{"id":"https://openalex.org/W4385767743","doi":"https://doi.org/10.24963/ijcai.2023/192","title":"Learning Object Consistency and Interaction in Image Generation from Scene Graphs","display_name":"Learning Object Consistency and Interaction in Image Generation from Scene Graphs","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767743","doi":"https://doi.org/10.24963/ijcai.2023/192"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/192","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/192","pdf_url":"https://www.ijcai.org/proceedings/2023/0192.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0192.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114040412","display_name":"Yangkang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"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":"Yangkang Zhang","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112978959","display_name":"Chenye Meng","orcid":"https://orcid.org/0000-0002-4787-6232"},"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":"Chenye Meng","raw_affiliation_strings":["Zhejiang University","School of Software Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Software Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015625724","display_name":"Zejian Li","orcid":"https://orcid.org/0000-0001-5313-2742"},"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":"Zejian Li","raw_affiliation_strings":["Zhejiang University","School of Software Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Software Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326683","display_name":"Pei Chen","orcid":"https://orcid.org/0000-0002-7594-3228"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"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":"Pei Chen","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436471","display_name":"Guang Yang","orcid":"https://orcid.org/0000-0002-9213-2953"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101627882","display_name":"Changyuan Yang","orcid":"https://orcid.org/0000-0003-0065-6272"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changyuan Yang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036387698","display_name":"Lingyun Sun","orcid":"https://orcid.org/0000-0002-5561-0493"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Lingyun Sun","raw_affiliation_strings":["Zhejiang University","College of Computer Science and Technology, Zhejiang University, China","Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1731","last_page":"1739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.7300314903259277},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6219439506530762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6181050539016724},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5984861254692078},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5840086936950684},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5630408525466919},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4687870740890503},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4641360640525818},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45949628949165344},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45618879795074463},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4214904308319092},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4195808470249176},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3556337356567383},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1884889304637909},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.10529491305351257},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06924393773078918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300314903259277},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6219439506530762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6181050539016724},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5984861254692078},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5840086936950684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5630408525466919},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4687870740890503},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4641360640525818},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45949628949165344},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45618879795074463},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4214904308319092},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4195808470249176},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3556337356567383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1884889304637909},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.10529491305351257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06924393773078918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/192","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/192","pdf_url":"https://www.ijcai.org/proceedings/2023/0192.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/192","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/192","pdf_url":"https://www.ijcai.org/proceedings/2023/0192.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3616824283","display_name":null,"funder_award_id":"No. 62006208 and No. 62107035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4354544145","display_name":null,"funder_award_id":"62107035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5106161203","display_name":null,"funder_award_id":"No. 62006208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7134619926","display_name":null,"funder_award_id":"62006208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G943756684","display_name":null,"funder_award_id":"No. 62107035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767743.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2561196672","https://openalex.org/W2579549467","https://openalex.org/W2771088323","https://openalex.org/W2783879794","https://openalex.org/W2899663614","https://openalex.org/W2920879895","https://openalex.org/W2943259397","https://openalex.org/W2962785568","https://openalex.org/W2962974533","https://openalex.org/W2963184176","https://openalex.org/W2963373786","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2965833116","https://openalex.org/W2986711944","https://openalex.org/W2996573420","https://openalex.org/W3011483492","https://openalex.org/W3016121695","https://openalex.org/W3034638741","https://openalex.org/W3043801304","https://openalex.org/W3086903637","https://openalex.org/W3088732637","https://openalex.org/W3106759358","https://openalex.org/W3108984808","https://openalex.org/W3111551570","https://openalex.org/W3129576130","https://openalex.org/W3162003367","https://openalex.org/W3164652084","https://openalex.org/W3174711319","https://openalex.org/W3180355996","https://openalex.org/W3191061784","https://openalex.org/W3191092153","https://openalex.org/W3195154899","https://openalex.org/W3203363269","https://openalex.org/W3203593958","https://openalex.org/W3213163682","https://openalex.org/W4221163505","https://openalex.org/W4281714985","https://openalex.org/W4283799386","https://openalex.org/W4285604311","https://openalex.org/W4287182033","https://openalex.org/W4293518023","https://openalex.org/W4293816553","https://openalex.org/W4297733535","https://openalex.org/W4301206121","https://openalex.org/W4312261724","https://openalex.org/W4312652102","https://openalex.org/W4320167334","https://openalex.org/W4320487943","https://openalex.org/W4353012152","https://openalex.org/W4382457527","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6755811877","https://openalex.org/W6768254745","https://openalex.org/W6791858558","https://openalex.org/W6803771590","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W4248383205","https://openalex.org/W4234745530","https://openalex.org/W2146383839","https://openalex.org/W2231829109","https://openalex.org/W2916591301","https://openalex.org/W2789577489"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2],"concerned":[3],"with":[4,95],"synthesizing":[5],"images":[6,64,167],"conditioned":[7],"on":[8,143,162],"a":[9,13,92,96,107],"scene":[10,71,111,135],"graph":[11,136],"(SG),":[12],"set":[14],"of":[15,21,126,129,156,165],"object":[16,42,59,88,118],"nodes":[17],"and":[18,30,83,106,113,137,145,158,168],"their":[19,62],"edges":[20],"interactive":[22],"relations.":[23],"We":[24],"divide":[25],"existing":[26],"works":[27],"into":[28],"image-oriented":[29,37],"code-oriented":[31,56],"methods.":[32],"In":[33],"our":[34,150],"analysis,":[35],"the":[36,49,55,69,133,138,154,160],"methods":[38,57],"do":[39],"not":[40],"consider":[41],"interaction":[43,123],"in":[44,52,68],"spatial":[45],"hidden":[46],"feature.":[47],"On":[48],"other":[50],"hand,":[51],"empirical":[53],"study,":[54],"lose":[58],"consistency":[60,93],"as":[61],"generated":[63,166],"miss":[65],"certain":[66],"objects":[67,101,157],"input":[70,134],"graph.":[72],"To":[73,86,116],"alleviate":[74],"these":[75],"two":[76],"issues,":[77],"we":[78,90,120],"propose":[79],"Learning":[80],"Object":[81],"Consistency":[82],"Interaction":[84],"(LOCI).":[85],"preserve":[87],"consistency,":[89],"design":[91,121],"module":[94,124],"weighted":[97],"augmentation":[98],"strategy":[99],"for":[100],"easy":[102],"to":[103],"be":[104],"ignored":[105],"matching":[108],"loss":[109],"between":[110,132],"graphs":[112],"image":[114,140],"codes.":[115],"learn":[117],"interaction,":[119],"an":[122],"consisting":[125],"three":[127],"kinds":[128],"message":[130],"propagation":[131],"learned":[139],"code.":[141],"Experiments":[142],"COCO-stuff":[144],"Visual":[146],"Genome":[147],"datasets":[148],"show":[149],"proposed":[151],"method":[152],"alleviates":[153],"ignorance":[155],"outperforms":[159],"state-of-the-art":[161],"visual":[163],"fidelity":[164],"objects.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}