MAMO: Fine-Grained Vision-Language Representations Learning with Masked Multimodal Modeling.

@inproceedings{zhao-2023-mamo, author = {Zijia Zhao and Longteng Guo and Xingjian He and Shuai Shao and Zehuan Yuan and Jing Liu}, editor = {Hsin-Hsi Chen and Wei-Jou (Edward) Duh and Hen-Hsen Huang and Makoto P. Kato and Josiane Mothe and Barbara Poblete}, title = {{MAMO: Fine-Grained Vision-Language Representations Learning with Masked Multimodal Modeling}}, booktitle = {{Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023}}, pages = {1528--1538}, publisher = {ACM}, year = {2023}, url = {https://doi.org/10.1145/3539618.3591721}, doi = {https://doi.org/10.1145/3539618.3591721} }