Research map / Vision-language and multimodal / Human and embodied modeling
Natural Language Object Retrieval
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 spatial configuration (ablation) | SCRC · ReferIt annotated regions | P@1: 64.09% -> 70.15% | Helped |
| Add global scene context (ablation) | SCRC · ReferIt annotated regions | P@1: 70.15% -> 72.74% | Helped |
| Pretrain on image captioning before retrieval fine-tuning (ablation) | SCRC · ReferIt annotated regions | P@1: 61.03% -> 64.09% | Helped |
| Add spatial configuration (ablation) | SCRC · ReferIt, 100 EdgeBox proposals | R@1: 15.78% -> 17.68% | Helped |
| Add spatial configuration (ablation) | SCRC · ReferIt, 100 EdgeBox proposals | R@10: 42.54% -> 44.77% | Helped |
| Add global scene context (ablation) | SCRC · ReferIt, 100 EdgeBox proposals | R@1: 17.68% -> 17.93% | Helped |
| Add global scene context (ablation) | SCRC · ReferIt, 100 EdgeBox proposals | R@10: 44.77% -> 45.27% | Helped |
| Pretrain on image captioning before retrieval fine-tuning (ablation) | SCRC · ReferIt, 100 EdgeBox proposals | R@1: 14.53% -> 15.78% | Helped |
| Pretrain on image captioning before retrieval fine-tuning (ablation) | SCRC · ReferIt, 100 EdgeBox proposals | R@10: 40.72% -> 42.54% | Helped |
| Pretrain on image captioning before retrieval fine-tuning (ablation) | SCRC · Kitchen | P@1: 54.02% -> 61.62% | Helped |
| Pretrain on image captioning before retrieval fine-tuning (ablation) | SCRC · ImageNet distractors | P@1: 74.08% -> 81.15% | Helped |
Closest papers by meaning
- SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval (ICML 2025 · similarity 0.87)
- Continual Vision-Language Retrieval via Dynamic Knowledge Rectification (AAAI 2024 · similarity 0.87)
- Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding (NeurIPS 2026 · similarity 0.86)
- EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension (CVPR 2024 · similarity 0.86)
- INQUIRE: A Natural World Text-to-Image Retrieval Benchmark (NeurIPS 2024 · similarity 0.86)
- Grounding Everything: Emerging Localization Properties in Vision-Language Transformers (CVPR 2024 · similarity 0.86)
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.