{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/wukong-reader-multi-modal-pre-training-for","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","arxiv_id":"2212.09621","date":"2022-12-19","proceeding":null,"authors":["Haoli Bai","Zhiguang Liu","Xiaojun Meng","Wentao Li","Shuang Liu","Nian Xie","Rongfu Zheng","Liangwei Wang","Lu Hou","Jiansheng Wei","Xin Jiang","Qun Liu"],"abstract":"Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document textlines. We introduce textline-region contrastive learning to achieve fine-grained alignment between the visual regions and texts of document textlines. Furthermore, masked region modeling and textline-grid matching are also designed to enhance the visual and layout representations of textlines. Experiments show that our Wukong-Reader has superior performance on various VDU tasks such as information extraction. The fine-grained alignment over textlines also empowers Wukong-Reader with promising localization ability.","url_abs":"https://arxiv.org/abs/2212.09621v1","url_pdf":"https://arxiv.org/pdf/2212.09621v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"wukong-reader-multi-modal-pre-training-for","repo_url":"https://github.com/MS-P3/code4/tree/main/wukong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.09621","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}