Xiao Wang, Yaoyu Li, Tian Gan, Zheng Zhang, Jingjing Lv, Liqiang Nie. RTQ: Rethinking Video-language Understanding Based on Image-text Model. In Abdulmotaleb El-Saddik, Tao Mei, Rita Cucchiara, Marco Bertini 0001, Diana Patricia Tobon Vallejo, Pradeep K. Atrey, M. Shamim Hossain, editors, Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023. pages 557-566, ACM, 2023. [doi]
@inproceedings{WangLGZLN23,
title = {RTQ: Rethinking Video-language Understanding Based on Image-text Model},
author = {Xiao Wang and Yaoyu Li and Tian Gan and Zheng Zhang and Jingjing Lv and Liqiang Nie},
year = {2023},
doi = {10.1145/3581783.3612152},
url = {https://doi.org/10.1145/3581783.3612152},
researchr = {https://researchr.org/publication/WangLGZLN23},
cites = {0},
citedby = {0},
pages = {557-566},
booktitle = {Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023},
editor = {Abdulmotaleb El-Saddik and Tao Mei and Rita Cucchiara and Marco Bertini 0001 and Diana Patricia Tobon Vallejo and Pradeep K. Atrey and M. Shamim Hossain},
publisher = {ACM},
}