@article{multimodaltransformerwithmultiviewvisual,
  title = {Multimodal Transformer with Multi-View Visual Representation for Image Captioning},
  author = {Jun Yu and Jing Li and Zhou Yu and Qingming Huang},
  year = {2019},
  eprint = {1905.07841},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1905.07841v1},
}