AI Paper Atlas

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

Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory

Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool

IJCV 2020 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 68 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 explicit top-view memory image instead of no memory (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 6.87 -> 11.92Improved
add top-view memory image instead of GPS coordinate sequence (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 9.04 -> 11.92Improved
add GPS coordinate memory instead of no memory (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 6.87 -> 9.04Improved
use ResNet features instead of pretrained SphereNet (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 9.37 -> 11.92Improved
add Indicator Controller (ACT) instead of no IC (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 9.71 -> 11.92Improved
use ACT instead of regular LSTM in the IC (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 8.95 -> 11.92Improved
use generative matching instead of discriminative matching (ablation)Talk2Nav agent · Talk2Nav (test)SPL (%): 11.15 -> 11.92Improved
train with routes of all difficulty levels instead of 4-landmark routes only (ablation)Talk2Nav agent · Talk2Nav (All landmark counts)SPL (%): 49.93 -> 51.37Improved
train on 3-landmark routes instead of 4-landmark routes, test on 4 landmarks (ablation)Talk2Nav agent · Talk2Nav (4 landmark routes)SPL (%): 11.92 -> 11.51Hurt
train on 1-landmark routes instead of 4-landmark, test on 4 landmarks (ablation)Talk2Nav agent · Talk2Nav (4 landmark routes)SPL (%): 11.92 -> 8.45Hurt
Ours method vs best baseline Self-MonitoringTalk2Nav agent · Talk2Nav (test)SPL (%): 9.56 -> 11.92Improved
Ours method vs best baseline Self-MonitoringTalk2Nav agent · Talk2Nav (test)Navigation Error (m): 740.12 -> 633.85Improved

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