@misc{arnab2021vivit, title={ViViT: A Video Vision Transformer}, author={Anurag Arnab and Mostafa Dehghani and Georg Heigold and Chen Sun and Mario Lučić and Cordelia Schmid}, year={2021}, eprint={2103.15691}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2103.15691} }