PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Yuan Yao, Qianyu Chen, Ao Zhang, Wei Ji, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

BibTeX
@inproceedings{yao2022pevl,
  author = {Yuan Yao and Qianyu Chen and Ao Zhang and Wei Ji and Zhiyuan Liu and Tat-Seng Chua and Maosong Sun},
  title = {{PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models}},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2022},
  doi = {10.18653/v1/2022.emnlp-main.763},
}
Figure