{"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/multi-scale-attention-with-dense-encoder-for","title":"Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition","arxiv_id":"1801.03530","date":"2018-01-05","proceeding":null,"authors":["Jianshu Zhang","Jun Du","Li-Rong Dai"],"abstract":"Handwritten mathematical expression recognition is a challenging problem due\nto the complicated two-dimensional structures, ambiguous handwriting input and\nvariant scales of handwritten math symbols. To settle this problem, we utilize\nthe attention based encoder-decoder model that recognizes mathematical\nexpression images from two-dimensional layouts to one-dimensional LaTeX\nstrings. We improve the encoder by employing densely connected convolutional\nnetworks as they can strengthen feature extraction and facilitate gradient\npropagation especially on a small training set. We also present a novel\nmulti-scale attention model which is employed to deal with the recognition of\nmath symbols in different scales and save the fine-grained details that will be\ndropped by pooling operations. Validated on the CROHME competition task, the\nproposed method significantly outperforms the state-of-the-art methods with an\nexpression recognition accuracy of 52.8% on CROHME 2014 and 50.1% on CROHME\n2016, by only using the official training dataset.","url_abs":"http://arxiv.org/abs/1801.03530v2","url_pdf":"http://arxiv.org/pdf/1801.03530v2.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":"multi-scale-attention-with-dense-encoder-for","repo_url":"https://github.com/JianshuZhang/WAP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-scale-attention-with-dense-encoder-for","repo_url":"https://github.com/learnpcclaimsapp/WAP-SAMPLE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"handwritten-mathmatical-expression","task_name":"Handwritten Mathmatical Expression Recognition"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/handwritten-mathmatical-expression","task":"Handwritten Mathmatical Expression Recognition","dataset":"CROHME 2014","model":"DenseWAP-MSA","rank_in_archive_order":14,"of":17,"metrics":{"ExpRate":"52.8"},"uses_additional_data":false},{"leaderboard":"/sota/handwritten-mathmatical-expression","task":"Handwritten Mathmatical Expression Recognition","dataset":"CROHME 2014","model":"DenseWAP","rank_in_archive_order":15,"of":17,"metrics":{"ExpRate":"50.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.03530","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}