Hu Xu, Gargi Ghosh, Po-Yao Huang 0001, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, Christoph Feichtenhofer. VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021. pages 6787-6800, Association for Computational Linguistics, 2021. [doi]
@inproceedings{XuG0OAMZF21,
title = {VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding},
author = {Hu Xu and Gargi Ghosh and Po-Yao Huang 0001 and Dmytro Okhonko and Armen Aghajanyan and Florian Metze and Luke Zettlemoyer and Christoph Feichtenhofer},
year = {2021},
url = {https://aclanthology.org/2021.emnlp-main.544},
researchr = {https://researchr.org/publication/XuG0OAMZF21},
cites = {0},
citedby = {0},
pages = {6787-6800},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021},
editor = {Marie-Francine Moens and Xuanjing Huang and Lucia Specia and Scott Wen-tau Yih},
publisher = {Association for Computational Linguistics},
}