{"id":"https://openalex.org/W4400573550","doi":"https://doi.org/10.1145/3641519.3657469","title":"Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","display_name":"Subject-Diffusion: Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400573550","doi":"https://doi.org/10.1145/3641519.3657469"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103483218","display_name":"Jian Ma","orcid":"https://orcid.org/0009-0004-0057-3033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Ma","raw_affiliation_strings":["OPPO AI Center, China"],"raw_orcid":"https://orcid.org/0009-0004-0057-3033","affiliations":[{"raw_affiliation_string":"OPPO AI Center, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408915","display_name":"Junhao Liang","orcid":"https://orcid.org/0000-0001-5612-7631"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Liang","raw_affiliation_strings":["Southern University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-5612-7631","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418563","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3498-2527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["OPPO AI Center, China"],"raw_orcid":"https://orcid.org/0000-0003-3498-2527","affiliations":[{"raw_affiliation_string":"OPPO AI Center, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007720098","display_name":"H. Lu","orcid":"https://orcid.org/0000-0001-6332-2785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["OPPO AI Center, China"],"raw_orcid":"https://orcid.org/0000-0001-6332-2785","affiliations":[{"raw_affiliation_string":"OPPO AI Center, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.7355373501777649},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5545778870582581},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49122709035873413},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4879162013530731},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4554452896118164},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4458789527416229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4331486225128174},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37640196084976196},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32955271005630493},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3211566209793091},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16530722379684448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11867484450340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355373501777649},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5545778870582581},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49122709035873413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4879162013530731},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4554452896118164},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4458789527416229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4331486225128174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37640196084976196},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32955271005630493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3211566209793091},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16530722379684448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11867484450340271},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641519.3657469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","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":22,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2507296351","https://openalex.org/W2561196672","https://openalex.org/W2948672349","https://openalex.org/W3036167779","https://openalex.org/W3135367836","https://openalex.org/W3159481202","https://openalex.org/W4281485151","https://openalex.org/W4288083516","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4386075639","https://openalex.org/W4386076027","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W6600075759","https://openalex.org/W6600100092","https://openalex.org/W6601101894","https://openalex.org/W6601158201","https://openalex.org/W6601676141","https://openalex.org/W6602344735","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W4318064328","https://openalex.org/W2357926602","https://openalex.org/W3200517220","https://openalex.org/W2374569605","https://openalex.org/W2955606923","https://openalex.org/W2990774877","https://openalex.org/W3093339210"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,14,43,65,157],"personalized":[3,22,38,59],"image":[4,23,39,56,113,122,162],"generation":[5,24,40,60],"using":[6],"diffusion":[7],"models":[8],"has":[9],"been":[10],"significant.":[11],"However,":[12],"development":[13],"the":[15,78],"area":[16],"of":[17,61,87],"open-domain":[18,37],"and":[19,76,90,99,112,119,128,144,160],"test-time":[20,48],"fine-tuning-free":[21],"is":[25],"proceeding":[26],"rather":[27],"slowly.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,69,103,131],"propose":[33],"Subject-Diffusion,":[34],"a":[35,53,83,105],"novel":[36],"model":[41],"that,":[42],"addition":[44],"to":[45,57,81,124,138],"not":[46],"requiring":[47],"fine-tuning,":[49],"also":[50,132],"only":[51],"requires":[52],"single":[54],"reference":[55,121],"support":[58,139],"single-":[62],"or":[63],"two-subjects":[64],"any":[66],"domain.":[67],"Firstly,":[68],"construct":[70,82],"an":[71,134],"automatic":[72],"data":[73],"labeling":[74],"tool":[75],"use":[77],"LAION-Aesthetics":[79],"dataset":[80,85],"large-scale":[84],"consisting":[86],"76M":[88],"images":[89],"their":[91],"corresponding":[92],"subject":[93,126],"detection":[94],"bounding":[95],"boxes,":[96],"segmentation":[97],"masks,":[98],"text":[100,111],"descriptions.":[101],"Secondly,":[102],"design":[104],"new":[106],"unified":[107],"framework":[108],"that":[109,148],"combines":[110],"semantics":[114],"by":[115],"incorporating":[116],"coarse":[117],"location":[118],"fine-grained":[120],"control":[123,136],"maximize":[125],"fidelity":[127],"generalization.":[129],"Furthermore,":[130],"adopt":[133],"attention":[135],"mechanism":[137],"two-subject":[140],"generation.":[141,163],"Extensive":[142],"qualitative":[143],"quantitative":[145],"results":[146],"demonstrate":[147],"our":[149],"method":[150],"have":[151],"certain":[152],"advantages":[153],"over":[154],"other":[155],"frameworks":[156],"single,":[158],"multiple,":[159],"human-customized":[161]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":24}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}