@inproceedings{chen-etal-2023-stair,
    title = "{STAIR}: Learning Sparse Text and Image Representation in Grounded Tokens",
    author = "Chen, Chen  and
      Zhang, Bowen  and
      Cao, Liangliang  and
      Shen, Jiguang  and
      Gunter, Tom  and
      Jose, Albin  and
      Toshev, Alexander  and
      Zheng, Yantao  and
      Shlens, Jonathon  and
      Pang, Ruoming  and
      Yang, Yinfei",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.932/",
    doi = "10.18653/v1/2023.emnlp-main.932",
    pages = "15079--15094"
}