{"id":"https://openalex.org/W4405033944","doi":"https://doi.org/10.1109/iccv51701.2025.01622","title":"TextSSR: Diffusion-Based Data Synthesis for Scene Text Recognition","display_name":"TextSSR: Diffusion-Based Data Synthesis for Scene Text Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405033944","doi":"https://doi.org/10.1109/iccv51701.2025.01622"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.01137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061265309","display_name":"Xiaoyun Ye","orcid":"https://orcid.org/0000-0002-7465-9882"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingsong Ye","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915298","display_name":"Yongkun Du","orcid":"https://orcid.org/0009-0005-3114-2188"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Du","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090936749","display_name":"Yunbo Tao","orcid":"https://orcid.org/0000-0002-5850-3159"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Tao","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"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"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17464","last_page":"17473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9707000255584717,"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":0.9707000255584717,"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/diffusion","display_name":"Diffusion","score":0.6412297487258911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5409802198410034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.364722341299057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33931028842926025},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33169493079185486},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09350809454917908}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6412297487258911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5409802198410034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.364722341299057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33931028842926025},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33169493079185486},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09350809454917908},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.01137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.01137","pdf_url":"https://arxiv.org/pdf/2412.01137","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.01137","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.01137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.01137","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.01137","pdf_url":"https://arxiv.org/pdf/2412.01137","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1120941959","display_name":null,"funder_award_id":"32341012,62172103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":{"Scene":[0,62],"text":[1,34,38,48,84,107,135,149],"recognition":[2],"(STR)":[3],"suffers":[4],"from":[5,105],"challenges":[6],"of":[7,17,26,145],"either":[8],"less":[9],"realistic":[10,46],"synthetic":[11,165],"training":[12,65,182],"data":[13],"or":[14,108],"the":[15,24],"difficulty":[16],"collecting":[18],"sufficient":[19],"high-quality":[20],"real-world":[21,181],"data,":[22],"limiting":[23],"effectiveness":[25],"trained":[27,157,162],"models.":[28],"Meanwhile,":[29],"despite":[30],"producing":[31],"holistically":[32],"appealing":[33],"images,":[35],"diffusion-based":[36],"visual":[37],"generation":[39,85,101,132],"methods":[40],"struggle":[41],"to":[42],"synthesize":[43],"accurate":[44],"and":[45,75,99,118,173],"instance-level":[47],"at":[49,187],"scale.":[50],"To":[51],"tackle":[52],"this,":[53],"we":[54,140],"introduce":[55],"TextSSR:":[56],"a":[57,81,143],"novel":[58],"pipeline":[59],"for":[60],"Synthesizing":[61],"Text":[63],"Recognition":[64],"data.":[66,183],"TextSSR":[67,129],"targets":[68],"three":[69],"key":[70],"synthesizing":[71],"characteristics:":[72],"accuracy,":[73],"realism,":[74],"scalability.":[76],"It":[77,93],"achieves":[78],"accuracy":[79],"through":[80,133],"proposed":[82],"region-centric":[83],"with":[86,180],"position-glyph":[87],"enhancement,":[88],"ensuring":[89],"proper":[90],"character":[91],"placement.":[92],"maintains":[94],"realism":[95],"by":[96,167],"guiding":[97],"style":[98],"appearance":[100],"using":[102],"contextual":[103],"hints":[104],"surrounding":[106],"background.":[109],"This":[110],"character-aware":[111],"diffusion":[112],"architecture":[113],"enjoys":[114],"precise":[115],"character-level":[116],"control":[117],"semantic":[119],"coherence":[120],"preservation,":[121],"without":[122],"relying":[123],"on":[124,138,158,163,170],"natural":[125],"language":[126],"prompts.":[127],"Therefore,":[128],"supports":[130],"large-scale":[131],"combinatorial":[134],"permutations.":[136],"Based":[137],"these,":[139],"present":[141],"TextSSR-F,":[142],"dataset":[144],"3.55":[146],"million":[147],"quality-screened":[148],"instances.":[150],"Extensive":[151],"experiments":[152],"show":[153],"that":[154],"STR":[155],"models":[156],"TextSSR-F":[159],"outperform":[160],"those":[161],"existing":[164],"datasets":[166],"clear":[168],"margins":[169],"common":[171],"benchmarks,":[172],"further":[174],"improvements":[175],"are":[176],"observed":[177],"when":[178],"mixed":[179],"Code":[184],"is":[185],"available":[186],"https://github.com/YesianRohn/TextSSR.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}