@inproceedings{ren-etal-2023-testa,
    title = "{TESTA}: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding",
    author = "Ren, Shuhuai  and
      Chen, Sishuo  and
      Li, Shicheng  and
      Sun, Xu  and
      Hou, Lu",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-emnlp.66/",
    doi = "10.18653/v1/2023.findings-emnlp.66",
    pages = "932--947"
}