{"id":"https://openalex.org/W7138145809","doi":"https://doi.org/10.1609/aaai.v40i5.37367","title":"DEIG: Detail-Enhanced Instance Generation with Fine-Grained Semantic Control","display_name":"DEIG: Detail-Enhanced Instance Generation with Fine-Grained Semantic Control","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138145809","doi":"https://doi.org/10.1609/aaai.v40i5.37367"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37367","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37367","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i5.37367","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shiyan Du","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyan Du","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Conghan Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conghan Yue","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyu Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Cheng","raw_affiliation_strings":["Yale University, New Haven, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, United States","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dongyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyu Zhang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25291966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3677","last_page":"3685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9534000158309937,"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":0.9534000158309937,"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":0.009999999776482582,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006399999838322401,"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/encoder","display_name":"Encoder","score":0.5774000287055969},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.486299991607666},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4700999855995178},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.37549999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245000243186951},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357999801635742},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37367","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37367","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37367","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37367","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37367","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-Instance":[0],"Generation":[1],"has":[2],"advanced":[3],"significantly":[4],"in":[5,17,138],"spatial":[6,139],"placement":[7],"and":[8,39,59,120,126,143],"attribute":[9,72],"binding.":[10],"However,":[11],"existing":[12,133],"approaches":[13,134],"still":[14],"face":[15],"challenges":[16],"fine-grained":[18,38,95],"semantic":[19,141],"understanding,":[20],"particularly":[21],"when":[22],"dealing":[23],"with":[24,102,117],"complex":[25],"textual":[26,91],"descriptions.To":[27],"overcome":[28],"these":[29],"limitations,":[30],"we":[31,97],"propose":[32],"DEIG,":[33],"a":[34,60,99,114,150],"novel":[35],"framework":[36],"for":[37,123],"controllable":[40],"multi-instance":[41,84],"generation.":[42],"DEIG":[43,79,130,147],"integrates":[44],"an":[45],"instance":[46,105],"Detail":[47,61],"Extractor":[48],"(IDE)":[49],"that":[50,65,86,129],"transforms":[51],"text":[52],"encoder":[53],"embeddings":[54],"into":[55,157],"compact,":[56],"instance-aware":[57],"representations,":[58],"Fusion":[62],"Module":[63],"(DFM)":[64],"applies":[66],"instance-based":[67],"masked":[68],"attention":[69],"to":[70,80],"prevent":[71],"leakage":[73],"across":[74,135],"instances.":[75],"These":[76],"components":[77],"enable":[78],"generate":[81],"visually":[82],"coherent":[83],"scenes":[85],"precisely":[87],"match":[88],"rich,":[89],"localized":[90],"descriptions.":[92],"To":[93],"support":[94],"supervision,":[96],"construct":[98],"high-quality":[100],"dataset":[101],"detailed,":[103],"compositional":[104,144],"captions":[106],"generated":[107],"by":[108],"VLMs.":[109],"We":[110],"also":[111],"introduce":[112],"DEIG-Bench,":[113],"new":[115],"benchmark":[116],"region-level":[118],"annotations":[119],"multi-attribute":[121],"prompts":[122],"both":[124],"humans":[125],"objects.Experiments":[127],"demonstrate":[128],"consistently":[131],"outperforms":[132],"multiple":[136],"benchmarks":[137],"consistency,":[140],"accuracy,":[142],"generalization.":[145],"Moreover,":[146],"functions":[148],"as":[149],"plug-and-play":[151],"module,":[152],"making":[153],"it":[154],"easily":[155],"integrable":[156],"standard":[158],"diffusion-based":[159],"pipelines.":[160]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-27T00:00:00"}