{"id":"https://openalex.org/W4200311227","doi":"https://doi.org/10.1145/3487075.3487158","title":"Text Pared into Scene Graph for Diverse Image Generation","display_name":"Text Pared into Scene Graph for Diverse Image Generation","publication_year":2021,"publication_date":"2021-10-19","ids":{"openalex":"https://openalex.org/W4200311227","doi":"https://doi.org/10.1145/3487075.3487158"},"language":"en","primary_location":{"id":"doi:10.1145/3487075.3487158","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3487075.3487158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","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/A5108217303","display_name":"Yonghua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghua Zhu","raw_affiliation_strings":["Shanghai Film Academy, Shanghai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Film Academy, Shanghai University, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006349693","display_name":"Jieyu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieyu Huang","raw_affiliation_strings":["Shanghai Film Academy, Shanghai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Film Academy, Shanghai University, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068580344","display_name":"Ning Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Ge","raw_affiliation_strings":["Shanghai Film Academy, Shanghai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Film Academy, Shanghai University, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052389063","display_name":"Yunwen Zhu","orcid":"https://orcid.org/0000-0001-6745-7468"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunwen Zhu","raw_affiliation_strings":["Shanghai Film Academy, Shanghai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Film Academy, Shanghai University, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056701316","display_name":"Binghui Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binghui Zheng","raw_affiliation_strings":["Shanghai Film Academy, Shanghai University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Film Academy, Shanghai University, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447806","display_name":"Wenjun Zhang","orcid":"https://orcid.org/0000-0001-8799-1182"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210154361","display_name":"Shanghai Jian Qiao University","ror":"https://ror.org/04xdqtw10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zhang","raw_affiliation_strings":["Shanghai Film Academy, Shanghai University, China and Information Technology Academy, Shanghai Jian Qiao University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Film Academy, Shanghai University, China and Information Technology Academy, Shanghai Jian Qiao University, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210154361"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.17793037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9969000220298767,"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":0.9889000058174133,"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/scene-graph","display_name":"Scene graph","score":0.7684007287025452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475805282592773},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6322956681251526},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6147116422653198},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5976129174232483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5649691820144653},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5090352892875671},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5089848041534424},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.49685361981391907},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4813450276851654},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.4684344232082367},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46262454986572266},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4417106509208679},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.40850165486335754},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4013090133666992},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39561110734939575},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3467940092086792},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1601419448852539}],"concepts":[{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.7684007287025452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475805282592773},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6322956681251526},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6147116422653198},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5976129174232483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5649691820144653},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5090352892875671},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5089848041534424},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.49685361981391907},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4813450276851654},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.4684344232082367},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46262454986572266},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4417106509208679},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40850165486335754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4013090133666992},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39561110734939575},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3467940092086792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1601419448852539},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3487075.3487158","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3487075.3487158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2277195237"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495"],"abstract_inverted_index":{"Although":[0],"significant":[1],"recent":[2],"advances":[3],"in":[4,114],"condition":[5],"generative":[6],"model":[7,113],"have":[8],"shown":[9],"remarkable":[10],"improvements":[11],"for":[12,19],"controlled":[13],"image":[14,17,52,79],"generation,":[15],"the":[16,29,50,60,77,81,88,109],"generation":[18],"multiple":[20,118],"complex":[21,121],"objects":[22,63,119],"is":[23,85],"still":[24],"a":[25,33],"challenge.":[26],"To":[27,75],"address":[28],"challenge,":[30],"we":[31],"propose":[32],"module":[34],"of":[35,90,111],"text":[36,73],"description":[37],"parsed":[38],"into":[39,87],"scene":[40,46],"graph,":[41],"which":[42],"can":[43],"generate":[44],"reasonable":[45],"layout":[47],"to":[48],"ensure":[49],"generated":[51],"and":[53,64,100,105,120],"object":[54,70],"realistic.":[55],"Our":[56],"proposed":[57],"method":[58,96],"enhances":[59],"interaction":[61],"between":[62],"global":[65],"semantics":[66],"by":[67],"concatenates":[68],"each":[69],"embedding":[71,74],"with":[72,117],"preserve":[76],"local":[78],"semantics,":[80],"Spatially-adaptive":[82],"normalization(SPADE)":[83],"layer":[84],"added":[86],"generator":[89],"our":[91,95,112],"model.":[92],"We":[93],"validate":[94],"on":[97],"Visual":[98],"Genome":[99],"COCO-Stuff,":[101],"where":[102],"qualitative":[103],"results":[104],"ablation":[106],"study":[107],"demonstrate":[108],"ability":[110],"generating":[115],"images":[116],"relationships.":[122]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
