28Xiujun LiXi YinChunyuan LiPengchuan ZhangXiaowei HuLei ZhangLijuan WangHoudong HuLi DongFuru Wei等。Oscar：用于视觉语言任务的对象-语义对齐预训练。在ECCV2020年。329Tsung-Yi LinMichael MaireSerge BelongieJames HaysPietro Pero

[28] Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. Oscar: Object-Semantic Alignment for Vision-Language Tasks. In ECCV, 2020. [29] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C Lawrence Zitnick. Microsoft COCO: Common Objects in Context. In ECCV, 2014. [30] Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. Vilbert: Task-Agnostic Visual Language Representations for Vision-Language Tasks. NeurIPS, 2019. Nicole Meister, Dora Zhao, Angelina Wang, Vikram V Ramaswamy, Ruth Fong, and Olga Russakovsky. Gender Bias in Visual Datasets. arXiv preprint arXiv:2206.09191, 2022.