AI Paper Atlas

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

TPAMI 2023 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 61 citations (OpenAlex)

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 changedWhereMeasuredEffect
add the full history-and-order aware pre-training (ablation)HOP baseline · R2R test unseenSPL: 50 -> 59Improved
add MLM-only pre-training (ablation)HOP baseline · R2R val unseenSR: 54.19 -> 60.75Improved
add TIM to MLM (ablation)HOP pre-training · R2R val unseenSPL: 54.81 -> 55.31Improved
add TOM to MLM (ablation)HOP pre-training · REVERIE val unseenRGSPL: 12.48 -> 14.49Improved
add GOM to MLM (ablation)HOP pre-training · REVERIE val unseenRGSPL: 12.48 -> 14.14Improved
add APH to MLM (ablation)HOP pre-training · R2R val unseenSPL: 54.81 -> 56.13Improved
use action prediction with history instead of without history (ablation)MLM + action prediction · R2R val unseenSPL: 55.68 -> 56.13Improved
use action prediction with history instead of without history (ablation)MLM + action prediction · REVERIE val unseenRGSPL: 13.64 -> 14.16Improved
combine TIM, TOM, GOM and APH with MLM (ablation)HOP pre-training · R2R val unseenSPL: 54.81 -> 57.07Improved
combine all tasks instead of baseline (ablation)HOP · NDH val unseengoal progress: 3.38 -> 4.37Improved
add processed BnB data to PREVALENT pre-training data (ablation)HOP · REVERIE val unseenRGSPL: 15.31 -> 15.73Improved
add processed BnB data to PREVALENT pre-training data (ablation)HOP · R2R val unseenSPL: 57.07 -> 57.22No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy