{"id":"https://openalex.org/W4408352117","doi":"https://doi.org/10.1109/icassp49660.2025.10890134","title":"SmartExp: An Adaptive Data Expansion Strategy for Improving Handwritten Text Recognition","display_name":"SmartExp: An Adaptive Data Expansion Strategy for Improving Handwritten Text Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352117","doi":"https://doi.org/10.1109/icassp49660.2025.10890134"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890134","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":"article","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/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050639942","display_name":"Hongxi Wei","orcid":"https://orcid.org/0000-0002-2570-4544"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxi Wei","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019511889","display_name":"Shiwen Sun","orcid":"https://orcid.org/0009-0007-8416-4406"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Sun","raw_affiliation_strings":["Inner Mongolia University,School of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,School of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02894687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9760000109672546,"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":0.9760000109672546,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7513659000396729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5619053840637207},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4567561745643616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44375908374786377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.417254775762558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513659000396729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5619053840637207},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4567561745643616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44375908374786377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.417254775762558},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890134","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322868","display_name":"Natural Science Foundation of Inner Mongolia","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1993155451","https://openalex.org/W2050995497","https://openalex.org/W2152928267","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2603777577","https://openalex.org/W2750938222","https://openalex.org/W2965066169","https://openalex.org/W2998382406","https://openalex.org/W3031548983","https://openalex.org/W3109645351","https://openalex.org/W3173630418","https://openalex.org/W3211060597","https://openalex.org/W4385991139","https://openalex.org/W4386076475","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6744310024","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6863094358"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Constructing":[0],"a":[1,40,80,103],"highly":[2],"accurate":[3],"handwritten":[4,35],"OCR":[5],"system":[6],"requires":[7],"large":[8],"amounts":[9],"of":[10,24,71],"high-quality":[11,27],"training":[12],"data,":[13],"yet":[14],"data":[15,43,51,73,76,87,94,111],"collection":[16],"is":[17,136],"labor-intensive":[18],"and":[19,75],"costly.":[20],"With":[21],"the":[22,49,62,65,69],"advance":[23],"generative":[25],"models,":[26,39],"synthetic":[28],"images":[29],"have":[30],"been":[31],"applied":[32],"to":[33,58],"enhance":[34],"text":[36],"recognition":[37],"(HTR)":[38],"technique":[41],"termed":[42],"expansion.":[44],"However,":[45],"we":[46,100],"find":[47],"that":[48,85,124],"generated":[50],"may":[52],"sometimes":[53],"provide":[54],"only":[55],"insignificant":[56],"improvements":[57],"HTR.":[59],"We":[60,78],"investigate":[61],"causes":[63],"behind":[64],"small":[66],"gains":[67],"from":[68],"perspectives":[70],"both":[72],"expansion":[74,88],"augmentation.":[77,95],"reveal":[79],"balancing":[81],"mechanism":[82],"in":[83],"HTR":[84,132],"stronger":[86],"should":[89],"be":[90],"paired":[91],"with":[92],"weaker":[93],"Informed":[96],"by":[97],"these":[98],"insights,":[99],"propose":[101],"SmartExp,":[102],"purely":[104],"data-driven":[105],"strategy":[106,127],"without":[107],"introducing":[108],"any":[109],"extra":[110],"or":[112],"computational":[113],"costs.":[114],"Extensive":[115],"experiments":[116],"on":[117],"three":[118],"widely":[119],"used":[120],"benchmark":[121],"datasets":[122],"demonstrate":[123],"our":[125],"SmartExp":[126],"can":[128],"significantly":[129],"improve":[130],"various":[131],"models.":[133],"Our":[134],"code":[135],"publicly":[137],"available":[138],"at:":[139],"https://github.com/Fyzjym/SmartExp.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}