Research map / Vision-language and multimodal / Robot action and navigation
The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Yuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang, 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 sequential connection between steps to BERT (ablation) | UNITER-initialised BERT · NDH val unseen | GP (m): 2.42 -> 2.86 | Improved |
| add sequential connection between steps to BERT (ablation) | UNITER-initialised BERT · REVERIE val unseen | SPL: 7.7 -> 13.3 | Improved |
| add sequential connection between steps (ablation) | BERT · NDH val seen | GP (m): 4.00 -> 3.80 | Hurt |
| add direction loss (ablation) | ORIST · NDH val unseen | GP (m): 2.86 -> 3.09 | Improved |
| add direction loss (ablation) | ORIST · REVERIE val unseen | SPL: 13.3 -> 16.9 | Improved |
| add next-room type loss (ablation) | ORIST · REVERIE val unseen | SPL: 16.9 -> 14.9 | Hurt |
| add next-room type loss (ablation) | ORIST · NDH val unseen | GP (m): 3.09 -> 3.15 | Improved |
| add goal room-type loss (ablation) | ORIST · NDH val unseen | GP (m): 3.15 -> 3.30 | Improved |
| add both room-type losses (ablation) | ORIST · REVERIE val seen | SPL: 39.5 -> 42.2 | Improved |
| add goal room-type loss (ablation) | ORIST · REVERIE val unseen | SPL: 14.9 -> 15.1 | No clear effect |
Closest papers by meaning
- SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation (NeurIPS 2021 · similarity 0.90)
- Improving Vision-and-Language Navigation with Image-Text Pairs from the Web (ECCV 2020 · similarity 0.89)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.89)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.87)
- Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation (NeurIPS 2025 · similarity 0.87)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 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.
