Research map / Vision-language and multimodal / Robot action and navigation
Agent Journey Beyond RGB: Hierarchical Semantic-Spatial Representation Enrichment for Vision-and-Language Navigation
Xuesong Zhang, Yunbo Xu, Jia Li, Ruonan Liu, Zhenzhen Hu
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 depth exploration map with Gibson-pretrained depth encoder (DSP) (ablation) | DUET · REVERIE Val Unseen | SPL (%): 33.7 -> 39.2 | Improved |
| use CLIP instead of ViT RGB features (ablation) | DUET · REVERIE Val Unseen | SPL (%): 33.7 -> 35.7 | Improved |
| use ImageNet-pretrained depth encoder rather than none (ablation) | SUSA DSP · REVERIE Val Unseen | SPL (%): 35.7 -> 34.6 | Hurt |
| pretrain depth encoder on Gibson rather than ImageNet (ablation) | SUSA DSP · REVERIE Val Unseen | SPL (%): 34.6 -> 39.2 | Improved |
| add TSU textual semantic selector (ablation) | DUET · REVERIE Test Unseen | SPL (%): 36.0 -> 40.8 | Improved |
| balance static and dynamic matching at delta 0.5 (ablation) | SUSA TSU · R2R Val Unseen | SPL (%): 63.7 -> 64.8 | Improved |
| use dynamic matching only (delta 1.0) (ablation) | SUSA TSU · REVERIE Val Unseen | SPL (%): 39.2 -> 37.8 | Hurt |
| use learnable adaptive delta (ablation) | SUSA TSU · REVERIE Val Unseen | SPL (%): 39.2 -> 38.2 | Hurt |
| add DSP + TSU without HAP (ablation) | SUSA · REVERIE Test Unseen | SPL (%): val 39.2 -> 39.5; test 39.5 -> 37.8 vs DSP alone | Mixed |
| add HAP contrastive aggregation (ablation) | SUSA · REVERIE Test Unseen | SPL (%): 37.8 -> 41.5 | Improved |
| partial pretraining vs complete pretraining (ablation) | SUSA · REVERIE Val Unseen | SR gap seen-unseen: gap reduced by 5.92% | Improved |
| SUSA vs DUET planner in continuous R2R-CE | ETPNav planner · R2R-CE Test Unseen | SPL (%): 40.5 -> 43.9 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DUET — DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning (AAAI 2023) · better on 11 of 11 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.92)
- Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation (CVPR 2026 · similarity 0.91)
- AgentVLN: Towards Agentic Vision-and-Language Navigation (ECCV 2026 · similarity 0.91)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.89)
- Do Visual Imaginations Improve Vision-and-Language Navigation Agents? (CVPR 2025 · similarity 0.89)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · 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.
