{"id":"https://openalex.org/W4392909361","doi":"https://doi.org/10.1109/icassp48485.2024.10447042","title":"Fast Personalized Text to Image Synthesis with Attention Injection","display_name":"Fast Personalized Text to Image Synthesis with Attention Injection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909361","doi":"https://doi.org/10.1109/icassp48485.2024.10447042"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100319895","display_name":"Yuxuan Zhang","orcid":"https://orcid.org/0000-0001-6905-3993"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019405339","display_name":"Yiren Song","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiren Song","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398288","display_name":"Jinpeng Yu","orcid":"https://orcid.org/0000-0002-4936-8637"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng Yu","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103271991","display_name":"Han Pan","orcid":"https://orcid.org/0000-0003-1574-3213"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Pan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032543777","display_name":"Zhongliang Jing","orcid":"https://orcid.org/0000-0003-1759-8785"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongliang Jing","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0219,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75437911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6195","last_page":"6199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9416999816894531,"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":0.9416999816894531,"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":0.9010999798774719,"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":0.6494870185852051},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5304322242736816},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.443861722946167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38238850235939026},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3448311686515808},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33906230330467224},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33191293478012085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494870185852051},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5304322242736816},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.443861722946167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38238850235939026},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3448311686515808},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33906230330467224},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33191293478012085}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":28,"referenced_works":["https://openalex.org/W2115252128","https://openalex.org/W2962770929","https://openalex.org/W3034600949","https://openalex.org/W3153469116","https://openalex.org/W3166396011","https://openalex.org/W4289785045","https://openalex.org/W4289785095","https://openalex.org/W4306820534","https://openalex.org/W4362679705","https://openalex.org/W4385527149","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4389539268","https://openalex.org/W4389539271","https://openalex.org/W4389539696","https://openalex.org/W4390872341","https://openalex.org/W4390874393","https://openalex.org/W4402753775","https://openalex.org/W6677618333","https://openalex.org/W6791353385","https://openalex.org/W6793547449","https://openalex.org/W6796581206","https://openalex.org/W6841366371","https://openalex.org/W6841755765","https://openalex.org/W6846007759","https://openalex.org/W6852049015","https://openalex.org/W6852060089"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2779427294","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2069885731","https://openalex.org/W2563206327","https://openalex.org/W2108687567","https://openalex.org/W2789220062"],"abstract_inverted_index":{"Currently,":[0],"personalized":[1,59,102],"image":[2,51],"generation":[3,69],"methods":[4],"mostly":[5],"require":[6],"considerable":[7],"time":[8],"to":[9,23,28,100],"finetune":[10],"and":[11,36,45,52,77,92],"often":[12],"overfit":[13],"the":[14,42,49,66,83,96,106,112],"concept":[15,85],"resulting":[16],"in":[17],"generated":[18,50,87],"images":[19,60,88,103],"that":[20,39,104],"are":[21],"similar":[22],"custom":[24,84],"concepts":[25],"but":[26],"difficult":[27],"edit":[29],"by":[30,89],"prompts.":[31],"We":[32],"propose":[33],"an":[34],"effective":[35],"fast":[37],"approach":[38],"could":[40],"balance":[41],"text-image":[43],"consistency":[44,47],"identity":[46],"of":[48,71,95,114],"reference":[53,79],"image.":[54],"Our":[55],"method":[56],"can":[57],"generate":[58,101],"without":[61],"any":[62],"fine-tuning":[63],"while":[64],"maintaining":[65],"inherent":[67],"text-to-image":[68],"ability":[70],"diffusion":[72,98],"models.":[73],"Given":[74],"a":[75,78],"prompt":[76],"image,":[80],"we":[81],"merge":[82],"into":[86],"manipulating":[90],"cross-attention":[91],"self-attention":[93],"layers":[94],"original":[97],"model":[99],"match":[105],"text":[107],"description.":[108],"Comprehensive":[109],"experiments":[110],"highlight":[111],"superiority":[113],"our":[115],"method.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}