Y
Yongsheng Zhou
Publications - 6
Citations - 52
Yongsheng Zhou is an academic researcher. The author has contributed to research in topics: Chinese characters & Reading (process). The author has an hindex of 2, co-authored 6 publications receiving 32 citations.
Papers
More filters
Proceedings ArticleDOI
ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
Rui Zhang,Mingkun Yang,Xiang Bai,Baoguang Shi,Dimosthenis Karatzas,Shijian Lu,C. V. Jawahar,Yongsheng Zhou,Qianyi Jiang,Qi Song,Nan Li,Kai Zhou,Lei Wang,Dong Wang,Minghui Liao +14 more
TL;DR: The ICDAR2019-ReCTS this article, which mainly focuses on reading Chinese text on signboard, has attracted great interest and the final results of the competition are presented in this article.
Posted Content
ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard.
Xi Liu,Rui Zhang,Yongsheng Zhou,Qianyi Jiang,Qi Song,Nan Li,Kai Zhou,Lei Wang,Dong Wang,Minghui Liao,Mingkun Yang,Xiang Bai,Baoguang Shi,Dimosthenis Karatzas,Shijian Lu,C. V. Jawahar +15 more
TL;DR: The ICDAR2019-ReCTS this article, which mainly focuses on reading Chinese text on signboard, has attracted great interest and the final results of the competition are presented in this article.
Proceedings ArticleDOI
Scene Text Detection with Feature Pyramid Network and Linking Segments
TL;DR: This paper proposes an effective and efficient model (SEG-FPN), which is based on Feature Pyramid Network (FPN) and Linking Segments (SegLink) and incorporates feature pyramid mechanism with Single Shot Detector (SSD) framework to deal with different scale texts, and link locally detectable elements to detect texts of different orientation and aspect ratios.
Book ChapterDOI
An Improved Convolutional Block Attention Module for Chinese Character Recognition
TL;DR: A novel method named ICBAM (Improved Convolutional Block Attention Module) for Chinese character recognition in the wild is proposed, which improves the generalization performance of the network and effectively avoid over-fitting.
Proceedings ArticleDOI
Reading Chinese Scene Text with Arbitrary Arrangement Based on Character Spotting
TL;DR: This paper proposes a character based framework to spotting Chinese text from another view that achieves superior performance comparing with state of the art text line based approaches.