@article{190600283,
  title = {Learning to Generate Grounded Visual Captions without Localization Supervision},
  author = {Chih-Yao Ma and Yannis Kalantidis and Ghassan AlRegib and Peter Vajda and Marcus Rohrbach and Zsolt Kira},
  year = {2019},
  eprint = {1906.00283},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.00283v3},
}