Vision-Dialog Navigation by Exploring Cross-modal Memory
CVPR(2020)
摘要
Vision-dialog navigation posed as a new holy-grail task in vision-language disciplinary targets at learning an agent endowed with the capability of constant conversation for help with natural language and navigating according to human responses. Besides the common challenges faced in visual language navigation, vision-dialog navigation also requires to handle well with the language intentions of a series of questions about the temporal context from dialogue history and co-reasoning both dialogs and visual scenes. In this paper, we propose the Cross-modal Memory Network (CMN) for remembering and understanding the rich information relevant to historical navigation actions. Our CMN consists of two memory modules, the language memory module (L-mem) and the visual memory module (V-mem). Specifically, L-mem learns latent relationships between the current language interaction and a dialog history by employing a multi-head attention mechanism. V-mem learns to associate the current visual views and the cross-modal memory about the previous navigation actions. The cross-modal memory is generated via a vision-to-language attention and a language-to-vision attention. Benefiting from the collaborative learning of the L-mem and the V-mem, our CMN is able to explore the memory about the decision making of historical navigation actions which is for the current step. Experiments on the CVDN dataset show that our CMN outperforms the previous state-of-the-art model by a significant margin on both seen and unseen environments.
更多查看译文
关键词
vision-dialog navigation,vision-language disciplinary targets,natural language,navigating according,visual language navigation,language intentions,dialogue history,co-reasoning both dialogs,visual scenes,cross-modal memory network,CMN,historical navigation actions,memory modules,language memory module,visual memory module,current language interaction,dialog history,previous navigation actions,vision-to-language attention,language-to-vision attention
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络