Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks

Introduction Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks. CVPR, 2019. 摘要 Vision-Language Navigation(VLN)任务是智能体在自然语言指令下学习如何在环境中进行导航的任务。这个任务的关键在于序列地感知视觉和文本。传统的方法利用跨模态ground

>>阅读原文<<