@article{marmotadeeplearningframeworkfor,
  title = {MARMOT: A Deep Learning Framework for Constructing Multimodal Representations for Vision-and-Language Tasks},
  author = {Patrick Y. Wu and Walter R. Mebane Jr},
  year = {2021},
  eprint = {2109.11526},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2109.11526v1},
}