{"id":"https://openalex.org/W4406610835","doi":"https://doi.org/10.1109/tcsvt.2025.3531917","title":"CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image Personalization","display_name":"CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image Personalization","publication_year":2025,"publication_date":"2025-01-20","ids":{"openalex":"https://openalex.org/W4406610835","doi":"https://doi.org/10.1109/tcsvt.2025.3531917"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3531917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3531917","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5101999278","display_name":"Ruoyu Zhao","orcid":"https://orcid.org/0000-0001-5193-8419"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruoyu Zhao","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076459579","display_name":"Mingrui Zhu","orcid":"https://orcid.org/0000-0002-4179-7701"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Zhu","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114049152","display_name":"Shiyin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Dong","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067159497","display_name":"De Cheng","orcid":"https://orcid.org/0000-0003-4603-847X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"De Cheng","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042507268","display_name":"Nannan Wang","orcid":"https://orcid.org/0000-0002-4695-6134"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Wang","raw_affiliation_strings":["State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Telecommunications Engineering, State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0003-1443-0776"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101999278"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":10.9627,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.98318116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"6","first_page":"6047","last_page":"6058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8137000203132629,"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":0.8137000203132629,"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/T10862","display_name":"AI in cancer detection","score":0.796500027179718,"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"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7944999933242798,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.631943941116333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5273017883300781},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4962490200996399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46882885694503784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3888521194458008},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3686496317386627},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19349372386932373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.631943941116333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5273017883300781},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4962490200996399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46882885694503784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3888521194458008},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3686496317386627},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19349372386932373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3531917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3531917","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2452297484","display_name":null,"funder_award_id":"QTZX23042","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3837195626","display_name":null,"funder_award_id":"20230121","funder_id":"https://openalex.org/F4320331108","funder_display_name":"Hunan Association for Science and Technology"},{"id":"https://openalex.org/G4297946667","display_name":null,"funder_award_id":"U22A2096","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4638375856","display_name":null,"funder_award_id":"KYFZ24012","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4726732360","display_name":null,"funder_award_id":"2023YFA1008600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8956037067","display_name":null,"funder_award_id":"62106184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G913836228","display_name":null,"funder_award_id":"62036007","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"},{"id":"https://openalex.org/F4320331108","display_name":"Hunan Association for Science and Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1972661442","https://openalex.org/W2152227675","https://openalex.org/W2752796333","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963612019","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2966792645","https://openalex.org/W3122490299","https://openalex.org/W3173102319","https://openalex.org/W3212516020","https://openalex.org/W4220899212","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4380451230","https://openalex.org/W4385245566","https://openalex.org/W4385271055","https://openalex.org/W4385535331","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4389160105","https://openalex.org/W4389334989","https://openalex.org/W4389539271","https://openalex.org/W4390872341","https://openalex.org/W4390874393","https://openalex.org/W4391952636","https://openalex.org/W4392151693","https://openalex.org/W4396605141","https://openalex.org/W4402774647","https://openalex.org/W4404984122","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6788990321","https://openalex.org/W6790978476","https://openalex.org/W6791276965","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6796242362","https://openalex.org/W6802744804","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6839328737","https://openalex.org/W6841755765","https://openalex.org/W6849437247","https://openalex.org/W6850716399","https://openalex.org/W6850995708","https://openalex.org/W6851800889","https://openalex.org/W6852885189","https://openalex.org/W6852912373","https://openalex.org/W6854511533","https://openalex.org/W6862995742"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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],"propose":[1],"CatVersion,":[2],"an":[3],"inversion-based":[4],"method":[5,59],"that":[6,25,39],"learns":[7],"the":[8,27,48,63,67,71,76,79,89,99,108,113,119,123,130,139,142,152,161,171,179],"personalized":[9,28,80,100,143,174],"concept":[10,54,81,144],"through":[11],"a":[12,158],"handful":[13],"of":[14,66,91,122,173],"examples.":[15],"Subsequently,":[16],"users":[17],"can":[18],"utilize":[19],"text":[20,68,109],"prompts":[21],"to":[22,36,74,87,117,137,192],"generate":[23],"images":[24],"embody":[26],"concept,":[29],"thereby":[30],"achieving":[31],"text-to-image":[32],"personalization.":[33],"In":[34,149],"contrast":[35],"existing":[37],"approaches":[38],"emphasize":[40],"word":[41],"embedding":[42],"learning":[43],"or":[44,56],"parameter":[45],"fine-tuning":[46],"for":[47],"diffusion":[49,72,95],"model,":[50],"which":[51],"potentially":[52],"causes":[53],"dilution":[55],"overfitting,":[57],"our":[58],"concatenates":[60],"embeddings":[61,128,154],"on":[62,129,160,185],"feature-dense":[64,120],"space":[65,121,136],"encoder":[69],"in":[70,94,112,134],"model":[73],"learn":[75,138],"gap":[77,140],"between":[78,141],"and":[82,132,145,168,188,198],"its":[83,146],"base":[84,147],"class,":[85],"aiming":[86],"maximize":[88],"preservation":[90],"prior":[92],"knowledge":[93],"models":[96],"while":[97],"restoring":[98],"concepts.":[101],"To":[102,165],"this":[103,135,150],"end,":[104],"we":[105,126,177],"first":[106],"dissect":[107],"encoder\u2019s":[110],"integration":[111],"image":[114,175,181],"generation":[115],"process":[116],"identify":[118],"encoder.":[124],"Afterward,":[125],"concatenate":[127],"Keys":[131],"Values":[133],"class.":[148],"way,":[151],"concatenated":[153],"ultimately":[155],"manifest":[156],"as":[157],"residual":[159],"original":[162],"attention":[163],"output.":[164],"more":[166,196,200],"accurately":[167],"unbiasedly":[169],"quantify":[170],"results":[172],"generation,":[176],"improve":[178],"CLIP":[180],"alignment":[182],"score":[183],"based":[184],"masks.":[186],"Qualitatively":[187],"quantitatively,":[189],"CatVersion":[190],"helps":[191],"restore":[193],"personalization":[194],"concepts":[195],"faithfully":[197],"enables":[199],"robust":[201],"editing.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":9}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}