{"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/end-to-end-handwritten-paragraph-text","title":"End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network","arxiv_id":"2012.03868","date":"2020-12-07","proceeding":null,"authors":["Denis Coquenet","Clément Chatelain","Thierry Paquet"],"abstract":"Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on the current text line features. This way, it performs a kind of implicit line segmentation. For each text line features, a decoder module recognizes the character sequence associated, leading to the recognition of a whole paragraph. We achieve state-of-the-art character error rate at paragraph level on three popular datasets: 1.91% for RIMES, 4.45% for IAM and 3.59% for READ 2016. Our code and trained model weights are available at https://github.com/FactoDeepLearning/VerticalAttentionOCR.","url_abs":"https://arxiv.org/abs/2012.03868v2","url_pdf":"https://arxiv.org/pdf/2012.03868v2.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":"end-to-end-handwritten-paragraph-text","repo_url":"https://github.com/FactoDeepLearning/VerticalAttentionOCR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"handwritten-text-recognition","task_name":"Handwritten Text Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/handwritten-text-recognition-on-iam","task":"Handwritten Text Recognition","dataset":"IAM","model":"VAN","rank_in_archive_order":7,"of":17,"metrics":{"CER":"4.32","WER":"16.24"},"uses_additional_data":false},{"leaderboard":"/sota/handwritten-text-recognition-on-iam-line","task":"Handwritten Text Recognition","dataset":"IAM(line-level)","model":"VAN","rank_in_archive_order":3,"of":5,"metrics":{"Test CER":"5.0","Test WER":"16.3"},"uses_additional_data":false},{"leaderboard":"/sota/handwritten-text-recognition-on-read2016-line","task":"Handwritten Text Recognition","dataset":"READ2016(line-level)","model":"VAN","rank_in_archive_order":2,"of":5,"metrics":{"Test CER":"4.1","Test WER":"16.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.03868","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}