AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Active Visual Information Gathering for Vision-Language Navigation

Hanqing Wang, Wenguan Wang, Tianmin Shu, Wei Liang, Jianbing Shen

ECCV 2020 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 77 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 naive one-step exploration of all directions (ablation)basic agent · R2R val unseenSR: 0.52 -> 0.54Improved
add naive one-step exploration of all directions (ablation)basic agent · R2R val unseenTL: 10.7 -> 35.7Hurt
add learned exploration decision (explore only some directions) (ablation)naive model · R2R val unseenTL: 35.7 -> 13.7Improved
add learned exploration decision (explore only some directions) (ablation)naive model · R2R val unseenSR: 0.54 -> 0.55Improved
allow multi-step exploration (at most 4 steps) in the naive model (ablation)naive model · R2R val unseenSR: 0.54 -> 0.60Improved
allow multi-step exploration (at most 4 steps) in the naive model (ablation)naive model · R2R val unseenTL: 35.7 -> 58.8Hurt
raise maximum exploration length from 1 to 4 steps (ablation)full model · R2R val unseenSR: 0.55 -> 0.58Improved
raise maximum exploration length from 4 to 6 steps (ablation)full model · R2R val unseenSPL: 0.40 -> 0.38Mixed
add imitation loss on exploration module (ablation)full model · R2R val unseenSR: 0.53 -> 0.58Improved
add reinforcement loss on exploration module (ablation)full model · R2R val unseenSR: 0.55 -> 0.58Improved
add memory-based lazy action-taking strategy (ablation)full model · R2R val unseenTL: 44.5 -> 20.6Improved
add memory-based lazy action-taking strategy (ablation)full model · R2R val unseenSPL: 0.18 -> 0.40Improved

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