@misc{multimodalitypixelbert2020,
  title = {{Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers}},
  author = {Zhicheng Huang and Zhaoyang Zeng and Bei Liu and Dongmei Fu and Jianlong Fu},
  year = {2020},
  eprint = {2004.00849},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.00849}
}
