Yongqing Zhu, Xiangyang Li 0002, Mao Zheng, Jiahao Yang, Zihan Wang, Xiaoqian Guo, Zifeng Chai, Yuchen Yuan, Shuqiang Jiang. Focus and Align: Learning Tube Tokens for Video-Language Pre-Training. IEEE Transactions on Multimedia, 25:8036-8050, 2023. [doi]
@article{ZhuLZYWGCYJ23,
title = {Focus and Align: Learning Tube Tokens for Video-Language Pre-Training},
author = {Yongqing Zhu and Xiangyang Li 0002 and Mao Zheng and Jiahao Yang and Zihan Wang and Xiaoqian Guo and Zifeng Chai and Yuchen Yuan and Shuqiang Jiang},
year = {2023},
doi = {10.1109/TMM.2022.3231108},
url = {https://doi.org/10.1109/TMM.2022.3231108},
researchr = {https://researchr.org/publication/ZhuLZYWGCYJ23},
cites = {0},
citedby = {0},
journal = {IEEE Transactions on Multimedia},
volume = {25},
pages = {8036-8050},
}