@inproceedings{sun-etal-2023-unifine, title = "{U}ni{F}ine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding", author = "Sun, Rui and Wang, Zhecan and You, Haoxuan and Codella, Noel and Chang, Kai-Wei and Chang, Shih-Fu", editor = "Rogers, Anna and Boyd-Graber, Jordan and Okazaki, Naoaki", booktitle = "Findings of the Association for Computational Linguistics: ACL 2023", month = jul, year = "2023", address = "Toronto, Canada", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-acl.49/", doi = "10.18653/v1/2023.findings-acl.49", pages = "778--793" }