Language-Guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 9; pp. 3469 - 3481
• Main Authors: Zhang, Weixia, Ma, Chao, Wu, Qi, Yang, Xiaokang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: adversarial learning; attention mechanism; embodied navigation; Generators; Grounding; Inference; Language instruction; Learning; Navigation; Shortest-path problems; Task analysis; Training; Trajectory; Vision-and-language; Visualization

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the...