{"id":"https://openalex.org/W3178679506","doi":"https://doi.org/10.1109/cvpr46437.2021.00373","title":"LayoutTransformer: Scene Layout Generation with Conceptual and Spatial Diversity","display_name":"LayoutTransformer: Scene Layout Generation with Conceptual and Spatial Diversity","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3178679506","doi":"https://doi.org/10.1109/cvpr46437.2021.00373","mag":"3178679506"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00373","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5103056761","display_name":"Cheng-Fu Yang","orcid":"https://orcid.org/0000-0002-6916-2142"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Fu Yang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022911737","display_name":"Wan-Cyuan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wan-Cyuan Fan","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032964198","display_name":"Fu-En Yang","orcid":"https://orcid.org/0000-0003-0102-7101"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I3020783763","display_name":"Asus (Taiwan)","ror":"https://ror.org/00bxkz165","country_code":"TW","type":"company","lineage":["https://openalex.org/I3020783763"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Fu-En Yang","raw_affiliation_strings":["ASUS Intelligent Cloud Services, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"ASUS Intelligent Cloud Services, Taiwan","institution_ids":["https://openalex.org/I3020783763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090045508","display_name":"Yu-Chiang Frank Wang","orcid":"https://orcid.org/0000-0002-2333-157X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I3020783763","display_name":"Asus (Taiwan)","ror":"https://ror.org/00bxkz165","country_code":"TW","type":"company","lineage":["https://openalex.org/I3020783763"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","raw_affiliation_strings":["ASUS Intelligent Cloud Services, Taiwan","Graduate Institute of Communication Engineering, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"ASUS Intelligent Cloud Services, Taiwan","institution_ids":["https://openalex.org/I3020783763"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.809,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.748913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3731","last_page":"3740"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986,"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":0.9986,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9983,"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":0.9966,"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/scene-graph","display_name":"Scene graph","score":0.66875774},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6600626},{"id":"https://openalex.org/keywords/scene-graph-generation","display_name":"Scene Graph Generation","score":0.585177},{"id":"https://openalex.org/keywords/scene-classification","display_name":"Scene Classification","score":0.520613},{"id":"https://openalex.org/keywords/representation-learning","display_name":"Representation Learning","score":0.519911},{"id":"https://openalex.org/keywords/image-captioning","display_name":"Image Captioning","score":0.506729},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.48454848},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4516777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79186934},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.66875774},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6600626},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.57829374},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5035495},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.48454848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4660925},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4516777},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43021423},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42034376},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3553322},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30440766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23626009},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.101053506},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00373","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320322108","funder_display_name":"Ministry of Science and Technology","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":35,"referenced_works":["https://openalex.org/W1546503963","https://openalex.org/W1598866093","https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2405756170","https://openalex.org/W2561196672","https://openalex.org/W2891997758","https://openalex.org/W2896457183","https://openalex.org/W2943259397","https://openalex.org/W2944466895","https://openalex.org/W2949999304","https://openalex.org/W2952489094","https://openalex.org/W2953783113","https://openalex.org/W2960053204","https://openalex.org/W2962785568","https://openalex.org/W2963037989","https://openalex.org/W2963163163","https://openalex.org/W2963184176","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963649796","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964113829","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2971191214","https://openalex.org/W2983248633","https://openalex.org/W2987919422","https://openalex.org/W3000176874","https://openalex.org/W3106759358","https://openalex.org/W3112646048","https://openalex.org/W4288627824","https://openalex.org/W4300672471","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4390524233","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2952736415","https://openalex.org/W2883297582","https://openalex.org/W2387360586"],"abstract_inverted_index":{"When":[0],"translating":[1],"text":[2,32],"inputs":[3],"into":[4,96],"layouts":[5,113],"or":[6,24,38],"images,":[7],"existing":[8],"works":[9],"typically":[10],"require":[11],"explicit":[12],"descriptions":[13],"of":[14,88,127,138],"each":[15],"object":[16],"in":[17,53],"a":[18,49,57],"scene,":[19],"including":[20],"their":[21,69,106],"spatial":[22],"information":[23],"the":[25,31,64,86,92,125,134],"associated":[26],"relationships.":[27,73],"To":[28],"better":[29],"exploit":[30],"input,":[33,59],"so":[34],"that":[35],"implicit":[36,72],"objects":[37],"relationships":[39],"can":[40,114],"be":[41,115,148],"properly":[42],"inferred":[43],"during":[44],"layout":[45,83,143],"generation,":[46],"we":[47],"propose":[48],"LayoutTransformer":[50],"Network":[51],"(LT-Net)":[52],"this":[54],"paper.":[55],"Given":[56],"scene-graph":[58],"our":[60,89,139],"LT-Net":[61,90,140],"uniquely":[62],"encodes":[63],"semantic":[65],"features":[66,95],"for":[67],"exploiting":[68],"co-occurrences":[70],"and":[71,129,132,136],"This":[74],"allows":[75],"one":[76],"to":[77,108],"manipulate":[78],"conceptually":[79],"diverse":[80],"yet":[81],"plausible":[82],"outputs.":[84],"Moreover,":[85],"decoder":[87],"translates":[91],"encoded":[93],"contextual":[94],"bounding":[97],"boxes":[98],"with":[99],"self-supervised":[100],"relation":[101],"consistency":[102],"preserved.":[103],"By":[104],"fitting":[105],"distributions":[107],"Gaussian":[109],"mixture":[110],"models,":[111],"spatially-diverse":[112],"additionally":[116],"produced":[117],"by":[118],"LT-Net.":[119],"We":[120],"conduct":[121],"extensive":[122],"experiments":[123],"on":[124],"datasets":[126],"MS-COCO":[128],"Visual":[130],"Genome,":[131],"confirm":[133],"effectiveness":[135],"plausibility":[137],"over":[141],"recent":[142],"generation":[144],"models.":[145],"Codes":[146],"will":[147],"released":[149],"at":[150],"LayoutTransformer.":[151]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3178679506","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":10}],"updated_date":"2024-12-05T19:18:28.903328","created_date":"2021-07-19"}