{"id":"https://openalex.org/W7125944302","doi":"https://doi.org/10.1109/smc58881.2025.11342862","title":"RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation","display_name":"RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125944302","doi":"https://doi.org/10.1109/smc58881.2025.11342862"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5101640227","display_name":"Geon Park","orcid":"https://orcid.org/0000-0002-6878-2649"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geon Park","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124140404","display_name":"Seon Bin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seon Bin Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036774708","display_name":"Gunho Jung","orcid":"https://orcid.org/0000-0002-1143-9663"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunho Jung","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124139481","display_name":"Seong-Whan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6371","last_page":"6376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8884999752044678,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8884999752044678,"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":0.022099999710917473,"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":0.008700000122189522,"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/relation","display_name":"Relation (database)","score":0.6694999933242798},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.43869999051094055},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406000256538391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5971999764442444},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5290105938911438}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1973181164","https://openalex.org/W2104558951","https://openalex.org/W2129169401","https://openalex.org/W2962845008","https://openalex.org/W3212535881","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4386066731","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4390872387","https://openalex.org/W4390873429","https://openalex.org/W4394625750","https://openalex.org/W4402623742","https://openalex.org/W4402715994","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"With":[0],"recent":[1],"advancements":[2],"in":[3,25,99],"text-to-image":[4],"(T2I)":[5],"models,":[6],"effectively":[7],"generating":[8,26,118],"multiple":[9,39,102,126],"instances":[10],"within":[11,131],"a":[12,18],"single":[13],"image":[14,65],"prompt":[15],"has":[16],"become":[17],"crucial":[19],"challenge.":[20],"Existing":[21],"methods,":[22,95],"while":[23],"successful":[24],"positions":[27],"of":[28,128],"individual":[29],"instances,":[30],"often":[31],"struggle":[32],"to":[33],"account":[34],"for":[35,117],"relationship":[36],"discrepancy":[37],"and":[38,62,87,105,125],"attributes":[40,58,103,127],"leakage.":[41],"To":[42],"address":[43],"these":[44],"limitations,":[45],"this":[46],"paper":[47],"proposes":[48],"the":[49,75,106,115,123,132],"relation-aware":[50,64],"disentangled":[51],"learning":[52],"(RaDL)":[53],"framework.":[54],"RaDL":[55,92,113],"enhances":[56],"instance-specific":[57],"through":[59],"learnable":[60],"parameters":[61],"generates":[63],"features":[66],"via":[67],"Relation":[68],"Attention,":[69],"utilizing":[70],"action":[71],"verbs":[72],"extracted":[73],"from":[74],"global":[76],"prompt.":[77],"Through":[78],"extensive":[79],"evaluations":[80],"on":[81],"benchmarks":[82],"such":[83],"as":[84,114],"COCO-Position,":[85],"COCO-MIG,":[86],"DrawBench,":[88],"we":[89],"demonstrate":[90],"that":[91,120],"outperforms":[93],"existing":[94],"showing":[96],"significant":[97],"improvements":[98],"positional":[100],"accuracy,":[101],"consideration,":[104],"relationships":[107,124],"between":[108],"instances.":[109],"Our":[110],"results":[111],"present":[112],"solution":[116],"images":[119],"consider":[121],"both":[122],"each":[129],"instance":[130],"multi-instance":[133],"image.":[134]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}