Research map / Vision-language and multimodal / Robot action and navigation
Language and Visual Entity Relationship Graph for Agent Navigation
Yicong Hong, Cristian Rodriguez, Yuankai Qi, Qi Wu, Stephen Gould
Read the paperCheck 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 |
|---|---|---|---|
| Model scene, object, and direction clues with language and visual relationship graphs | VLN agent · R2R test unseen | SPL: 0.47 -> 0.52 | Improved |
| Model scene, object, and direction clues with language and visual relationship graphs | VLN agent · R4R validation unseen | SDTW: 0.13 -> 0.34 | Improved |
| Add specialized scene, object, and direction clues (ablation) | VLN baseline · R2R validation unseen | SPL: 0.48 -> 0.51 | Improved |
| Add object clues to a graph model with scene and direction clues (ablation) | Model 2 · R2R validation unseen | SPL: 0.50 -> 0.53 | Improved |
| Add scene clues to a graph model with object and direction clues (ablation) | Model 3 · R2R validation unseen | SPL: 0.46 -> 0.53 | Improved |
| Add graph relationship modeling to scene, object, and direction clues (ablation) | Model 4 · R2R validation unseen | SPL: 0.51 -> 0.53 | Improved |
| Add language graph edges when visual graph edges are present (ablation) | Model 5 · R2R validation unseen | SPL: 0.50 -> 0.53 | Improved |
| Add object visual clues (ablation) | Model 2 · R2R validation unseen, instructions with 1 object | success rate: 0.504 -> 0.504 | No clear effect |
| Add object visual clues (ablation) | Model 2 · R2R validation unseen, instructions with 9 objects | success rate: 0.405 -> 0.459 | Improved |
Closest papers by meaning
- Bridging the Visual Semantic Gap in VLN via Semantically Richer Instructions (ECCV 2022 · similarity 0.90)
- Object-and-Action Aware Model for Visual Language Navigation (ECCV 2020 · similarity 0.89)
- Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule (ICLR 2021 · similarity 0.89)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.88)
- WebVLN: Vision-and-Language Navigation on Websites (AAAI 2024 · similarity 0.87)
- Do Visual Imaginations Improve Vision-and-Language Navigation Agents? (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.
