FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model

@misc{xieMon Oct 13 2025 02:32:07 GMT+0000 (Coordinated Universal Time)fgclipbilingualfinegrained,
      title={FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model},
      author={Chunyu Xie and Bin Wang and Fanjing Kong and Jincheng Li and Dawei Liang and Ji Ao and Dawei Leng and Yuhui Yin},
      year={Mon Oct 13 2025 02:32:07 GMT+0000 (Coordinated Universal Time)},
      eprint={2510.10921/metadata},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2510.10921/metadata},
}