@article{videostirunderstandinglongvideosviaspati,
  title = {VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG},
  author = {Honghao Fu and Miao Xu and Yiwei Wang and Dailing Zhang and Jun Liu and Yujun Cai},
  year = {2026},
  eprint = {2604.05418},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.05418},
}