@InProceedings{ramisa-EtAl:2017:VL17,
  author    = {Ramisa, Arnau  and  Yan, Fei  and  Moreno-Noguer, Francesc  and  Mikolajczyk, Krystian},
  title     = {The BreakingNews Dataset},
  booktitle = {Proceedings of the Sixth Workshop on Vision and Language},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  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.},
  url       = {http://www.aclweb.org/anthology/W17-2005}
}