@inproceedings{zhao-etal-2024-video,
    title = "Video-Text Prompting for Weakly Supervised Spatio-Temporal Video Grounding",
    author = "Zhao, Heng  and
      Yinjie, Zhao  and
      Wen, Bihan  and
      Ong, Yew-Soon  and
      Zhou, Joey Tianyi",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.1086/",
    doi = "10.18653/v1/2024.emnlp-main.1086",
    pages = "19494--19505"
}