{"id":"https://openalex.org/W7137820158","doi":"https://doi.org/10.1609/aaai.v40i5.37370","title":"MDiff4STR: Mask Diffusion Model for Scene Text Recognition","display_name":"MDiff4STR: Mask Diffusion Model for Scene Text Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137820158","doi":"https://doi.org/10.1609/aaai.v40i5.37370"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i5.37370","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37370","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37370/41332","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37370/41332","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129678893","display_name":"Yongkun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Du","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129702148","display_name":"MIAOMIAO ZHAO","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaomiao Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002485153","display_name":"Songlin Fan","orcid":"https://orcid.org/0000-0003-4906-6660"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlin Fan","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, China\nChina Mobile Shanghai ICT Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, China\nChina Mobile Shanghai ICT Co., Ltd., China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692887","display_name":"Zhineng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, China","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129409096","display_name":"Caiyan Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiyan Jia","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129669423","display_name":"Yu-Gang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, China","institution_ids":["https://openalex.org/I4210139618"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3705","last_page":"3713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9265000224113464,"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":0.9265000224113464,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.009600000455975533,"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/T10028","display_name":"Topic Modeling","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/inference","display_name":"Inference","score":0.7573000192642212},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6323999762535095},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5878999829292297},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5734999775886536},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.35519999265670776},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3257000148296356},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3255999982357025}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7573000192642212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6323999762535095},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853999853134155},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i5.37370","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37370","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37370/41332","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37370","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37370","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37370/41332","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137820158.pdf","grobid_xml":"https://content.openalex.org/works/W7137820158.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mask":[0,69],"Diffusion":[1,70],"Models":[2],"(MDMs)":[3],"have":[4],"recently":[5],"emerged":[6],"as":[7,177,179],"a":[8,68,132,138],"promising":[9],"alternative":[10],"to":[11,19,90,145],"auto-regressive":[12],"models":[13],"(ARMs)":[14],"for":[15,30,79],"vision-language":[16],"tasks,":[17],"owing":[18],"their":[20],"flexible":[21],"balance":[22],"of":[23,54,108,158,183],"efficiency":[24],"and":[25,96,98,147,163,174],"accuracy.":[26],"In":[27],"this":[28,63],"paper,":[29],"the":[31,38,106,112,128,143,181],"first":[32,113],"time,":[33],"we":[34,65,82,115,130],"introduce":[35],"MDMs":[36,89],"into":[37],"Scene":[39],"Text":[40],"Recognition":[41],"(STR)":[42],"task.":[43],"We":[44,154],"show":[45],"that":[46,120,136],"vanilla":[47],"MDM":[48],"lags":[49],"behind":[50],"ARMs":[51,196],"in":[52,87,197],"terms":[53],"accuracy,":[55,198],"although":[56],"it":[57],"improves":[58],"recognition":[59],"efficiency.":[60],"To":[61,110],"bridge":[62],"gap,":[64],"propose":[66,131],"MDiff4STR,":[67],"model":[71,144],"enhanced":[72],"with":[73,124,203],"two":[74,84],"key":[75,85],"improvement":[76],"strategies":[77,119],"tailored":[78],"STR.":[80],"Specifically,":[81],"identify":[83],"challenges":[86],"applying":[88],"STR:":[91],"noising":[92,118],"gap":[93],"between":[94],"training":[95,123],"inference,":[97],"overconfident":[99],"predictions":[100],"during":[101],"inference.":[102],"Both":[103],"significantly":[104],"hinder":[105],"performance":[107],"MDMs.":[109],"mitigate":[111],"issue,":[114],"develop":[116],"six":[117],"better":[121],"align":[122],"inference":[125,202],"behavior.":[126],"For":[127],"second,":[129],"token-replacement":[133],"noise":[134,140],"mechanism":[135],"provides":[137],"non-mask":[139],"type,":[141],"encouraging":[142],"reconsider":[146],"revise":[148],"overly":[149],"confident":[150],"but":[151],"incorrect":[152],"predictions.":[153],"conduct":[155],"extensive":[156],"evaluations":[157],"MDiff4STR":[159,188],"on":[160],"both":[161],"standard":[162],"challenging":[164],"STR":[165,192],"benchmarks,":[166],"covering":[167],"diverse":[168],"scenarios":[169],"including":[170],"irregular,":[171],"artistic,":[172],"occluded,":[173],"Chinese":[175],"text,":[176],"well":[178],"whether":[180],"use":[182],"pretraining.":[184],"Across":[185],"these":[186],"settings,":[187],"consistently":[189],"outperforms":[190],"popular":[191],"models,":[193],"surpassing":[194],"state-of-the-art":[195],"while":[199],"maintaining":[200],"fast":[201],"only":[204],"three":[205],"denoising":[206],"steps.":[207],"Code:":[208],"https://github.com/Topdu/OpenOCR.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}