@Article{moens_et_al:DagRep.9.1.1,
  author =	{Moens, Marie-Francine and Specia, Lucia and Tuytelaars, Tinne},
  title =	{{Joint Processing of Language and Visual Data for Better Automated Understanding (Dagstuhl Seminar 19021)}},
  pages =	{1--27},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2019},
  volume =	{9},
  number =	{1},
  editor =	{Moens, Marie-Francine and Specia, Lucia and Tuytelaars, Tinne},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.9.1.1},
  URN =		{urn:nbn:de:0030-drops-105673},
  doi =		{10.4230/DagRep.9.1.1},
  annote =	{Keywords: multimodal learning, representation learning, computer vision, natural language processing, machine learning}
}