@article{leveragingvisionlanguagelargemodelsforin,
  title = {Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization},
  author = {Jingwei Peng and Zhixuan Qiu and Boyu Jin and Surasakdi Siripong},
  year = {2025},
  eprint = {2509.05695},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.05695},
}