{"id":"https://openalex.org/W3164115078","doi":"https://doi.org/10.1007/s11042-021-11038-0","title":"Improving text-to-image generation with object layout guidance","display_name":"Improving text-to-image generation with object layout guidance","publication_year":2021,"publication_date":"2021-05-20","ids":{"openalex":"https://openalex.org/W3164115078","doi":"https://doi.org/10.1007/s11042-021-11038-0","mag":"3164115078"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-021-11038-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-021-11038-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-021-11038-0.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-021-11038-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071938620","display_name":"Jezia Zakraoui","orcid":"https://orcid.org/0000-0002-5133-3695"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Jezia Zakraoui","raw_affiliation_strings":["Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063475947","display_name":"Moutaz Saleh","orcid":"https://orcid.org/0000-0002-6434-1790"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Moutaz Saleh","raw_affiliation_strings":["Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-6434-1790","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017608892","display_name":"Somaya Al-M\u00e1adeed","orcid":"https://orcid.org/0000-0002-0241-2899"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Somaya Al-Maadeed","raw_affiliation_strings":["Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071875717","display_name":"Jihad Mohammed Jaam","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Jihad Mohammed Jaam","raw_affiliation_strings":["Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Qatar University, 2713, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5063475947"],"corresponding_institution_ids":["https://openalex.org/I60342839"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2341,"currency":"EUR","value_usd":2524},"fwci":1.18,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.78084046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"80","issue":"18","first_page":"27423","last_page":"27443"},"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":0.9970999956130981,"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":0.9887999892234802,"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":0.8674030303955078},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.7111322283744812},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6343579292297363},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6063939929008484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805138945579529},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5560930967330933},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4404095709323883},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42787545919418335},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4060235917568207},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20796647667884827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8674030303955078},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.7111322283744812},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6343579292297363},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6063939929008484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805138945579529},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5560930967330933},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4404095709323883},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42787545919418335},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4060235917568207},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20796647667884827},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11042-021-11038-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-021-11038-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-021-11038-0.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/21597408","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_text-to-image_generation_with_object_layout_guidance/21597408","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:qspace.qu.edu.qa:10576/31089","is_oa":false,"landing_page_url":"http://hdl.handle.net/10576/31089","pdf_url":null,"source":{"id":"https://openalex.org/S4306400014","display_name":"Qatar University QSpace (Qatar University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60342839","host_organization_name":"Qatar University","host_organization_lineage":["https://openalex.org/I60342839"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.57945/manara.21597408.v1","is_oa":true,"landing_page_url":"https://doi.org/10.57945/manara.21597408.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407052475","display_name":"Qatar National Library","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s11042-021-11038-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-021-11038-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-021-11038-0.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3947569920","display_name":null,"funder_award_id":"10-0205-170346","funder_id":"https://openalex.org/F4320309815","funder_display_name":"Qatar Foundation"},{"id":"https://openalex.org/G52763459","display_name":null,"funder_award_id":"NPRP #10-0205-170346","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"},{"id":"https://openalex.org/G6999223617","display_name":null,"funder_award_id":"10-0205-170346","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"}],"funders":[{"id":"https://openalex.org/F4320309815","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"},{"id":"https://openalex.org/F4320334468","display_name":"Qatar National Library","ror":"https://ror.org/02jv93662"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164115078.pdf","grobid_xml":"https://content.openalex.org/works/W3164115078.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1967271542","https://openalex.org/W2099471712","https://openalex.org/W2148489082","https://openalex.org/W2155292833","https://openalex.org/W2548275288","https://openalex.org/W2561196672","https://openalex.org/W2564591810","https://openalex.org/W2566832195","https://openalex.org/W2605135824","https://openalex.org/W2788768663","https://openalex.org/W2884466206","https://openalex.org/W2899675781","https://openalex.org/W2907077346","https://openalex.org/W2949888546","https://openalex.org/W2949999304","https://openalex.org/W2951004968","https://openalex.org/W2951523806","https://openalex.org/W2961334035","https://openalex.org/W2962845008","https://openalex.org/W2963047368","https://openalex.org/W2963073614","https://openalex.org/W2963184176","https://openalex.org/W2963373786","https://openalex.org/W2963565467","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964024144","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2971191214","https://openalex.org/W2979672901","https://openalex.org/W3010564927","https://openalex.org/W3011418067","https://openalex.org/W3019523615","https://openalex.org/W3098584011","https://openalex.org/W3108650314","https://openalex.org/W6601104142","https://openalex.org/W6608993855"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W4293226380","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2121496884","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"automatic":[2],"generation":[3,26,65,151,156,164],"of":[4,34,51,99,211,233,258,261,266],"realistic":[5],"images":[6,196,269],"directly":[7],"from":[8,102,116,187],"a":[9,13,23,44,75,130,160,172],"story":[10,36,52,86,272],"text":[11,37,58,73,273],"is":[12,169],"very":[14],"challenging":[15],"problem,":[16],"as":[17,120,122,166,174],"it":[18,221],"cannot":[19],"be":[20],"addressed":[21],"using":[22,74,171],"single":[24],"image":[25,64,150,155,163,186,200,234],"approach":[27,46,190,249],"due":[28],"mainly":[29],"to":[30,95,140,148,240],"the":[31,35,49,72,85,97,103,108,117,149,154,178,183,199,204,209,216,241,252,259,267,271],"semantic":[32,57,82,142,262],"complexity":[33],"constituents.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,158,214],"propose":[43],"new":[45],"that":[47,80,144],"decomposes":[48],"task":[50],"visualization":[53],"into":[54],"three":[55,223],"phases:":[56],"understanding,":[59],"object":[60,92,109,114,126,179,192,246],"layout":[61,93,110,180,247],"prediction,":[62],"and":[63,66,182,219,229,236,264],"refinement.":[67],"We":[68,88],"start":[69],"by":[70,129],"simplifying":[71],"scene":[76,105,118,161],"graph":[77,119,131,162],"triple":[78],"notation":[79],"encodes":[81],"relationships":[83],"between":[84],"objects.":[87],"then":[89,146],"introduce":[90],"an":[91],"module":[94,111,181],"capture":[96],"features":[98,115,127,137],"these":[100,136],"objects":[101],"corresponding":[104],"graph.":[106],"Specifically,":[107],"aggregates":[112],"individual":[113],"well":[121],"averaged":[123],"or":[124],"likelihood":[125],"generated":[128,184,268],"convolutional":[132],"neural":[133],"network.":[134],"All":[135],"are":[138,145],"concatenated":[139],"form":[141],"triples":[143],"provided":[147],"framework.":[152],"For":[153],"phase,":[157],"adopt":[159],"framework":[165],"stage-I,":[167],"which":[168],"refined":[170],"StackGAN":[173,228],"stage-II":[175],"conditioned":[176],"on":[177],"output":[185],"stage-I.":[188],"Our":[189],"renders":[191],"details":[193],"in":[194,231,256],"high-resolution":[195],"while":[197],"keeping":[198],"structure":[201],"consistent":[202],"with":[203,222],"input":[205],"text.":[206],"To":[207],"evaluate":[208],"performance":[210],"our":[212,245],"approach,":[213],"use":[215],"COCO":[217],"dataset":[218],"compare":[220],"baseline":[224,254],"approaches,":[225],"namely,":[226],"sg2im,":[227],"AttnGAN,":[230],"terms":[232,257],"quality":[235],"user":[237],"evaluation.":[238],"According":[239],"obtained":[242],"assessment":[243],"results,":[244],"guidance-based":[248],"significantly":[250],"outperforms":[251],"abovementioned":[253],"approaches":[255],"accuracy":[260],"matching":[263],"realism":[265],"representing":[270],"sentences.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2021-06-07T00:00:00"}