@article{coattentiongatedvisionlanguageembedding,
  title = {CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery},
  author = {Long Bai and Mobarakol Islam and Hongliang Ren},
  year = {2023},
  eprint = {2307.05182},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.05182v3},
}