{"id":"https://openalex.org/W4402703014","doi":"https://doi.org/10.1109/cvpr52733.2024.00015","title":"Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation","display_name":"Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402703014","doi":"https://doi.org/10.1109/cvpr52733.2024.00015"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5061318621","display_name":"Daichi Horita","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daichi Horita","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058832609","display_name":"Naoto Inoue","orcid":"https://orcid.org/0000-0002-1969-2006"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Inoue","raw_affiliation_strings":["CyberAgent"],"affiliations":[{"raw_affiliation_string":"CyberAgent","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052366179","display_name":"Kotaro Kikuchi","orcid":"https://orcid.org/0000-0003-1747-5945"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Kikuchi","raw_affiliation_strings":["CyberAgent"],"affiliations":[{"raw_affiliation_string":"CyberAgent","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065025107","display_name":"Kota Yamaguchi","orcid":"https://orcid.org/0000-0002-3597-2913"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kota Yamaguchi","raw_affiliation_strings":["CyberAgent"],"affiliations":[{"raw_affiliation_string":"CyberAgent","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069982192","display_name":"Kiyoharu Aizawa","orcid":"https://orcid.org/0000-0003-2146-6275"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoharu Aizawa","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061318621"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":4.1987,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95350894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973000288009644,"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":0.7078965902328491},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6572050452232361},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.382347971200943},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.32050472497940063},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2009996473789215},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1306997537612915},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10441464185714722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078965902328491},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6572050452232361},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.382347971200943},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.32050472497940063},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2009996473789215},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1306997537612915},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10441464185714722}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":56,"referenced_works":["https://openalex.org/W1632809586","https://openalex.org/W2066405128","https://openalex.org/W2081211779","https://openalex.org/W2131210874","https://openalex.org/W2194775991","https://openalex.org/W2271551547","https://openalex.org/W2565639579","https://openalex.org/W2896457183","https://openalex.org/W2960053204","https://openalex.org/W2961348656","https://openalex.org/W2962785568","https://openalex.org/W3000176874","https://openalex.org/W3007672467","https://openalex.org/W3033926673","https://openalex.org/W3094084711","https://openalex.org/W3096609285","https://openalex.org/W3112646048","https://openalex.org/W3158555958","https://openalex.org/W3160663997","https://openalex.org/W3166396011","https://openalex.org/W3167280680","https://openalex.org/W3190835409","https://openalex.org/W3199003182","https://openalex.org/W3202536355","https://openalex.org/W3206831165","https://openalex.org/W4225744354","https://openalex.org/W4226079479","https://openalex.org/W4226082499","https://openalex.org/W4283803959","https://openalex.org/W4285605355","https://openalex.org/W4288627824","https://openalex.org/W4304080663","https://openalex.org/W4312964941","https://openalex.org/W4378498608","https://openalex.org/W4380994596","https://openalex.org/W4385245566","https://openalex.org/W4385570290","https://openalex.org/W4386071540","https://openalex.org/W4386071617","https://openalex.org/W4386071810","https://openalex.org/W4386076211","https://openalex.org/W4386076468","https://openalex.org/W4387846478","https://openalex.org/W4390873073","https://openalex.org/W4390874507","https://openalex.org/W6636566652","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757941371","https://openalex.org/W6765841262","https://openalex.org/W6771898956","https://openalex.org/W6774222543","https://openalex.org/W6791353385","https://openalex.org/W6810730852","https://openalex.org/W6852567072","https://openalex.org/W6853332882"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Content-aware":[0],"graphic":[1],"layout":[2,29,41,67],"generation":[3,30,54,91],"aims":[4],"to":[5,88],"automatically":[6],"arrange":[7],"visual":[8],"elements":[9],"along":[10],"with":[11],"a":[12,46,98],"given":[13],"content,":[14],"such":[15],"as":[16],"an":[17,71,79],"e-commerce":[18],"product":[19],"image.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"argue":[25],"that":[26,45,105],"the":[27,34,39,53,120],"current":[28],"approaches":[31],"suffer":[32],"from":[33],"limited":[35],"training":[36],"data":[37],"for":[38],"high-dimensional":[40],"structure.":[42],"We":[43],"show":[44,104],"simple":[47],"retrieval":[48,86],"augmentation":[49,87],"can":[50,84],"significantly":[51,118],"improve":[52],"quality.":[55],"Our":[56,82,101],"model,":[57],"which":[58],"is":[59],"named":[60],"Retrieval-Augmented":[61],"Layout":[62],"Transformer":[63],"(RALF),retrieves":[64],"nearest":[65],"neighbor":[66],"examples":[68],"based":[69],"on":[70],"input":[72],"image":[73],"and":[74,93,114,117],"feeds":[75],"these":[76],"results":[77],"into":[78],"autoregressive":[80],"generator.":[81],"model":[83],"apply":[85],"various":[89],"controllable":[90],"tasks":[92],"yield":[94],"high-quality":[95],"layouts":[96,110],"within":[97],"unified":[99],"architecture.":[100],"extensive":[102],"experiments":[103],"RALF":[106],"successfully":[107],"generates":[108],"content-aware":[109],"in":[111],"both":[112],"constrained":[113],"unconstrained":[115],"settings":[116],"outperforms":[119],"baselines.":[121],"<sup":[122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[124]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}