@misc{https://doi.org/10.48550/arxiv.2204.03162,
  doi = {10.48550/ARXIV.2204.03162},

  url = {https://arxiv.org/abs/2204.03162},

  author = {Thrush, Tristan and Jiang, Ryan and Bartolo, Max and Singh, Amanpreet and Williams, Adina and Kiela, Douwe and Ross, Candace},

  keywords = {Computer Vision and Pattern Recognition (cs.CV), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},

  title = {Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality},

  publisher = {arXiv},

  year = {2022},

  copyright = {Creative Commons Attribution 4.0 International}
}