@inproceedings{jin-etal-2019-video, title = "Video Dialog via Progressive Inference and Cross-Transformer", author = "Jin, Weike and Zhao, Zhou and Gu, Mao and Xiao, Jun and Wei, Furu and Zhuang, Yueting", editor = "Inui, Kentaro and Jiang, Jing and Ng, Vincent and Wan, Xiaojun", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)", month = nov, year = "2019", address = "Hong Kong, China", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/D19-1217/", doi = "10.18653/v1/D19-1217", pages = "2109--2118" }