@inproceedings{bao-etal-2025-calligraphicocr,
title = "{C}alligraphic{OCR} for {C}hinese Calligraphy Recognition",
author = "Bao, Xiaoyi and
Wang, Zhongqing and
Gu, Jinghang and
Huang, Chu-Ren",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.245/",
pages = "4865--4877",
ISBN = "979-8-89176-332-6",
abstract = "With thousand years of history, calligraphy serve as one of the representative symbols of Chinese culture. Increasing works try to digitize calligraphy by recognizing the context of calligraphy for better preservation and propagation. However, previous works stick to isolated single character recognition, not only requires unpractical manual splitting into characters, but also abandon the enriched context information that could be supplementary. To this end, we construct the pioneering end-to-end calligraphy recognition benchmark dataset, this dataset is challenging due to both the visual variations such as different writing styles and the textual understanding such as the domain shift in semantics. We further propose CalligraphicOCR (COCR) equipped with calligraphic image augmentation and action-based corrector targeted at the challenging root of this setting. Experiments demonstrate the advantage of our proposed model over cutting-edge baselines, underscoring the necessity of introducing this new setting, thereby facilitating a solid precondition for protecting and propagating the already scarce resources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2025-calligraphicocr">
<titleInfo>
<title>CalligraphicOCR for Chinese Calligraphy Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyi</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghang</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>With thousand years of history, calligraphy serve as one of the representative symbols of Chinese culture. Increasing works try to digitize calligraphy by recognizing the context of calligraphy for better preservation and propagation. However, previous works stick to isolated single character recognition, not only requires unpractical manual splitting into characters, but also abandon the enriched context information that could be supplementary. To this end, we construct the pioneering end-to-end calligraphy recognition benchmark dataset, this dataset is challenging due to both the visual variations such as different writing styles and the textual understanding such as the domain shift in semantics. We further propose CalligraphicOCR (COCR) equipped with calligraphic image augmentation and action-based corrector targeted at the challenging root of this setting. Experiments demonstrate the advantage of our proposed model over cutting-edge baselines, underscoring the necessity of introducing this new setting, thereby facilitating a solid precondition for protecting and propagating the already scarce resources.</abstract>
<identifier type="citekey">bao-etal-2025-calligraphicocr</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.245/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>4865</start>
<end>4877</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CalligraphicOCR for Chinese Calligraphy Recognition
%A Bao, Xiaoyi
%A Wang, Zhongqing
%A Gu, Jinghang
%A Huang, Chu-Ren
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F bao-etal-2025-calligraphicocr
%X With thousand years of history, calligraphy serve as one of the representative symbols of Chinese culture. Increasing works try to digitize calligraphy by recognizing the context of calligraphy for better preservation and propagation. However, previous works stick to isolated single character recognition, not only requires unpractical manual splitting into characters, but also abandon the enriched context information that could be supplementary. To this end, we construct the pioneering end-to-end calligraphy recognition benchmark dataset, this dataset is challenging due to both the visual variations such as different writing styles and the textual understanding such as the domain shift in semantics. We further propose CalligraphicOCR (COCR) equipped with calligraphic image augmentation and action-based corrector targeted at the challenging root of this setting. Experiments demonstrate the advantage of our proposed model over cutting-edge baselines, underscoring the necessity of introducing this new setting, thereby facilitating a solid precondition for protecting and propagating the already scarce resources.
%U https://aclanthology.org/2025.emnlp-main.245/
%P 4865-4877
Markdown (Informal)
[CalligraphicOCR for Chinese Calligraphy Recognition](https://aclanthology.org/2025.emnlp-main.245/) (Bao et al., EMNLP 2025)
ACL
- Xiaoyi Bao, Zhongqing Wang, Jinghang Gu, and Chu-Ren Huang. 2025. CalligraphicOCR for Chinese Calligraphy Recognition. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 4865–4877, Suzhou, China. Association for Computational Linguistics.