Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy 0002, Cordelia Schmid. VideoBERT: A Joint Model for Video and Language Representation Learning. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. pages 7463-7472, IEEE, 2019. [doi]
@inproceedings{SunMV0S19,
title = {VideoBERT: A Joint Model for Video and Language Representation Learning},
author = {Chen Sun and Austin Myers and Carl Vondrick and Kevin Murphy 0002 and Cordelia Schmid},
year = {2019},
doi = {10.1109/ICCV.2019.00756},
url = {https://doi.org/10.1109/ICCV.2019.00756},
researchr = {https://researchr.org/publication/SunMV0S19},
cites = {0},
citedby = {0},
pages = {7463-7472},
booktitle = {2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019},
publisher = {IEEE},
isbn = {978-1-7281-4803-8},
}