@inproceedings{girdhar2022omnivore,
  title={{Omnivore: A Single Model for Many Visual Modalities}},
  author={Girdhar, Rohit and Singh, Mannat and Ravi, Nikhila and van der Maaten, Laurens and Joulin, Armand and Misra, Ishan},
  booktitle={CVPR},
  year={2022}
}

@article{girdhar2022omnimae,
  title={OmniMAE: Single Model Masked Pretraining on Images and Videos},
  author={Girdhar, Rohit and El-Nouby, Alaaeldin and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan},
  journal={arXiv preprint arXiv:2206.08356},
  year={2022}
}