{"id":"https://openalex.org/W4415540420","doi":"https://doi.org/10.1145/3746027.3754792","title":"Text-to-Image Generation with Multi-modal Knowledge Graph Construction and Retrieval","display_name":"Text-to-Image Generation with Multi-modal Knowledge Graph Construction and Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540420","doi":"https://doi.org/10.1145/3746027.3754792"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754792","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5113115069","display_name":"Jiawei Meng","orcid":"https://orcid.org/0009-0000-7815-1333"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiawei Meng","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0000-7815-1333","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109625114","display_name":"Zhengmao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengmao Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-9919-3678","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiqiang Liu","orcid":"https://orcid.org/0009-0009-5656-6859"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Liu","raw_affiliation_strings":["Ant Group, Hangzhou, Zhejiang, China","Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-5656-6859","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, Zhejiang, China","institution_ids":[]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaokai Chen","orcid":"https://orcid.org/0009-0008-5247-1820"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaokai Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0008-5247-1820","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhizhen Liu","orcid":"https://orcid.org/0009-0004-3511-5139"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhizhen Liu","raw_affiliation_strings":["Ant Group, Hangzhou, Zhejiang, China","Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-3511-5139","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, Zhejiang, China","institution_ids":[]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023045386","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0001-8429-9326"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["Zhejiang University, Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8429-9326","affiliations":[{"raw_affiliation_string":"Zhejiang University, Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102018239","display_name":"Huajun Chen","orcid":"https://orcid.org/0000-0001-5496-7442"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huajun Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China and Zhejiang University-Ant Group Joint Laboratory of Knowledge Graph, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5496-7442","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China and Zhejiang University-Ant Group Joint Laboratory of Knowledge Graph, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113115069"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28947661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5316","last_page":"5325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9930999875068665,"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/scalability","display_name":"Scalability","score":0.620199978351593},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5838000178337097},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5123999714851379},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5016999840736389},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4959999918937683},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47099998593330383},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46399998664855957},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824000120162964},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171999931335449},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5016999840736389},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3246000111103058},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2531000077724457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754792","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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":17,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W3003265726","https://openalex.org/W3174525637","https://openalex.org/W3176182290","https://openalex.org/W4224035735","https://openalex.org/W4312388283","https://openalex.org/W4312933868","https://openalex.org/W4365421094","https://openalex.org/W4386076027","https://openalex.org/W4386556027","https://openalex.org/W4389421838","https://openalex.org/W4389523960","https://openalex.org/W4389984066","https://openalex.org/W4390872247","https://openalex.org/W4391709523","https://openalex.org/W4392638288","https://openalex.org/W4403852017"],"related_works":[],"abstract_inverted_index":{"Current":[0],"Text-to-Image":[1],"(T2I)":[2],"generation":[3,37,55,100],"methods":[4,124],"struggle":[5],"to":[6,46,78,103],"accurately":[7],"create":[8],"images":[9,63],"with":[10,136],"complex":[11],"object":[12],"relationships":[13],"and":[14,60,97,106,116,129,162],"scene":[15],"compositions.":[16],"To":[17],"overcome":[18],"these":[19],"challenges,":[20],"we":[21],"propose":[22],"KAIG,":[23],"a":[24,31,69],"novel":[25],"text-to-image":[26],"generative":[27],"model":[28],"that":[29,119],"integrates":[30],"knowledge":[32,45],"graph":[33],"into":[34],"the":[35,48,54,85,98,164],"image":[36,99,127,167],"process.":[38],"Unlike":[39],"traditional":[40],"models,":[41],"KAIG":[42,120,132,150],"uses":[43],"structured":[44],"enhance":[47],"retrieval":[49],"of":[50,56,166],"relevant":[51],"information,":[52],"enabling":[53],"high-quality,":[57],"contextually":[58],"rich,":[59],"semantically":[61],"consistent":[62],"from":[64],"multi-modal":[65,80],"inputs.":[66],"We":[67],"introduce":[68],"two-stage":[70],"training":[71,144],"strategy:":[72],"first,":[73],"condition":[74],"adapters":[75],"are":[76],"trained":[77],"align":[79],"inputs,":[81],"followed":[82],"by":[83],"fine-tuning":[84],"entire":[86],"diffusion":[87,139],"model.":[88],"This":[89],"approach":[90],"ensures":[91],"precise":[92],"alignment":[93],"between":[94],"retrieved":[95],"conditions":[96],"process,":[101],"leading":[102],"an":[104],"efficient":[105],"scalable":[107],"pipeline.":[108],"Our":[109],"experiments":[110],"on":[111],"two":[112],"popular":[113],"datasets,":[114],"MS-COCO":[115],"CUB-200-2011,":[117],"show":[118],"consistently":[121],"outperforms":[122],"existing":[123],"in":[125,158],"both":[126],"quality":[128],"consistency.":[130],"Notably,":[131],"can":[133],"seamlessly":[134],"integrate":[135],"any":[137],"pre-trained":[138],"model,":[140],"requiring":[141],"minimal":[142],"additional":[143],"while":[145],"achieving":[146],"superior":[147],"results.":[148],"Ultimately,":[149],"demonstrates":[151],"strong":[152],"potential":[153],"for":[154],"addressing":[155],"key":[156],"limitations":[157],"current":[159],"T2I":[160],"models":[161],"advancing":[163],"field":[165],"synthesis.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}