Research map / Vision-language and multimodal / Human and embodied modeling
Generating Descriptions With Grounded and Co-Referenced People
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 |
|---|---|---|---|
| add grounding and co-reference supervision (ablation) | Our · MPII-MD test, manual labeled subset | F1 Grounding + Co-Reference + word: 13.47 -> 49.55 | Helped |
| add grounding and co-reference supervision (ablation) | Our · MPII-MD Co-ref+Gender test, with previous clip character grounding | CIDEr: 10.48 -> 11.70 | Helped |
| add activity body-context features (ablation) | Our · MPII-MD Co-ref+Gender test, with previous clip character grounding | CIDEr: 11.70 -> 12.64 | Helped |
| add activity body-context features (ablation) | Our · MPII-MD test, automatic ground truth full set | F1 Grounding + Co-Reference + word: 33.88 -> 37.23 | Helped |
| add ResNet body-context features (ablation) | Our · MPII-MD test, automatic ground truth full set | F1 Grounding + Co-Reference + word: 33.88 -> 37.92 | Helped |
| add statistic features (ablation) | Our · MPII-MD test, automatic ground truth full set | F1 Grounding + Co-Reference + word: 32.87 -> 33.88 | Helped |
| add statistic features (ablation) | Our · MPII-MD Co-ref+Gender test, with previous clip character grounding | CIDEr: 11.65 -> 11.70 | No clear effect |
| remove attention and co-reference (ablation) | Our + Activity · MPII-MD Co-ref+Gender test, without previous clip character grounding | human judgment: 15.0 -> 11.0 | Hurt |
| use automatically grounded previous-clip characters instead of the no-grounding setup | Our + Activity · MPII-MD Co-ref+Gender test | human judgment: 15.0 -> 14.5 | Mixed |
Closest papers by meaning
- Comprehensive Visual Grounding for Video Description (AAAI 2024 · similarity 0.86)
- Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding (CVPR 2025 · similarity 0.86)
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 2024 · similarity 0.86)
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.86)
- Improved Visual Grounding through Self-Consistent Explanations (CVPR 2024 · similarity 0.86)
- VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding (CVPR 2024 · similarity 0.85)
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.