Anurag Arnab, Mostafa Dehghani 0001, Georg Heigold, Chen Sun 0002, Mario Lucic, Cordelia Schmid. ViViT: A Video Vision Transformer. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. pages 6816-6826, IEEE, 2021. [doi]
@inproceedings{Arnab0H0LS21,
title = {ViViT: A Video Vision Transformer},
author = {Anurag Arnab and Mostafa Dehghani 0001 and Georg Heigold and Chen Sun 0002 and Mario Lucic and Cordelia Schmid},
year = {2021},
doi = {10.1109/ICCV48922.2021.00676},
url = {https://doi.org/10.1109/ICCV48922.2021.00676},
researchr = {https://researchr.org/publication/Arnab0H0LS21},
cites = {0},
citedby = {0},
pages = {6816-6826},
booktitle = {2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021},
publisher = {IEEE},
isbn = {978-1-6654-2812-5},
}