【VLN学习内容LIST】

一，已完成

---

综述

Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions

任务提出论文

方法提出论文

Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation

英文表达积累

相关知识学习总结

---

二，待完成

任务提出论文

R2R
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments

CVDN 视觉对话导航，一个更细分的方向
Vision-and-dialog navigation

REVERIE
Reverie: Remote embodied visual referring expression in real indoor environments

方法提出论文

数据增强
Amin Parvaneh, Ehsan Abbasnejad, Damien Teney, Qin- feng Shi, and Anton van den Hengel. 2020. Counter- factual vision-and-language navigation: Unravelling the unseen. In NeurIPS

Chong Liu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang, Zongyuan Ge, and Yi-Dong Shen. 2021. Vision-language navigation with random environmental mixup. In Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision (ICCV), pages 1644–1654.

先验探索
Xin Wang, Qiuyuan Huang, Asli Celikyilmaz, Jian feng Gao, Dinghan Shen, Y uan-Fang Wang, William Wang, and Lei Zhang. 2019. Reinforced cross-modal matching and self-supervised imitation learning for vision-language navigation. In CVPR

Xinzhe Zhou, Wei Liu, and Y adong Mu. 2021. Rethinking the spatial route prior in vision-and-language navigation.

探索与开发权衡
Jing Y u Koh, Honglak Lee, Yinfei Yang, Jason Baldridge, and Peter Anderson. 2021. Pathdreamer: A world model for indoor navigation. In ICCV, pages 14738–14748.

强化学习
Keji He, Yan Huang, Qi Wu, Jianhua Yang, Dong An, Shuanglin Sima, and Liang Wang. 2021. Landmark- rxr: Solving vision-and-language navigation with fine-grained alignment supervision. In NeurIPS.

辅助学习
Fengda Zhu, Yi Zhu, Xiaojun Chang, and Xiaodan Liang. 2020a. Vision-language navigation with self- supervised auxiliary reasoning tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Haoshuo Huang, Vihan Jain, Harsh Mehta, Alexander Ku, Gabriel Magalhaes, Jason Baldridge, and Eu- gene Ie. 2019. Transferable representation learning in vision-and-language navigation. In ICCV

记忆增强
Shizhe Chen, Pierre-Louis Guhur, Cordelia Schmid, and Ivan Laptev. 2021b. History aware multimodal trans- former for vision-and-language navigation. arXiv preprint arXiv:2110.13309（重点读）利用了完整的导航历史进行决策