Consistent multimodal pre-training for visual tokenization

Ting Pan, Lulu Tang, Xinlong Wang, Xin Liu, Shiguang ShanScience China Information Sciences 2025 · DOI

BibTeX
@article{pan2025consistent,
  author = {Ting Pan and Lulu Tang and Xinlong Wang and Xin Liu and Shiguang Shan},
  title = {{Consistent multimodal pre-training for visual tokenization}},
  journal = {Science China Information Sciences},
  year = {2025},
  doi = {10.1007/s11432-024-4603-x},
}

Loading related content...

Figure