CrossMap Transformer：一种用于视觉语言导航的采用双反向翻译的跨模态掩码路径Transformer
CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation
AI总结：
针对视觉语言导航中环境探索与语言-视觉路径对齐的难题，提出CrossMap Transformer网络，结合基于Transformer的指令生成器构建双反向翻译模型，通过共享潜在特征实现双向增强，提升了指令理解与生成效果。
摘要：
由自然语言指令引导的导航特别适合与用户进行自然交互的家庭服务机器人。该任务需要在给定自然语言导航指令的情况下，预测通往指定目的地的动作序列，因此要求理解诸如“走出浴室，在右侧的楼梯处等候”这类指令。视觉语言导航（Visual and Language Navigation）任务至今仍颇具挑战性，主要原因在于它需要探索环境，还需要精准遵循指令指定的路径，以建模语言与视觉之间的关联。为解决这一问题，我们提出CrossMap Transformer网络，该网络对语言特征和视觉特征进行编码，以逐段生成路径。CrossMap Transformer与一个基于Transformer的指令生成器（speaker）绑定，后者负责生成导航指令。两个网络共享共同的潜在特征，通过双反向翻译模型实现相互增强：生成的路径被翻译成指令，同时生成的指令被翻译成路径。实验结果表明，我们的方法在指令理解和指令生成方面均具有优势。
英文摘要：
Navigation guided by natural language instructions is particularly suitable for Domestic Service Robots that interacts naturally with users. This task involves the prediction of a sequence of actions that leads to a specified destination given a natural language navigation instruction. The task thus requires the understanding of instructions, such as ``Walk out of the bathroom and wait on the stairs that are on the right''. The Visual and Language Navigation remains challenging, notably because it requires the exploration of the environment and at the accurate following of a path specified by the instructions to model the relationship between language and vision. To address this, we propose the CrossMap Transformer network, which encodes the linguistic and visual features to sequentially generate a path. The CrossMap transformer is tied to a Transformer-based speaker that generates navigation instructions. The two networks share common latent features, for mutual enhancement through a double back translation model: Generated paths are translated into instructions while generated instructions are translated into path The experimental results show the benefits of our approach in terms of instruction understanding and instruction generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
