FudanDISC/weakly-supervised-mVLP
Implementation of our ACL2023 paper: Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training
MIT
No issues in this repository yet.
Implementation of our ACL2023 paper: Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training
MIT
No issues in this repository yet.