{"id":"https://openalex.org/W4415333272","doi":"https://doi.org/10.1109/tpami.2025.3623025","title":"RealCustom++: Representing Images as Real Textual Word for Real-Time Customization","display_name":"RealCustom++: Representing Images as Real Textual Word for Real-Time Customization","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415333272","doi":"https://doi.org/10.1109/tpami.2025.3623025","pmid":"https://pubmed.ncbi.nlm.nih.gov/41105542"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3623025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3623025","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5739-8126","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengqi Huang","orcid":"https://orcid.org/0000-0001-9449-4491"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9449-4491","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911810","display_name":"Fei Ding","orcid":"https://orcid.org/0009-0006-5431-4744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Ding","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038933312","display_name":"Mingcong Liu","orcid":"https://orcid.org/0000-0003-1638-8348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingcong Liu","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112317049","display_name":"Qian He","orcid":"https://orcid.org/0009-0009-1932-5802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian He","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1151-1792","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.2488128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"2","first_page":"2078","last_page":"2095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9943000078201294,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9943000078201294,"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/subject","display_name":"Subject (documents)","score":0.7753000259399414},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7297000288963318},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7091000080108643},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5996000170707703},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.46129998564720154},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36090001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353999853134155},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.7753000259399414},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7297000288963318},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7091000080108643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431999802589417},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6105999946594238},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5512999892234802},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3623025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3623025","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41105542","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41105542","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7854910236","display_name":null,"funder_award_id":"62222212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G818119199","display_name":null,"funder_award_id":"623B2094","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":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2133515615","https://openalex.org/W2296073425","https://openalex.org/W2528287124","https://openalex.org/W2962770929","https://openalex.org/W2963163163","https://openalex.org/W2972758308","https://openalex.org/W2982450728","https://openalex.org/W3142849873","https://openalex.org/W3159481202","https://openalex.org/W3173229273","https://openalex.org/W4288083516","https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4385271055","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4386083144","https://openalex.org/W4389347744","https://openalex.org/W4389539271","https://openalex.org/W4390534338","https://openalex.org/W4390872341","https://openalex.org/W4390873312","https://openalex.org/W4390874393","https://openalex.org/W4390874575","https://openalex.org/W4391428899","https://openalex.org/W4393149651","https://openalex.org/W4396909806","https://openalex.org/W4400573550","https://openalex.org/W4402703076","https://openalex.org/W4402704604","https://openalex.org/W4402716297","https://openalex.org/W4402727536","https://openalex.org/W4402753775","https://openalex.org/W4402754193","https://openalex.org/W4402782221","https://openalex.org/W4402816803","https://openalex.org/W4404199212","https://openalex.org/W4409365603"],"related_works":[],"abstract_inverted_index":{"Given":[0],"a":[1,7,38,74,93,102,109,133,142,159],"text":[2,22,47,81,124],"and":[3,23,42,63,80,113,125,148,155,173,220,236,250],"an":[4],"image":[5,112],"of":[6,122,184,213,232,248],"specific":[8,186],"subject,":[9],"text-to-image":[10],"customization":[11],"aims":[12],"to":[13,48,106,180,195],"generate":[14,49,108],"new":[15],"images":[16],"that":[17,97,198],"align":[18],"with":[19,45,69,101,211],"both":[20],"the":[21,24,30,35,52,99,119,123,153,165,169,174,182,185],"subject's":[25],"appearance.":[26],"Existing":[27],"works":[28],"follow":[29],"pseudo-word":[31],"paradigm,":[32],"which":[33],"represents":[34,98],"subject":[36,78,100,115,126,170],"as":[37],"non-existent":[39],"pseudo":[40,53],"word":[41,54,105,188],"combines":[43],"it":[44,140],"other":[46,70],"images.":[50],"However,":[51],"causes":[55],"semantic":[56],"conflict":[57],"from":[58,65],"its":[59],"different":[60],"learning":[61],"objective":[62],"entanglement":[64],"overlapping":[66],"influence":[67,120],"scopes":[68,121],"texts,":[71],"resulting":[72],"in":[73,152,200,209,215,218,222,234,238,246],"dual-optimum":[75],"paradox":[76],"where":[77,164],"similarity":[79],"controllability":[82,202,235],"cannot":[83],"be":[84],"optimal":[85],"simultaneously.":[86],"To":[87],"address":[88],"this,":[89],"we":[90],"propose":[91],"RealCustom++,":[92],"novel":[94],"real-word":[95],"paradigm":[96],"non-conflicting":[103],"real":[104,150,187],"firstly":[107],"coherent":[110],"guidance":[111,171],"corresponding":[114],"mask,":[116],"thereby":[117],"disentangling":[118],"for":[127],"simultaneous":[128],"optimization.":[129],"Specifically,":[130],"RealCustom++":[131,205,228],"introduces":[132],"train-inference":[134],"decoupled":[135],"framework:":[136],"(1)":[137],"during":[138,157],"training,":[139],"learns":[141],"general":[143],"alignment":[144],"between":[145],"visual":[146],"conditions":[147],"all":[149],"words":[151],"text;":[154],"(2)":[156],"inference,":[158],"dual-branch":[160],"architecture":[161],"is":[162],"employed,":[163],"Guidance":[166],"Branch":[167,176],"produces":[168],"mask":[172,179],"Generation":[175],"utilizes":[177],"this":[178],"customize":[181],"generation":[183,223],"exclusively":[189],"within":[190],"subject-relevant":[191],"regions.":[192],"In":[193],"contrast":[194],"previous":[196],"methods":[197],"excel":[199],"either":[201],"or":[203],"similarity,":[204,219],"achieves":[206,230],"superior":[207],"performance":[208],"both,":[210],"improvements":[212,231],"7.48%":[214],"controllability,":[216],"3.04%":[217],"76.43%":[221],"quality.":[224],"For":[225],"multi-subject":[226,239],"customization,":[227],"further":[229],"4.6%":[233],"6.34%":[237],"similarity.":[240],"Our":[241],"work":[242],"has":[243],"been":[244],"applied":[245],"JiMeng":[247],"ByteDance,":[249],"codes":[251],"are":[252],"released":[253],"at":[254],"<uri":[255],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[256],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/bytedance/RealCustom</uri>.":[257]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-19T00:00:00"}
