{"id":"https://openalex.org/W4402727471","doi":"https://doi.org/10.1109/cvpr52733.2024.00782","title":"Personalized Residuals for Concept-Driven Text-to-Image Generation","display_name":"Personalized Residuals for Concept-Driven Text-to-Image Generation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402727471","doi":"https://doi.org/10.1109/cvpr52733.2024.00782"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5029588803","display_name":"Cusuh Ham","orcid":"https://orcid.org/0009-0002-2686-052X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cusuh Ham","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084900583","display_name":"M. Fisher","orcid":"https://orcid.org/0000-0003-3756-1146"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Fisher","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016775802","display_name":"James Hays","orcid":"https://orcid.org/0000-0001-7016-4252"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Hays","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084487169","display_name":"Nicholas Kolkin","orcid":"https://orcid.org/0000-0003-1233-1969"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Kolkin","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373068","display_name":"Yuchen Liu","orcid":"https://orcid.org/0009-0004-0955-5624"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616529","display_name":"Richard Zhang","orcid":"https://orcid.org/0009-0006-0299-1057"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Zhang","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001873096","display_name":"Tobias Hinz","orcid":"https://orcid.org/0000-0003-1354-1562"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tobias Hinz","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5029588803"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.0399,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78114741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8186","last_page":"8195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9959999918937683,"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":0.9959999918937683,"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":0.994700014591217,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.686235785484314},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5216467976570129},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4390799403190613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38545507192611694},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33206796646118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686235785484314},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5216467976570129},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4390799403190613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38545507192611694},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33206796646118164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":45,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1901129140","https://openalex.org/W2081580037","https://openalex.org/W3036167779","https://openalex.org/W3121370741","https://openalex.org/W3159481202","https://openalex.org/W3168867926","https://openalex.org/W3209532394","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4289785045","https://openalex.org/W4289785095","https://openalex.org/W4308163867","https://openalex.org/W4312933868","https://openalex.org/W4365475020","https://openalex.org/W4377121606","https://openalex.org/W4378473834","https://openalex.org/W4379261331","https://openalex.org/W4380559233","https://openalex.org/W4382323274","https://openalex.org/W4385245566","https://openalex.org/W4385270985","https://openalex.org/W4385271055","https://openalex.org/W4385535331","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4390872341","https://openalex.org/W4390874393","https://openalex.org/W4402727368","https://openalex.org/W6640963894","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6791353385","https://openalex.org/W6802987763","https://openalex.org/W6809885388","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6841755765","https://openalex.org/W6846655393","https://openalex.org/W6852306693","https://openalex.org/W6853219534","https://openalex.org/W6853229210","https://openalex.org/W6853453422","https://openalex.org/W6854106264","https://openalex.org/W6855219701"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,100],"present":[1],"personalized":[2,103],"residuals":[3,34,59,104],"and":[4,31,70,128,135],"localized":[5,67,136],"attention-guided":[6],"sampling":[7,53,81,137],"for":[8,35,146],"efficient":[9],"concept-driven":[10],"generation":[11],"using":[12,139],"text-to-image":[13],"diffusion":[14,29,74,98],"models.":[15],"Our":[16],"method":[17],"first":[18],"represents":[19],"concepts":[20],"by":[21],"freezing":[22],"the":[23,40,57,64,72,84,88,91,96,107,123,140,150],"weights":[24,75],"of":[25,39,50,87,95,109,125,149],"a":[26,36,110,119],"pretrained":[27],"text-conditioned":[28],"model":[30,142],"learning":[32],"low-rank":[33],"small":[37],"subset":[38],"model's":[41],"layers.":[42],"The":[43],"residual-based":[44],"approach":[45],"then":[46],"directly":[47],"enables":[48],"application":[49],"our":[51],"proposed":[52],"technique,":[54],"which":[55],"applies":[56,71],"learned":[58,85],"only":[60],"in":[61,76,112],"areas":[62],"where":[63],"concept":[65,89,111],"is":[66],"via":[68],"cross-attention":[69],"original":[73,141],"all":[77],"other":[78],"regions.":[79],"Localized":[80],"therefore":[82],"combines":[83],"identity":[86,108],"with":[90,129],"existing":[92],"generative":[93],"prior":[94,145],"underlying":[97],"model.":[99],"show":[101],"that":[102],"effectively":[105],"capture":[106],"<tex":[113],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\sim$</tex>":[115],"3":[116],"minutes":[117],"on":[118],"single":[120],"GPU":[121],"without":[122],"use":[124],"regularization":[126],"images":[127],"fewer":[130],"parameters":[131],"than":[132],"previous":[133],"models,":[134],"allows":[138],"as":[143],"strong":[144],"large":[147],"parts":[148],"image.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}