Research map / Vision-language and multimodal / Human and embodied modeling
Cross-Modal Relationship Inference for Grounding Referring Expressions
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 CMRIN rather than MAttNet with ResNet-101 features | Grounding referring expressions · RefCOCO | Precision@1: 85.65 -> 86.99; 85.26 -> 87.63; 84.57 -> 84.73 | Helped |
| Use CMRIN rather than MAttNet with ResNet-101 features | Grounding referring expressions · RefCOCO+ | Precision@1: 71.01 -> 75.52; 75.13 -> 80.93; 66.17 -> 68.99 | Helped |
| Use CMRIN rather than MAttNet with ResNet-101 features | Grounding referring expressions · RefCOCOg | Precision@1: 78.10 -> 80.45; 78.12 -> 80.66 | Helped |
| Replace instance-level visual features and global language context with CMRIN's multimodal contexts (ablation) | CMRIN · RefCOCO val | Precision@1: 79.05 -> 86.99 | Helped |
| Replace instance-level visual features and global language context with CMRIN's multimodal contexts (ablation) | CMRIN · RefCOCO+ val | Precision@1: 63.85 -> 75.52 | Helped |
| Replace instance-level visual features and global language context with CMRIN's multimodal contexts (ablation) | CMRIN · RefCOCOg val | Precision@1: 70.78 -> 80.45 | Helped |
| Use global visual context rather than language-guided visual context (ablation) | CMRIN · RefCOCO val | Precision@1: 86.99 -> 82.61 | Hurt |
| Use global visual context rather than language-guided visual context (ablation) | CMRIN · RefCOCO+ val | Precision@1: 75.52 -> 67.75 | Hurt |
| Use global visual context rather than language-guided visual context (ablation) | CMRIN · RefCOCOg val | Precision@1: 80.45 -> 74.29 | Hurt |
| Omit fusion of each vertex's language context into the graph (ablation) | CMRIN · RefCOCO val | Precision@1: 86.99 -> 85.29 | Hurt |
| Omit fusion of each vertex's language context into the graph (ablation) | CMRIN · RefCOCO+ val | Precision@1: 75.52 -> 73.70 | Hurt |
| Omit fusion of each vertex's language context into the graph (ablation) | CMRIN · RefCOCOg val | Precision@1: 80.45 -> 78.47 | Hurt |
Closest papers by meaning
- Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension (AAAI 2025 · similarity 0.88)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.88)
- Remodeling Semantic Relationships in Vision-Language Fine-Tuning (AAAI 2026 · similarity 0.87)
- Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions (CVPR 2024 · similarity 0.87)
- Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point (AAAI 2024 · similarity 0.87)
- Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding (CVPR 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.