@article{stervlmspatiotemporalwithenhancedreferen,
  title = {STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models},
  author = {Tinh-Anh Nguyen-Nhu and Triet Dao Hoang Minh and Dat To-Thanh and Phuc Le-Gia and Tuan Vo-Lan and Tien-Huy Nguyen},
  year = {2025},
  eprint = {2508.13470},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.13470},
}