The importance of low-resource document analysis is multifaceted, particularly in the fields of cultural preservation, data scarcity, linguistic research, and technological applications. Firstly, low-resource languages often embody unique cultural and historical contexts. Document analysis facilitates the digitization and preservation of these linguistic materials, providing crucial resources for understanding human history and cultural evolution. For instance, many endangered languages possess vast amounts of scanned documents, which can be analyzed to create valuable linguistic and cultural repositories. Secondly, low-resource languages typically suffer from a lack of large-scale annotated datasets, posing challenges for training machine learning models. Document analysis techniques, such as Optical Character Recognition (OCR) and document layout analysis, enable the extraction and structuring of data from existing documents, thereby mitigating data scarcity issues. Moreover, document analysis plays a pivotal role in enhancing machine translation capabilities. Monolingual data extracted through OCR can be utilized to improve machine translation for low-resource languages, which is particularly critical for languages with limited parallel corpora. Additionally, document analysis supports linguistic research by enabling the study of language variations and historical documentation, shedding light on the evolution and unique features of these languages. Finally, document analysis enhances the accessibility and usability of low-resource language documents. For example, advancements in OCR systems for non-Latin scripts allow researchers to extract text more efficiently from scanned documents, enabling applications such as content summarization and information retrieval. In summary, low-resource document analysis is not only a vital tool for cultural preservation but also a key driver of language technology development and academic research.

Submission Guidelines

This workshop invites original contributions in both theoretical and applied research domains. All submissions must adhere to the formatting guidelines specified on the ICDAR 2025 official website. Paper length is limited to 15 pages (excluding references) and must comply with our double-blind review requirements:

• Remove all author identifiers (names, affiliations, etc.) from the manuscript
• Cite previous work in third-person format to avoid identity disclosure
• Omit acknowledgments section in initial submissions

Submissions will be accepted through the workshop's EasyChair submission portal. At least one author of each accepted paper must complete workshop registration to present the work. Detailed submission procedures are available on the ICDAR 2025 guidelines portal

List of Topics

• Document image processing
• Document image processing Optical Character Recognition, OCR
• Logical layout analysis
• Handwriting recognition
• Natural language processing for document understanding
• Medical document analysis
• Document entity recognition
• Document entity relationship
• Pretrained model for document analysis
• Language model for document information extraction
• Gold-Standard benchmarks and datasets for low-resource languages
• Document analysis systems for low-resource languages

Workshop Chairs

• Yong,Tso, Xizang University, China
• Brian Kenji Iwana，Kyushu University,Japan
• Yu,Yongbin, University of Electronic Science and Technology, China

Program Committee Members

• Nyima,Trashi, Xizang University,China
• Brian Kenji Iwana，Kyushu University,Japan
• Harold MOUCHERE，Nantes Univerisity, France
• Cheng,Jian,University of Electronic Science and Technology, China
• Anna Zhu, Wuhan University of Technology,China
• Yu,Yongbin, University of Electronic Science and Technology, China
• Yong,Tso, Xizang University,China
• Rinchen,Dongrub, Xizang University,China

Contact

All questions about submissions should be emailed to yongtso@163.com.