Research map / Vision-language and multimodal / Robot action and navigation
HOP+: History-Enhanced and Order-Aware Pre-Training for Vision-and-Language Navigation
Yanyuan Qiao, Yuankai Qi, Yicong Hong, Zheng Yu, Peng Wang, 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 the full history-and-order aware pre-training (ablation) | HOP baseline · R2R test unseen | SPL: 50 -> 59 | Improved |
| add MLM-only pre-training (ablation) | HOP baseline · R2R val unseen | SR: 54.19 -> 60.75 | Improved |
| add TIM to MLM (ablation) | HOP pre-training · R2R val unseen | SPL: 54.81 -> 55.31 | Improved |
| add TOM to MLM (ablation) | HOP pre-training · REVERIE val unseen | RGSPL: 12.48 -> 14.49 | Improved |
| add GOM to MLM (ablation) | HOP pre-training · REVERIE val unseen | RGSPL: 12.48 -> 14.14 | Improved |
| add APH to MLM (ablation) | HOP pre-training · R2R val unseen | SPL: 54.81 -> 56.13 | Improved |
| use action prediction with history instead of without history (ablation) | MLM + action prediction · R2R val unseen | SPL: 55.68 -> 56.13 | Improved |
| use action prediction with history instead of without history (ablation) | MLM + action prediction · REVERIE val unseen | RGSPL: 13.64 -> 14.16 | Improved |
| combine TIM, TOM, GOM and APH with MLM (ablation) | HOP pre-training · R2R val unseen | SPL: 54.81 -> 57.07 | Improved |
| combine all tasks instead of baseline (ablation) | HOP · NDH val unseen | goal progress: 3.38 -> 4.37 | Improved |
| add processed BnB data to PREVALENT pre-training data (ablation) | HOP · REVERIE val unseen | RGSPL: 15.31 -> 15.73 | Improved |
| add processed BnB data to PREVALENT pre-training data (ablation) | HOP · R2R val unseen | SPL: 57.07 -> 57.22 | No clear effect |
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.
- AirBERT — Airbert: In-Domain Pretraining for Vision-and-Language Navigation (ICCV 2021) · better on 4 of 4 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
- HOP: History-and-Order Aware Pre-Training for Vision-and-Language Navigation (CVPR 2022 · similarity 0.99)
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (CVPR 2020 · similarity 0.90)
- Improving Vision-and-Language Navigation by Generating Future-View Image Semantics (CVPR 2023 · similarity 0.90)
- History Aware Multimodal Transformer for Vision-and-Language Navigation (NeurIPS 2021 · similarity 0.89)
- History to Future: Evolving Agent with Experience and Thought for Zero-shot Vision-and-Language Navigation (CVPR 2026 · similarity 0.89)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.88)
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.
