Research map / Vision-language and multimodal / Human and embodied modeling
Graph-Structured Referring Expression Reasoning in the Wild
Sibei Yang, Guanbin Li, Yizhou Yu
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 graph-guided modular reasoning | SGMN · Ref-Reasoning test | accuracy: 49.51 -> 51.39 | Improved |
| Use graph-guided modular reasoning | SGMN* · RefCOCO testA | accuracy: 85.63 -> 86.67 | Improved |
| Use graph-guided modular reasoning | SGMN* · RefCOCO testB | accuracy: 85.08 -> 85.36 | Improved |
| Use graph-guided modular reasoning | SGMN* · RefCOCO+ testA | accuracy: 75.74 -> 78.66 | Improved |
| Use graph-guided modular reasoning | SGMN* · RefCOCO+ testB | accuracy: 67.62 -> 69.77 | Improved |
| Use graph-guided modular reasoning | SGMN* · RefCOCOg test | accuracy: 78.21 -> 81.42 | Improved |
| Add the Transfer module (ablation) | SGMN · Ref-Reasoning test | accuracy: 41.88 -> 51.39 | Improved |
| Add the Norm module (ablation) | SGMN · Ref-Reasoning test | accuracy: 41.93 -> 51.39 | Improved |
| Replace max-merge with sum-merge (ablation) | SGMN · Ref-Reasoning test | accuracy: 45.27 -> 51.39 | Improved |
| Replace min-merge with sum-merge (ablation) | SGMN · Ref-Reasoning test | accuracy: 46.00 -> 51.39 | Improved |
Closest papers by meaning
- Dynamic Graph Attention for Referring Expression Comprehension (ICCV 2019 · similarity 0.94)
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.90)
- Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.89)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.88)
- Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models (ICML 2026 · similarity 0.88)
- Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation (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.
