@inproceedings{liao-etal-2024-videoinsta,
    title = "{V}ideo{INSTA}: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with {LLM}s",
    author = "Liao, Ruotong  and
      Erler, Max  and
      Wang, Huiyu  and
      Zhai, Guangyao  and
      Zhang, Gengyuan  and
      Ma, Yunpu  and
      Tresp, Volker",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.384/",
    doi = "10.18653/v1/2024.findings-emnlp.384",
    pages = "6577--6602"
}