@inproceedings{kim-etal-2024-extending,
    title = "Extending {CLIP}`s Image-Text Alignment to Referring Image Segmentation",
    author = "Kim, Seoyeon  and
      Kang, Minguk  and
      Kim, Dongwon  and
      Park, Jaesik  and
      Kwak, Suha",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.258/",
    doi = "10.18653/v1/2024.naacl-long.258",
    pages = "4611--4628"
}