@inproceedings{ramisa-etal-2017-breakingnews,
    title = "The {B}reaking{N}ews Dataset",
    author = "Ramisa, Arnau  and
      Yan, Fei  and
      Moreno-Noguer, Francesc  and
      Mikolajczyk, Krystian",
    editor = "Belz, Anya  and
      Erdem, Erkut  and
      Pastra, Katerina  and
      Mikolajczyk, Krystian",
    booktitle = "Proceedings of the Sixth Workshop on Vision and Language",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-2005/",
    doi = "10.18653/v1/W17-2005",
    pages = "38--39",
    abstract = "We present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (e.g. GPS coordinates and popularity metrics). The tenuous connection between the images and text in news data is appropriate to take work at the intersection of Computer Vision and Natural Language Processing to the next step, hence we hope this dataset will help spur progress in the field."
}