Ting Pan, Lulu Tang, Xinlong Wang, Xin Liu, Shiguang Shan. Consistent multimodal pre-training for visual tokenization. // Science China Information Sciences. – 2025. – DOI: 10.1007/s11432-024-4603-x. – URL: https://doi.org/10.1007/s11432-024-4603-x
Ting Pan, Lulu Tang, Xinlong Wang, Xin Liu, & Shiguang Shan (2025). Consistent multimodal pre-training for visual tokenization. Science China Information Sciences. https://doi.org/10.1007/s11432-024-4603-x
Ting Pan, et al. “Consistent multimodal pre-training for visual tokenization.” Science China Information Sciences, 2025. doi:10.1007/s11432-024-4603-x.
@article{Pan2025,
title = {Consistent multimodal pre-training for visual tokenization},
author = {Pan, Ting and Tang, Lulu and Wang, Xinlong and Liu, Xin and Shan, Shiguang},
journal = {Science China Information Sciences},
year = {2025},
doi = {10.1007/s11432-024-4603-x},
url = {https://doi.org/10.1007/s11432-024-4603-x}
}