@article{pyramidcliphierarchicalfeaturealignment,
  title = {PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining},
  author = {Yuting Gao and Jinfeng Liu and Zihan Xu and Jun Zhang and Ke Li and Rongrong Ji and Chunhua Shen},
  year = {2022},
  eprint = {2204.14095},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2204.14095v2},
}