FudanDISC / weakly-supervised-mVLP

Implementation of our ACL2023 paper: Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training
18Updated last year

Alternatives and similar repositories for weakly-supervised-mVLP:

Users that are interested in weakly-supervised-mVLP are comparing it to the libraries listed below