{"id":"https://openalex.org/W4408354624","doi":"https://doi.org/10.1109/icassp49660.2025.10888964","title":"Disentangled Representation Learning for Chinese Handwriting Recognition","display_name":"Disentangled Representation Learning for Chinese Handwriting Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354624","doi":"https://doi.org/10.1109/icassp49660.2025.10888964"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059850130","display_name":"Tianqi Zhao","orcid":"https://orcid.org/0000-0002-3562-4679"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianqi Zhao","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076442506","display_name":"Liangrui Peng","orcid":"https://orcid.org/0000-0001-7793-1039"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangrui Peng","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059777846","display_name":"Gang Yao","orcid":"https://orcid.org/0000-0001-9311-0337"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yao","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087166824","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-6818-1886"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016755979","display_name":"Tao Yao","orcid":"https://orcid.org/0000-0003-2660-1050"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Tao","raw_affiliation_strings":["Huawei Technologies,Noah’s Ark Lab,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,Noah’s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440004348754883},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.6457569599151611},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5186414122581482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4827951192855835},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4502614140510559},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44175955653190613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4016183614730835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440004348754883},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.6457569599151611},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5186414122581482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4827951192855835},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4502614140510559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44175955653190613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4016183614730835},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2156338447","https://openalex.org/W2163922914","https://openalex.org/W2194775991","https://openalex.org/W2565262489","https://openalex.org/W2907106451","https://openalex.org/W2962766617","https://openalex.org/W2963150697","https://openalex.org/W3004388780","https://openalex.org/W3096609285","https://openalex.org/W3176337110","https://openalex.org/W4211049957","https://openalex.org/W4225289787","https://openalex.org/W4307649176","https://openalex.org/W4372263458","https://openalex.org/W4385245566","https://openalex.org/W4392133760","https://openalex.org/W4400188660","https://openalex.org/W4402335574","https://openalex.org/W4402754116","https://openalex.org/W6600284362","https://openalex.org/W6637373629","https://openalex.org/W6640963894","https://openalex.org/W6718140377","https://openalex.org/W6748223763","https://openalex.org/W6779459370","https://openalex.org/W6780012054"],"related_works":["https://openalex.org/W2388180914","https://openalex.org/W2063708026","https://openalex.org/W2507888814","https://openalex.org/W3118925046","https://openalex.org/W2381764175","https://openalex.org/W2561540377","https://openalex.org/W2360066868","https://openalex.org/W3084909207","https://openalex.org/W1694630026","https://openalex.org/W3166464480"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"sequence":[2],"modeling":[3],"methods":[4],"have":[5],"improved":[6],"the":[7,15,58,68,98,103,122,129,146],"performance":[8],"in":[9,19,60,90,121,152],"Chinese":[10,47,132,139,155],"handwriting":[11,33,48,73,133],"recognition":[12,49],"tasks.":[13],"However,":[14],"implicit":[16],"representations":[17,100,107,118],"learned":[18],"current":[20],"deep":[21,76],"neural":[22],"network":[23],"models":[24,57],"usually":[25],"lack":[26],"explainability":[27],"and":[28,70,82,116,135],"generalization":[29],"ability":[30],"for":[31,46,108],"practical":[32],"samples":[34],"with":[35,79,158],"diverse":[36,159],"styles.":[37,160],"This":[38],"paper":[39],"proposes":[40],"a":[41,52,91,136],"disentangled":[42],"representation":[43],"learning":[44,77],"method":[45,148],"by":[50,102],"using":[51],"latent":[53,61],"Gaussian":[54,64],"process,":[55],"which":[56,143],"features":[59],"space":[62],"as":[63],"distributions":[65],"conditioned":[66],"on":[67,128],"content":[69,109,115],"style":[71,88,92,117],"of":[72],"samples.":[74],"A":[75],"model":[78],"one":[80],"encoder":[81,104],"multiple":[83],"decoders":[84],"is":[85],"designed.":[86],"The":[87],"embeddings":[89],"decoder":[93],"are":[94,119,126],"used":[95],"to":[96,113],"convert":[97],"hidden":[99],"output":[101],"into":[105],"style-agnostic":[106],"decoding.":[110],"Objective":[111],"functions":[112],"decouple":[114],"introduced":[120],"training":[123],"stage.":[124],"Experiments":[125],"conducted":[127],"public":[130],"CASIA-HWDB":[131],"dataset":[134],"self-built":[137],"historical":[138],"local":[140],"genealogies":[141],"dataset,":[142],"demonstrate":[144],"that":[145],"proposed":[147],"achieves":[149],"high":[150],"accuracy":[151],"recognizing":[153],"handwritten":[154],"text":[156],"images":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}