C
Chenxia Li
Publications - 5
Citations - 87
Chenxia Li is an academic researcher. The author has contributed to research in topics: Computer science & Optical character recognition. The author has an hindex of 1, co-authored 2 publications receiving 15 citations.
Papers
More filters
Posted Content
PP-OCR: A Practical Ultra Lightweight OCR System
Yuning Du,Chenxia Li,Ruoyu Guo,Xiaoting Yin,Weiwei Liu,Jun Zhou,Yifan Bai,Yu Zilin,Yehua Yang,Qingqing Dang,Haoshuang Wang +10 more
TL;DR: This paper proposes a practical ultra lightweight OCR system, i.e., PP-OCR, with an overall model size of only 3.5M, and introduces a bag of strategies to either enhance the model ability or reduce the model size.
Proceedings ArticleDOI
SVTR: Scene Text Recognition with a Single Visual Model
Yongkun Du,Zhineng Chen,Caiyan Jia,Xiaoyue Yin,Tianlun Zheng,Chenxia Li,Yuning Du,Yu-Gang Jiang +7 more
TL;DR: A Single Visual model for Scene Text recognition within the patch-wise image tokenization framework, which dispenses with the sequential modeling entirely and is effective on both English and Chinese scene text recognition tasks.
Journal ArticleDOI
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
Chenxia Li,Weiwei Liu,Ruoyu Guo,Xiaoyue Yin,Kaitao Jiang,Yongkun Du,Yuning Du,Lingfeng Zhu,Baohua Lai,Xiaoguang Hu,Dianhai Yu,Yanjun Ma +11 more
TL;DR: A more robust OCR system PP-OCRv3 is proposed in this paper, which upgrades the text detection model and text recognition model in 9 aspects based on PP- OCRv2 and shows that Hmean of PP-PCRV3 outperforms PP-ocRv1 by 5% with comparable inference speed.
Journal ArticleDOI
PP-StructureV2: A Stronger Document Analysis System
Chenxia Li,Ruoyu Guo,Jun Zhou,Mengtao An,Yuning Du,Lingfeng Zhu,Yi Liu,Xiaoguang Hu,Dianhai Yu +8 more
TL;DR: This work proposes PP-StructureV2 in this work, which contains two subsystems: layout information Extraction and Key Information Extraction, which brings 2.8% and 9.1% improvement respectively on the Hmean of Entity Recognition and Relation Extraction tasks.
Posted Content
PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System
Yuning Du,Chenxia Li,Ruoyu Guo,Cheng Cui,Weiwei Liu,Jun Zhou,Bin Lu,Yehua Yang,Qiwen Liu,Xiaoguang Hu,Dianhai Yu,Yanjun Ma +11 more
TL;DR: In this paper, the authors proposed a more robust OCR system, i.e. PP-OCRv2, which uses collaborative mutual learning (CML), CopyPaste, Lightweight CPUNetwork (LCNet), Unified-Deep Mutual Learning (U-DML), and Enhanced CTCLoss.