Research map / Vision-language and multimodal / Robot action and navigation
Object-and-Action Aware Model for Visual Language Navigation
Yuankai Qi, Zizheng Pan, Shengping Zhang, Anton van den Hengel, Qi Wu
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 |
|---|---|---|---|
| add OAAM to the baseline (ablation) | EnvDrop baseline · R2R Val Seen | SPL: 0.60 -> 0.62 | Improved |
| add nearest point loss (NPL) to the baseline (ablation) | EnvDrop baseline · R2R Val Seen | SPL: 0.60 -> 0.66 | Improved |
| add OAAM to the baseline (ablation) | EnvDrop baseline · R2R Val Unseen | SR: 0.50 -> 0.51 | Improved |
| add OAAM to the baseline (ablation) | EnvDrop baseline · R2R Val Unseen | SPL: 0.47 -> 0.47 | No clear effect |
| add NPL alone to the baseline (ablation) | EnvDrop baseline · R2R Val Unseen | SR: 0.50 -> 0.48 | Hurt |
| add NPL alone to the baseline (ablation) | EnvDrop baseline · R2R Val Unseen | SPL: 0.47 -> 0.45 | Hurt |
| add NPL on top of OAAM (ablation) | OAAM · R2R Val Unseen | SR: 0.51 -> 0.54 | Improved |
| add NPL on top of OAAM (ablation) | OAAM · R2R Val Unseen | SPL: 0.47 -> 0.50 | Improved |
| add OAAM and NPL together to the baseline (ablation) | EnvDrop baseline · R2R Val Unseen | SPL: 0.47 -> 0.50 | Improved |
| add action-aware module to object-aware module (vs OA alone) (ablation) | OAAM · R2R Val Unseen | SPL: 0.40 -> 0.50 | Improved |
| add object-aware module to action-aware module (vs AA alone) (ablation) | OAAM · R2R Val Unseen | SPL: 0.22 -> 0.50 | Improved |
| add OAAM and NPL to the baseline on R4R (ablation) | EnvDrop baseline · R4R Val Unseen | CLS: 0.34 -> 0.40 | Improved |
Closest papers by meaning
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (CVPR 2020 · similarity 0.91)
- Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation (AAAI 2023 · similarity 0.91)
- AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation (CVPR 2026 · similarity 0.91)
- CoT-VLNBench: A Benchmark for Visual Chain-of-Thought Reasoning in Vision-Language-Navigation Robots (AAAI 2026 · similarity 0.90)
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.90)
- OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction (ICML 2025 · similarity 0.89)
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.
