@inproceedings{acharya-etal-2019-vqd,
    title = "{VQD}: Visual Query Detection In Natural Scenes",
    author = "Acharya, Manoj  and
      Jariwala, Karan  and
      Kanan, Christopher",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N19-1194/",
    doi = "10.18653/v1/N19-1194",
    pages = "1955--1961",
    abstract = "We propose a new visual grounding task called Visual Query Detection (VQD). In VQD, the task is to localize a \textit{variable} number of objects in an image where the objects are specified in natural language. VQD is related to visual referring expression comprehension, where the task is to localize only \textit{one} object. We propose the first algorithms for VQD, and we evaluate them on both visual referring expression datasets and our new VQDv1 dataset."
}