Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Fang, Zhihang"'
While vision transformers have been highly successful in improving the performance in image-based tasks, not much work has been reported on applying transformers to multilingual scene text recognition due to the complexities in the visual appearance
Externí odkaz:
http://arxiv.org/abs/2302.14261
Autor:
Zhu, Jianzhuo, Zhang, Qian, Ma, Liang, Wang, Sheng, Ma, Ying, Duan, Xiangyi, Cao, Xiaoyu, Fang, Zhihang, Liu, Yang, Wei, Yong, Feng, Chao
Publikováno v:
Journal of Chemical Physics; 11/7/2024, Vol. 161 Issue 17, p1-8, 8p
Publikováno v:
In Knowledge-Based Systems 25 November 2023 280
Publikováno v:
In Applied Surface Science 30 September 2022 597