@inproceedings{mirttlearningmultimodalinteraction,
  title = {MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering},
  author = {Junjie Wang and Yatai Ji and Jiaqi Sun and Yujiu Yang and Tetsuya Sakai},
  year = {2021},
  booktitle = {Findings (EMNLP) 2021 11},
  url = {https://aclanthology.org/2021.findings-emnlp.196},
}