@inproceedings{mmftbertmultimodalfusiontransformerwith,
  title = {MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering},
  author = {Aisha Urooj Khan and Amir Mazaheri and Niels da Vitoria Lobo and Mubarak Shah},
  year = {2020},
  booktitle = {Findings of the Association for Computational Linguistics 2020},
  eprint = {2010.14095},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2010.14095v1},
}