{"id":"https://openalex.org/W3132623428","doi":"https://doi.org/10.1145/3474085.3475541","title":"CanvasEmb: Learning Layout Representation with Large-scale Pre-training for Graphic Design","display_name":"CanvasEmb: Learning Layout Representation with Large-scale Pre-training for Graphic Design","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3132623428","doi":"https://doi.org/10.1145/3474085.3475541","mag":"3132623428"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475541","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475541","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475541","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475541","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101498987","display_name":"Yuxi Xie","orcid":"https://orcid.org/0009-0009-0843-6507"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuxi Xie","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061321029","display_name":"Danqing Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danqing Huang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376310","display_name":"Jinpeng Wang","orcid":"https://orcid.org/0000-0001-6127-9146"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090151187","display_name":"Chin-Yew Lin","orcid":"https://orcid.org/0000-0002-0798-6365"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chin-Yew Lin","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4100","last_page":"4108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9975000023841858,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9975000023841858,"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":0.995199978351593,"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":0.991100013256073,"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":0.8351353406906128},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5534899830818176},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5248489379882812},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5062743425369263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016438961029053},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49672991037368774},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48170262575149536},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4695618450641632},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4618251919746399},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42306458950042725},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35978955030441284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351353406906128},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5534899830818176},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5248489379882812},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5062743425369263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016438961029053},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49672991037368774},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48170262575149536},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4695618450641632},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4618251919746399},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42306458950042725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35978955030441284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475541","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475541","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475541","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3474085.3475541","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475541","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475541","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132623428.pdf","grobid_xml":"https://content.openalex.org/works/W3132623428.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W112197792","https://openalex.org/W1815076433","https://openalex.org/W2014740140","https://openalex.org/W2037668370","https://openalex.org/W2067237863","https://openalex.org/W2072747082","https://openalex.org/W2170288539","https://openalex.org/W2593581739","https://openalex.org/W2740747242","https://openalex.org/W2753094203","https://openalex.org/W2892181857","https://openalex.org/W2952489094","https://openalex.org/W2960053204","https://openalex.org/W2962739339","https://openalex.org/W2963103943","https://openalex.org/W2970042171","https://openalex.org/W2998811520","https://openalex.org/W3034503989","https://openalex.org/W3098605233","https://openalex.org/W3104953317","https://openalex.org/W3112646048","https://openalex.org/W4241307704"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3048601286","https://openalex.org/W2965925734"],"abstract_inverted_index":{"Layout":[0],"representation,":[1],"which":[2,87],"models":[3,139],"visual":[4,34],"elements":[5,35,102],"and":[6,27,45,49,58,111,129,166,179,211,223],"their":[7],"inter-relations":[8],"in":[9,16,73,79,103],"a":[10,13,21,39,104,107,112,131,141,157,200],"canvas,":[11,105],"plays":[12],"crucial":[14],"role":[15,177],"graphic":[17,93],"design":[18],"intelligence.":[19],"With":[20],"large":[22],"variety":[23],"of":[24,31,41,69,134,144,209],"layout":[25,169,220,224],"designs":[26,94],"the":[28,66,100,206],"unique":[29],"characteristic":[30],"layouts":[32],"that":[33,189],"are":[36],"defined":[37],"as":[38],"list":[40],"categorical":[42],"(e.g.,":[43,47],"type)":[44],"numerical":[46],"position":[48],"size)":[50],"properties,":[51],"it":[52],"is":[53],"challenging":[54],"to":[55,137,204],"learn":[56],"general":[57],"compact":[59],"representations":[60,90],"with":[61,106,123,130,151,160,172,192,216],"limited":[62],"data.":[63,154],"Inspired":[64],"by":[65,95],"recent":[67],"success":[68],"self-supervised":[70],"pre-training":[71],"techniques":[72],"various":[74],"natural":[75],"language":[76],"processing":[77],"tasks,":[78],"this":[80],"paper,":[81],"we":[82,198],"propose":[83,167],"CanvasEmb":[84,118,210],"(Canvas":[85],"Embedding),":[86],"pre-trains":[88],"deep":[89,201],"from":[91],"unlabeled":[92],"jointly":[96],"conditioning":[97],"on":[98,184],"all":[99],"context":[101],"multi-dimensional":[108],"feature":[109],"encoder":[110],"multi-task":[113],"learning":[114],"objective.":[115],"The":[116],"pre-trained":[117],"model":[119,191],"can":[120],"be":[121],"fine-tuned":[122],"just":[124],"one":[125,163],"additional":[126],"output":[127],"layer":[128],"small":[132],"size":[133],"training":[135],"data":[136],"create":[138],"for":[140],"wide":[142],"range":[143],"downstream":[145],"tasks.":[146],"We":[147,155],"verify":[148],"our":[149,190],"approach":[150],"presentation":[152],"slides":[153,165],"construct":[156],"large-scale":[158],"dataset":[159],"more":[161],"than":[162],"million":[164],"two":[168,186,217],"understanding":[170],"tasks":[171,187],"human-labeled":[173],"sets,":[174],"namely":[175],"element":[176],"labeling":[178],"image":[180],"captioning.":[181],"Evaluation":[182],"results":[183],"these":[185],"show":[188],"fine-tuning":[193],"achieves":[194],"state-of-the-art":[195],"performance.":[196],"Furthermore,":[197],"conduct":[199],"analysis":[202],"aiming":[203],"understand":[205],"modeling":[207],"mechanism":[208],"demonstrate":[212],"its":[213],"great":[214],"potential":[215],"extended":[218],"applications:":[219],"auto":[221],"completion":[222],"retrieval.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}