
The authors propose a Dual-Level Alignment (DELAN) framework that utilizes cross-modal contrastive learning to align various navigation-related modalities, including instruction, observation, and navigation history, before the fusion stage in order to enhance cross-modal interaction and action decision-making.


coremsg

dual-level-alignment-for-vision-and-language-navigation-via-cross-modal-contrastive-learning


Dual-Level Alignment for Vision-and-Language Navigation via Cross-Modal Contrastive Learning


title_rewrite


Using language as a perceptual representation can improve performance in low-data vision-and-language navigation settings compared to using continuous visual features alone.


language-as-a-perceptual-representation-for-efficient-vision-and-language-navigation


Language as a Perceptual Representation for Efficient Vision-and-Language Navigation
