Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, Yonghui Wu. CoCa: Contrastive Captioners are Image-Text Foundation Models. Trans. Mach. Learn. Res., 2022, 2022. [doi]
@article{YuWVYSW22,
title = {CoCa: Contrastive Captioners are Image-Text Foundation Models},
author = {Jiahui Yu and Zirui Wang and Vijay Vasudevan and Legg Yeung and Mojtaba Seyedhosseini and Yonghui Wu},
year = {2022},
url = {https://openreview.net/forum?id=Ee277P3AYC},
researchr = {https://researchr.org/publication/YuWVYSW22},
cites = {0},
citedby = {0},
journal = {Trans. Mach. Learn. Res.},
volume = {2022},
}