{"id":"https://openalex.org/W4403792157","doi":"https://doi.org/10.1145/3664647.3680621","title":"Customizing Text-to-Image Generation with Inverted Interaction","display_name":"Customizing Text-to-Image Generation with Inverted Interaction","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792157","doi":"https://doi.org/10.1145/3664647.3680621"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101903528","display_name":"Mengmeng Ge","orcid":"https://orcid.org/0009-0003-1301-1323"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengmeng Ge","raw_affiliation_strings":["Advanced Micro Devices, Inc. &amp; Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc. &amp; Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067168484","display_name":"Xu Jia","orcid":"https://orcid.org/0000-0003-3168-3505"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Jia","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111821872","display_name":"Takashi Isobe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Isobe","raw_affiliation_strings":["Advanced Micro Devices, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635377","display_name":"Xiaomin Li","orcid":"https://orcid.org/0000-0001-7202-6865"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomin Li","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020704860","display_name":"Qinghe Wang","orcid":"https://orcid.org/0000-0001-6908-5485"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghe Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101464630","display_name":"Jing Mu","orcid":"https://orcid.org/0000-0003-4812-1111"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Mu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087583644","display_name":"Dong Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Zhou","raw_affiliation_strings":["Advanced Micro Devices, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382450","display_name":"Wang Li","orcid":"https://orcid.org/0009-0008-3347-1518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Advanced Micro Devices, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365670","display_name":"Lu Tian","orcid":"https://orcid.org/0009-0007-6734-1984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Tian","raw_affiliation_strings":["Advanced Micro Devices, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086949543","display_name":"Ashish Sirasao","orcid":"https://orcid.org/0009-0004-7828-0871"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Sirasao","raw_affiliation_strings":["Advanced Micro Devices, Inc., San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., San Jose, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027115167","display_name":"Emad Barsoum","orcid":"https://orcid.org/0000-0002-4097-8690"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emad Barsoum","raw_affiliation_strings":["Advanced Micro Devices, Inc., San Jose, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., San Jose, USA","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5101903528"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67110934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"10901","last_page":"10909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T12290","display_name":"Human Motion and Animation","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958000183105469,"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":0.7086665630340576},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.6952309608459473},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4728914797306061},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.4660875201225281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39795786142349243},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36511707305908203},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35051649808883667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086665630340576},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.6952309608459473},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4728914797306061},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.4660875201225281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39795786142349243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36511707305908203},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35051649808883667},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680621","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2423576022","https://openalex.org/W2559085405","https://openalex.org/W4293342478","https://openalex.org/W4312933868","https://openalex.org/W4386071613","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4402728006"],"related_works":["https://openalex.org/W2124379162","https://openalex.org/W2805651586","https://openalex.org/W1604458106","https://openalex.org/W2970215257","https://openalex.org/W3209232512","https://openalex.org/W3112768174","https://openalex.org/W2104956440","https://openalex.org/W2382673214","https://openalex.org/W2154619320","https://openalex.org/W2383319806"],"abstract_inverted_index":{"Subject-driven":[0],"image":[1,91],"generation,":[2],"aimed":[3],"at":[4],"customizing":[5],"user-specified":[6,190],"subjects,":[7],"has":[8],"experienced":[9],"rapid":[10],"progress.":[11],"However,":[12],"most":[13],"of":[14,22,49,89,96,125,139,162],"them":[15],"focus":[16],"on":[17],"transferring":[18,45],"the":[19,37,46,57,80,87,129,137,140,143,155,160,168,176,186],"customized":[20,53,187],"appearance":[21],"subjects.":[23,97],"In":[24,73,145],"this":[25,100],"work,":[26],"we":[27,102],"consider":[28],"a":[29,70,104,109,119,122],"novel":[30],"concept":[31,48,141],"customization":[32],"task,":[33,101],"that":[34,167],"is,":[35],"capturing":[36],"interaction":[38,50,58,81,111],"between":[39,59,82],"subjects":[40,60],"in":[41,68,128],"exemplar":[42,76,180],"images":[43,77,181],"and":[44,63,107,149,182],"learned":[47],"to":[51,66,135,158,173,185],"achieve":[52],"text-to-image":[54],"generation.":[55],"Intrinsically,":[56],"is":[61,64,132],"diverse":[62],"difficult":[65],"describe":[67],"only":[69],"few":[71],"words.":[72],"addition,":[74,146],"typical":[75],"are":[78,152,171],"about":[79],"humans,":[83],"which":[84],"further":[85],"intensifies":[86],"challenge":[88],"interaction-driven":[90],"generation":[92,188],"with":[93,189],"various":[94],"categories":[95],"To":[98],"address":[99],"adopt":[103],"divide-and-conquer":[105],"strategy":[106],"propose":[108],"two-stage":[110],"inversion":[112],"framework.":[113],"The":[114],"framework":[115],"begins":[116],"by":[117],"learning":[118,138],"pseudo-word":[120],"for":[121,142],"single":[123],"pose":[124,178],"each":[126],"subject":[127],"interaction.":[130,144,163,191],"This":[131],"then":[133],"employed":[134],"promote":[136],"language":[147],"prior":[148],"cross-attention":[150],"loss":[151],"incorporated":[153],"into":[154],"optimization":[156],"process":[157],"encourage":[159],"modeling":[161],"Extensive":[164],"experiments":[165],"demonstrate":[166],"proposed":[169],"methods":[170],"able":[172],"effectively":[174],"invert":[175],"interactive":[177],"from":[179],"apply":[183],"it":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
