@inproceedings{vaidyanathan-etal-2018-snag,
    title = "{SNAG}: Spoken Narratives and Gaze Dataset",
    author = "Vaidyanathan, Preethi  and
      Prud{'}hommeaux, Emily T.  and
      Pelz, Jeff B.  and
      Alm, Cecilia O.",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/P18-2022/",
    doi = "10.18653/v1/P18-2022",
    pages = "132--137",
    abstract = "Humans rely on multiple sensory modalities when examining and reasoning over images. In this paper, we describe a new multimodal dataset that consists of gaze measurements and spoken descriptions collected in parallel during an image inspection task. The task was performed by multiple participants on 100 general-domain images showing everyday objects and activities. We demonstrate the usefulness of the dataset by applying an existing visual-linguistic data fusion framework in order to label important image regions with appropriate linguistic labels."
}