@inproceedings{shin-narihira-2021-transformer, title = "Transformer-Exclusive Cross-Modal Representation for Vision and Language", author = "Shin, Andrew and Narihira, Takuya", editor = "Zong, Chengqing and Xia, Fei and Li, Wenjie and Navigli, Roberto", booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.findings-acl.240/", doi = "10.18653/v1/2021.findings-acl.240", pages = "2719--2725" }