@inproceedings{gella-keller-2018-evaluation,
    title = "An Evaluation of Image-Based Verb Prediction Models against Human Eye-Tracking Data",
    author = "Gella, Spandana  and
      Keller, Frank",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/N18-2119/",
    doi = "10.18653/v1/N18-2119",
    pages = "758--763",
    abstract = "Recent research in language and vision has developed models for predicting and disambiguating verbs from images. Here, we ask whether the predictions made by such models correspond to human intuitions about visual verbs. We show that the image regions a verb prediction model identifies as salient for a given verb correlate with the regions fixated by human observers performing a verb classification task."
}