{"id":"https://openalex.org/W4304013646","doi":"https://doi.org/10.1145/3503161.3548112","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","display_name":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304013646","doi":"https://doi.org/10.1145/3503161.3548112"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548112","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/A5067298679","display_name":"Yupan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yupan Huang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031963349","display_name":"Tengchao Lv","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":"Tengchao Lv","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581994","display_name":"Lei Cui","orcid":"https://orcid.org/0000-0002-4270-4896"},"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":"Lei Cui","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"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":"Furu Wei","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067298679"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":25.6072,"has_fulltext":false,"cited_by_count":463,"citation_normalized_percentile":{"value":0.99609735,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4083","last_page":"4091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.821439802646637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5636543035507202},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5132348537445068},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.4835748076438904},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4384879171848297},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3381040096282959},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32532525062561035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821439802646637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5636543035507202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5132348537445068},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.4835748076438904},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4384879171848297},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3381040096282959},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32532525062561035},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548112","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1966382373","https://openalex.org/W2962772269","https://openalex.org/W2962784628","https://openalex.org/W3003711898","https://openalex.org/W3011411500","https://openalex.org/W3104152799","https://openalex.org/W3165647589","https://openalex.org/W3173325518","https://openalex.org/W3184784418","https://openalex.org/W3202839357","https://openalex.org/W3205981739","https://openalex.org/W3206384369","https://openalex.org/W3207212285","https://openalex.org/W4226020328","https://openalex.org/W4312784228","https://openalex.org/W6803916128"],"related_works":["https://openalex.org/W3014541132","https://openalex.org/W2994737807","https://openalex.org/W2948639032","https://openalex.org/W2948704552","https://openalex.org/W2948403110","https://openalex.org/W3156494719","https://openalex.org/W2948123712","https://openalex.org/W4241313390","https://openalex.org/W2948769344","https://openalex.org/W4251317489"],"abstract_inverted_index":{"Self-supervised":[0],"pre-training":[1,32],"techniques":[2],"have":[3],"achieved":[4],"remarkable":[5],"progress":[6],"in":[7,31,122,137],"Document":[8,57,109],"AI.":[9],"Most":[10],"multimodal":[11,43,54],"pre-trained":[12,68,102],"models":[13,152],"use":[14],"a":[15,70,86,100],"masked":[16],"language":[17],"modeling":[18],"objective":[19,73],"to":[20,42,52,74],"learn":[21,75],"bidirectional":[22],"representations":[23],"on":[24],"the":[25,35,81],"text":[26,61,87],"modality,":[27],"but":[28,135],"they":[29],"differ":[30],"objectives":[33,97],"for":[34,56,104],"image":[36,63,83,143],"modality.":[37],"This":[38],"discrepancy":[39],"adds":[40],"difficulty":[41],"representation":[44],"learning.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"LayoutLMv3":[51,66,99,116],"pre-train":[53],"Transformers":[55],"AI":[58,110],"with":[59,69],"unified":[60,93],"and":[62,95,107,130,145,151],"masking.":[64],"Additionally,":[65],"is":[67,89],"word-patch":[71],"alignment":[72,77],"cross-modal":[76],"by":[78],"predicting":[79],"whether":[80],"corresponding":[82],"patch":[84],"of":[85],"word":[88],"masked.":[90],"The":[91,149],"simple":[92],"architecture":[94],"training":[96],"make":[98],"general-purpose":[101],"model":[103],"both":[105],"text-centric":[106,123],"image-centric":[108,138],"tasks.":[111],"Experimental":[112],"results":[113],"show":[114],"that":[115],"achieves":[117],"state-of-the-art":[118],"performance":[119],"not":[120],"only":[121],"tasks,":[124],"including":[125],"form":[126],"understanding,":[127,129],"receipt":[128],"document":[131,142,146],"visual":[132],"question":[133],"answering,":[134],"also":[136],"tasks":[139],"such":[140],"as":[141],"classification":[144],"layout":[147],"analysis.":[148],"code":[150],"are":[153],"publicly":[154],"available":[155],"at":[156],"https://aka.ms/layoutlmv3.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":34},{"year":2025,"cited_by_count":163},{"year":2024,"cited_by_count":136},{"year":2023,"cited_by_count":126},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}