多模态训练方面paper

多模态预训练+对比学习

CLIP - Learning Transferable Visual Models From Natural Language Supervision

WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training 2021-5

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning

https://github.com/openai/CLIP

https://colab.research.google.com/github/openai/clip/blob/master/notebooks/Interacting_with_CLIP.ipynb#scrollTo=0BpdJkdBssk9

https://github.com/huggingface/transformers