
- Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Gronding (AAAI 2024 · similarity 0.89)
- VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding (CVPR 2024 · similarity 0.88)
- VideoGEM: Training-free Action Grounding in Videos (CVPR 2025 · similarity 0.88)
- Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding (AAAI 2024 · similarity 0.88)
- What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions (CVPR 2024 · similarity 0.88)
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.