“…Handwritten Chinese text recognition (HCTR) has been studied for decades (Graves et al, 2009;Wang et al, 2012;Zhou et al, 2013;Keysers et al, 2017;Zhang et al, 2018). However, most previous studies (Yin et al, 2013;Wang et al, 2012Wang et al, , 2016Peng et al, 2019;Su et al, 2009;Du et al, 2016;Wang et al, 2018Wang et al, , 2020aMessina and Louradour, 2015;Xie et al, 2020;Xiu et al, 2019;Xie et al, 2019b;Wang et al, 2020b;Zhu et al, 2020;Luo et al, 2021;Rodriguez-Serrano et al, 2015;Jaderberg et al, 2016) assume that text line detection is provided by annotations and only focus on the recognition of cropped text line images. Although the accuracy of these line-level methods seems to be sufficient when combined with language models, they are limited to the one-dimensional distribution of characters and are significantly affected by the accuracy of text line detection in real-world applications.…”