Zobrazeno 1 - 10
of 201
pro vyhledávání: '"Ma, Weihong"'
Autor:
Lyu, Pengyuan, Li, Yulin, Zhou, Hao, Ma, Weihong, Wan, Xingyu, Xie, Qunyi, Wu, Liang, Zhang, Chengquan, Yao, Kun, Ding, Errui, Wang, Jingdong
Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images play crucial roles in information transmission but are accompanied by di
Externí odkaz:
http://arxiv.org/abs/2405.21013
Autor:
Lyu, Pengyuan, Ma, Weihong, Wang, Hongyi, Yu, Yuechen, Zhang, Chengquan, Yao, Kun, Xue, Yang, Wang, Jingdong
All tables can be represented as grids. Based on this observation, we propose GridFormer, a novel approach for interpreting unconstrained table structures by predicting the vertex and edge of a grid. First, we propose a flexible table representation
Externí odkaz:
http://arxiv.org/abs/2309.14962
Online and offline handwritten Chinese text recognition (HTCR) has been studied for decades. Early methods adopted oversegmentation-based strategies but suffered from low speed, insufficient accuracy, and high cost of character segmentation annotatio
Externí odkaz:
http://arxiv.org/abs/2207.14801
Autor:
Kong, Yuxin, Luo, Canjie, Ma, Weihong, Zhu, Qiyuan, Zhu, Shenggao, Yuan, Nicholas, Jin, Lianwen
Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which further increa
Externí odkaz:
http://arxiv.org/abs/2205.00146
Autor:
Ma, Weihong1 (AUTHOR) mawh@nercita.org.cn, Sun, Yi2 (AUTHOR) sunyi@nwafu.edu.cn, Qi, Xiangyu3 (AUTHOR) qxy@cau.edu.cn, Xue, Xianglong1 (AUTHOR) xuexl@nercita.org.cn, Chang, Kaixuan1 (AUTHOR) a91616@163.com, Xu, Zhankang2 (AUTHOR) 1043283468@nwafu.edu.cn, Li, Mingyu1 (AUTHOR) limy@nercita.org.cn, Wang, Rong2 (AUTHOR) rongw@nwafu.edu.cn, Meng, Rui1 (AUTHOR) mengr@nercita.org.cn, Li, Qifeng1 (AUTHOR) nercita1017@163.com
Publikováno v:
Sensors (14248220). Mar2024, Vol. 24 Issue 5, p1504. 24p.
Autor:
Wang, Rong, Gao, Ronghua, Li, Qifeng, Zhao, Chunjiang, Ru, Lin, Ding, Luyu, Yu, Ligen, Ma, Weihong
Publikováno v:
In Expert Systems With Applications 1 September 2024 249 Part B
Autor:
Wang, Jiapeng, Wang, Tianwei, Tang, Guozhi, Jin, Lianwen, Ma, Weihong, Ding, Kai, Huang, Yichao
Visual information extraction (VIE) has attracted increasing attention in recent years. The existing methods usually first organized optical character recognition (OCR) results into plain texts and then utilized token-level entity annotations as supe
Externí odkaz:
http://arxiv.org/abs/2106.10681
Autor:
Ma, Weihong, Zhang, Hesuo, Yan, Shuang, Yao, Guangshun, Huang, Yichao, Li, Hui, Wu, Yaqiang, Jin, Lianwen
In this paper, we fill the research gap by adopting state-of-the-art computer vision techniques for the data extraction stage in a data mining system. As shown in Fig.1, this stage contains two subtasks, namely, plot element detection and data conver
Externí odkaz:
http://arxiv.org/abs/2105.02039
Autor:
Wang, Jiashui, Li, Yanxia, Ma, Weihong, Zhang, Jiali, Yang, Hongbin, Wu, Peicong, Li, Jingyang, Jin, Zhiqiang
Publikováno v:
In Food Chemistry: X 30 March 2024 21
Autor:
Dang, Zhiguo, Zhu, Min, Chen, Huarui, Zhang, Ye, Gao, Aiping, Ma, Weihong, Chen, Yeyuan, Wei, Yunxie, Zhang, He
Publikováno v:
In International Journal of Biological Macromolecules 31 December 2023 253 Part 8