@inproceedings{cao-etal-2021-pursuit,
    title = "On Pursuit of Designing Multi-modal Transformer for Video Grounding",
    author = "Cao, Meng  and
      Chen, Long  and
      Shou, Mike Zheng  and
      Zhang, Can  and
      Zou, Yuexian",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.emnlp-main.773/",
    doi = "10.18653/v1/2021.emnlp-main.773",
    pages = "9810--9823"
}