{"id":"https://openalex.org/W4304086649","doi":"https://doi.org/10.1145/3503161.3548154","title":"Background Layout Generation and Object Knowledge Transfer for Text-to-Image Generation","display_name":"Background Layout Generation and Object Knowledge Transfer for Text-to-Image Generation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304086649","doi":"https://doi.org/10.1145/3503161.3548154"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548154","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5056344041","display_name":"Zhuowei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuowei Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008604905","display_name":"Shancheng Fang","orcid":"https://orcid.org/0000-0002-3100-3664"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shancheng Fang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049438048","display_name":"Bo Hu","orcid":"https://orcid.org/0000-0002-3862-1350"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Hu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3539,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67218002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4327","last_page":"4335"},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9897000193595886,"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":0.9768999814987183,"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/computer-science","display_name":"Computer science","score":0.7741259336471558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5921800136566162},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5302072763442993},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4530661702156067},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4251050055027008},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4192241430282593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741259336471558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921800136566162},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5302072763442993},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4530661702156067},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4251050055027008},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4192241430282593},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548154","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2533598788","https://openalex.org/W2561196672","https://openalex.org/W2962845008","https://openalex.org/W2962974533","https://openalex.org/W2963163163","https://openalex.org/W2963212250","https://openalex.org/W2963402808","https://openalex.org/W2963966654","https://openalex.org/W2964078384","https://openalex.org/W2964216930","https://openalex.org/W2965833116","https://openalex.org/W2982450728","https://openalex.org/W2983248633","https://openalex.org/W3202536355","https://openalex.org/W3205866742","https://openalex.org/W4210699831","https://openalex.org/W4214485011"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Text-to-Image":[0],"generation":[1],"(T2I)":[2],"aims":[3],"to":[4,12,62,102,124,128,143,149,164,170],"generate":[5],"realistic":[6],"and":[7,153,155,179,196],"semantically":[8],"consistent":[9],"images":[10,41],"according":[11],"the":[13,19,47,53,57,66,72,95,99,104,108,112,116,125,130,140,145,167,171,176,183,192],"natural":[14],"language":[15],"descriptions.":[16],"Built":[17],"upon":[18],"recent":[20],"advances":[21],"in":[22,71,191],"generative":[23],"adversarial":[24],"networks":[25],"(GANs),":[26],"existing":[27,109,121],"T2I":[28,92],"models":[29],"have":[30],"made":[31],"great":[32],"process.":[33],"However,":[34],"a":[35,90,134,156],"close":[36],"inspection":[37],"of":[38,52,151],"their":[39],"generated":[40,54,73],"shows":[42],"two":[43],"major":[44],"limitations:":[45],"1)":[46],"background":[48,105,177],"(e.g.,":[49,68],"fence,":[50],"lake)":[51],"image":[55,74,172,193],"with":[56,107],"complicated,":[58],"real-world":[59],"scene":[60],"tends":[61],"be":[63],"unrealistic;":[64],"2)":[65],"object":[67,110,117,131,152,168,181],"elephant,":[69],"zebra)":[70],"often":[75],"presents":[76],"highly":[77],"distorted":[78],"shape":[79],"or":[80],"key":[81],"parts":[82],"missing.":[83],"To":[84],"address":[85],"these":[86],"limitations,":[87],"we":[88],"propose":[89],"two-stage":[91],"approach,":[93],"where":[94],"first":[96],"stage":[97,114],"redesigns":[98],"text-to-layout":[100],"process":[101,127],"incorporate":[103],"layout":[106,141,150,178],"layout,":[111],"second":[113],"transfers":[115],"knowledge":[118,169],"from":[119,147,175],"an":[120],"class-to-image":[122],"model":[123],"layout-to-image":[126],"improve":[129],"fidelity.":[132],"Specifically,":[133],"transformer-based":[135],"architecture":[136],"is":[137,162],"introduced":[138],"as":[139],"generator":[142],"learn":[144],"mapping":[146],"text":[148],"background,":[154],"Text-attended":[157],"Layout-aware":[158],"feature":[159],"Normalization":[160],"(TL-Norm)":[161],"proposed":[163,184],"adaptively":[165],"transfer":[166],"generation.":[173],"Benefitting":[174],"transferred":[180],"knowledge,":[182],"approach":[185],"significantly":[186],"surpasses":[187],"previous":[188],"state-of-the-art":[189],"methods":[190],"quality":[194],"metric":[195],"achieves":[197],"superior":[198],"image-text":[199],"alignment":[200],"performance.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}