@article{multiscalesuperpixelstructureddifference,
  title = {Superpixel Semantics Representation and Pre-training for Vision-Language Task},
  author = {Siyu Zhang and Yeming Chen and Yaoru Sun and Fang Wang and Jun Yang and Lizhi Bai and Shangce Gao},
  year = {2023},
  eprint = {2310.13447},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.13447v3},
}