@inproceedings{yu-etal-2019-see, title = "What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues", author = "Yu, Xintong and Zhang, Hongming and Song, Yangqiu and Song, Yan and Zhang, Changshui", 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://preview.aclanthology.org/fix-sig-urls/D19-1516/", doi = "10.18653/v1/D19-1516", pages = "5123--5132" }