@article{vtlvlmaravideotemporallargevisionlanguag,
  title = {VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos},
  author = {Kaining Li and Shuwei He and Zihan Xu},
  year = {2025},
  eprint = {2508.15903},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.15903},
}