{"id":"https://openalex.org/W4386596887","doi":"https://doi.org/10.1109/icip49359.2023.10222793","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","display_name":"DiffusionSTR: Diffusion Model for Scene Text Recognition","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386596887","doi":"https://doi.org/10.1109/icip49359.2023.10222793"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5051026262","display_name":"Masato Fujitake","orcid":"https://orcid.org/0000-0001-7702-499X"},"institutions":[{"id":"https://openalex.org/I4210105676","display_name":"Foundation for the Advancement of Social Theory","ror":"https://ror.org/01n95pm43","country_code":"US","type":"other","lineage":["https://openalex.org/I4210105676"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Masato Fujitake","raw_affiliation_strings":["Fast Accounting Co., Ltd,FA Research","FA Research, Fast Accounting Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fast Accounting Co., Ltd,FA Research","institution_ids":["https://openalex.org/I4210105676"]},{"raw_affiliation_string":"FA Research, Fast Accounting Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051026262"],"corresponding_institution_ids":["https://openalex.org/I4210105676"],"apc_list":null,"apc_paid":null,"fwci":1.3446,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8323127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1585","last_page":"1589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.995199978351593,"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/T11309","display_name":"Music and Audio Processing","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/text-recognition","display_name":"Text recognition","score":0.8369567394256592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787656784057617},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6761128306388855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6174281239509583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.544764518737793},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5331225991249084},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5168805122375488},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4467144012451172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34681516885757446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32612913846969604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06649792194366455}],"concepts":[{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.8369567394256592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787656784057617},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6761128306388855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6174281239509583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.544764518737793},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5331225991249084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5168805122375488},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4467144012451172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34681516885757446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32612913846969604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06649792194366455},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2343052201","https://openalex.org/W2810983211","https://openalex.org/W2908510526","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W3035449864","https://openalex.org/W3036167779","https://openalex.org/W3094502228","https://openalex.org/W3129651364","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3204479434","https://openalex.org/W4206184212","https://openalex.org/W4224035735","https://openalex.org/W4287329820","https://openalex.org/W4312879041","https://openalex.org/W4375869061","https://openalex.org/W4385245566","https://openalex.org/W4390873752","https://openalex.org/W6629590909","https://openalex.org/W6679045638","https://openalex.org/W6757817989","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6796163713","https://openalex.org/W6809885388"],"related_works":["https://openalex.org/W2353644209","https://openalex.org/W2593663830","https://openalex.org/W2348743188","https://openalex.org/W2902317490","https://openalex.org/W2463239216","https://openalex.org/W4387423451","https://openalex.org/W2025460258","https://openalex.org/W2046628353","https://openalex.org/W2096879929","https://openalex.org/W2381703089"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Diffusion":[3],"Model":[4],"for":[5,18,53],"Scene":[6],"Text":[7],"Recognition":[8],"(DiffusionSTR),":[9],"an":[10,35],"end-to-end":[11],"text":[12,20,31,65],"recognition":[13,32],"framework":[14],"using":[15],"diffusion":[16,49,59],"models":[17],"recognizing":[19],"in":[21,47],"the":[22,29,54,58,76],"wild.":[23],"While":[24],"existing":[25],"studies":[26],"have":[27],"viewed":[28],"scene":[30],"task":[33],"as":[34,41],"image-to-text":[36],"transformation,":[37],"we":[38],"rethought":[39],"it":[40],"a":[42,48],"text-text":[43],"one":[44],"under":[45],"images":[46],"model.":[50],"We":[51],"show":[52,74],"first":[55],"time":[56],"that":[57,75],"model":[60],"can":[61],"be":[62],"applied":[63],"to":[64,83],"recognition.":[66],"Furthermore,":[67],"experimental":[68],"results":[69],"on":[70],"publicly":[71],"available":[72],"datasets":[73],"proposed":[77],"method":[78],"achieves":[79],"competitive":[80],"accuracy":[81],"compared":[82],"state-of-the-art":[84],"methods.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}