{"id":"https://openalex.org/W7158515584","doi":"https://doi.org/10.1145/3806389","title":"Diff-Oracle: Learning Styles and Contents to Augment Realistic Oracle Characters in Diffusion Model","display_name":"Diff-Oracle: Learning Styles and Contents to Augment Realistic Oracle Characters in Diffusion Model","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W7158515584","doi":"https://doi.org/10.1145/3806389"},"language":"en","primary_location":{"id":"doi:10.1145/3806389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806389","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3806389","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134892675","display_name":"Jing Li","orcid":"https://orcid.org/0009-0000-3411-3140"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["College of Science and Technology, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0009-0000-3411-3140","affiliations":[{"raw_affiliation_string":"College of Science and Technology, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764076","display_name":"Qiufeng Wang","orcid":"https://orcid.org/0000-0002-6196-3092"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiufeng Wang","raw_affiliation_strings":["School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0918-4606","affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134899673","display_name":"Siyuan Wang","orcid":"https://orcid.org/0009-0008-3580-9885"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wang","raw_affiliation_strings":["School of Mathematics and Physics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-3580-9885","affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134881583","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8104-5432"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["School of Mathematics and Physics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8104-5432","affiliations":[{"raw_affiliation_string":"School of Mathematics and Physics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134885772","display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Digital Innovation Research Center, Duke Kunshan University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3034-9639","affiliations":[{"raw_affiliation_string":"Digital Innovation Research Center, Duke Kunshan University, Suzhou, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134885514","display_name":"Erik Cambria","orcid":"https://orcid.org/0000-0002-3030-1280"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Erik Cambria","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3030-1280","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.50410812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"6","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.36550000309944153,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.36550000309944153,"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":0.18279999494552612,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.09570000320672989,"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/oracle","display_name":"Oracle","score":0.9085999727249146},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6710000038146973},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6421999931335449},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5848000049591064},{"id":"https://openalex.org/keywords/glyph","display_name":"Glyph (data visualization)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4629000127315521},{"id":"https://openalex.org/keywords/oracle-unified-method","display_name":"Oracle Unified Method","score":0.4503999948501587}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.9085999727249146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859000027179718},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6421999931335449},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.5447999835014343},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625999927520752},{"id":"https://openalex.org/C22664368","wikidata":"https://www.wikidata.org/wiki/Q4045949","display_name":"Oracle Unified Method","level":5,"score":0.4503999948501587},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3488999903202057},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806389","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3806389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806389","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.573101818561554,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7341722744","display_name":null,"funder_award_id":"92370119, 62376113, and 62276258","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2904573478","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963802693","https://openalex.org/W2964350391","https://openalex.org/W2965378892","https://openalex.org/W2981515171","https://openalex.org/W3003466563","https://openalex.org/W3004249119","https://openalex.org/W3108009117","https://openalex.org/W3108255684","https://openalex.org/W3108316907","https://openalex.org/W3110137169","https://openalex.org/W3196600796","https://openalex.org/W4247050319","https://openalex.org/W4283794091","https://openalex.org/W4304083954","https://openalex.org/W4312933868","https://openalex.org/W4313180564","https://openalex.org/W4323647302","https://openalex.org/W4385991130","https://openalex.org/W4385992052","https://openalex.org/W4386066434","https://openalex.org/W4390873054","https://openalex.org/W4393148042","https://openalex.org/W4399813700"],"related_works":[],"abstract_inverted_index":{"Recognizing":[0],"oracle":[1,23,46,60,90,117,135,230,237],"bone":[2],"scripts":[3],"plays":[4],"an":[5,144],"important":[6],"role":[7],"in":[8,186,220],"Chinese":[9],"archaeology":[10],"and":[11,140,175,189,224],"philology.":[12],"However,":[13],"a":[14,33,41,80,99,104,158,204,216,233],"significant":[15],"challenge":[16,56],"remains":[17],"because":[18],"of":[19,22,44,52,57,112],"the":[20,55,110,125,152,210,221],"scarcity":[21],"character":[24,61,91,136,238],"images.":[25,170],"To":[26],"overcome":[27],"this":[28],"issue,":[29],"we":[30,131],"propose":[31],"Diff-Oracle,":[32],"novel":[34],"multi-modal":[35],"conditional":[36],"diffusion":[37,70],"model":[38],"that":[39,72,120,179],"generates":[40],"diverse":[42],"range":[43],"controllable":[45],"characters":[47,122],"by":[48,78,143,203],"inputting":[49],"random":[50],"combinations":[51],"references.":[53],"Given":[54],"accurately":[58,123],"describing":[59],"styles":[62],"using":[63],"natural":[64],"language,":[65],"Diff-Oracle":[66,156,180,192,214],"departs":[67],"from":[68,88,167],"traditional":[69],"models":[71],"rely":[73],"primarily":[74],"on":[75,173,209],"text":[76,100],"prompts":[77,87],"introducing":[79],"style":[81,86,94,139],"encoder.":[82],"This":[83],"encoder":[84,160],"extracts":[85],"existing":[89,183,200],"images,":[92],"where":[93],"details":[95,166],"are":[96],"converted":[97],"into":[98],"embedding":[101],"format":[102],"via":[103],"pre-trained":[105],"language-vision":[106],"model.":[107],"Additionally,":[108],"given":[109],"lack":[111],"explicit":[113],"content":[114,141,149,159,165,168],"information":[115,150],"for":[116,151,228,236],"characters,":[118,231],"ensuring":[119],"generated":[121],"represent":[124],"intended":[126],"glyphs":[127],"is":[128,242],"challenging.":[129],"Therefore,":[130],"pre-generate":[132],"pixel-level":[133],"paired":[134],"images":[137],"(i.e.,":[138],"images)":[142],"image-to-image":[145],"translation":[146],"model,":[147],"providing":[148],"generation":[153],"process.":[154],"Meanwhile,":[155],"integrates":[157],"designed":[161],"to":[162],"capture":[163],"specific":[164],"reference":[169],"Extensive":[171],"experiments":[172],"Oracle-241":[174],"OBC306":[176,212],"datasets":[177],"demonstrate":[178],"significantly":[181],"outperforms":[182],"generative":[184],"methods":[185,202],"image":[187],"quality":[188],"diversity.":[190],"Moreover,":[191],"substantially":[193],"benefits":[194],"downstream":[195],"recognition":[196],"tasks,":[197],"outperforming":[198],"all":[199],"state-of-the-art":[201],"large":[205],"margin.":[206],"In":[207],"particular,":[208],"challenging":[211],"dataset,":[213],"achieves":[215],"7.70%":[217],"accuracy":[218,227],"gain":[219],"zero-shot":[222],"setting":[223,232],"reaches":[225],"84.62%":[226],"unseen":[229],"new":[234],"benchmark":[235],"recognition.":[239],"The":[240],"code":[241],"available":[243],"at":[244],"https://github.com/JJJingLi/Diff-Oracle":[245],".":[246]},"counts_by_year":[],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2026-05-01T00:00:00"}