@inproceedings{visualgroundinginvideoforunsupervised,
  title = {Visual Grounding in Video for Unsupervised Word Translation},
  author = {Gunnar A. Sigurdsson and Jean-Baptiste Alayrac and Aida Nematzadeh and Lucas Smaira and Mateusz Malinowski and João Carreira and Phil Blunsom and Andrew Zisserman},
  year = {2020},
  booktitle = {CVPR 2020 6},
  eprint = {2003.05078},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.05078v2},
}