{"id":"https://openalex.org/W2997154779","doi":"https://doi.org/10.1145/3394486.3403172","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","display_name":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W2997154779","doi":"https://doi.org/10.1145/3394486.3403172","mag":"2997154779"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.13318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yiheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiheng Xu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Minghao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Cui","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":"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":null,"display_name":"Shaohan 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":"Shaohan Huang","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":null,"display_name":"Furu Wei","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":"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"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ming Zhou","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":"Ming Zhou","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":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":22.6718,"has_fulltext":false,"cited_by_count":559,"citation_normalized_percentile":{"value":0.99671762,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1192","last_page":"1200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9958999752998352,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9873999953269958,"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/leverage","display_name":"Leverage (statistics)","score":0.6712999939918518},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.6385999917984009},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.616100013256073},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5166000127792358},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.48989999294281006},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939000129699707},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6712999939918518},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.6385999917984009},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.616100013256073},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5656999945640564},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C2778979077","wikidata":"https://www.wikidata.org/wiki/Q330190","display_name":"Receipt","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.2786000072956085},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2773999869823456}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.13318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.13318","pdf_url":"https://arxiv.org/pdf/1912.13318","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.13318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.13318","pdf_url":"https://arxiv.org/pdf/1912.13318","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1966382373","https://openalex.org/W2095818033","https://openalex.org/W2099926976","https://openalex.org/W2112692009","https://openalex.org/W2135164809","https://openalex.org/W2163113711","https://openalex.org/W2444353601","https://openalex.org/W2605976347","https://openalex.org/W2891117443","https://openalex.org/W2922714365","https://openalex.org/W2962772269","https://openalex.org/W2964346820","https://openalex.org/W2964350391","https://openalex.org/W2965085721","https://openalex.org/W6606151494"],"related_works":[],"abstract_inverted_index":{"Pre-training":[0],"techniques":[1],"have":[2],"been":[3],"verified":[4],"successfully":[5],"in":[6,12,116,128],"a":[7,69,117],"variety":[8],"of":[9,19,72,101],"NLP":[10,23],"tasks":[11,77],"recent":[13],"years.":[14],"Despite":[15],"the":[16,50,99,106],"widespread":[17],"use":[18],"pre-training":[20],"models":[21,158],"for":[22,41,68,120],"applications,":[24],"they":[25],"almost":[26],"exclusively":[27],"focus":[28],"on":[29],"text-level":[30],"manipulation,":[31],"while":[32],"neglecting":[33],"layout":[34,59,112],"and":[35,58,111,145,155],"style":[36],"information":[37,60,80,95],"that":[38,109],"is":[39,66,105],"vital":[40],"document":[42,63,74,146],"image":[43,75,89,147],"understanding.":[44],"In":[45],"this":[46,104],"paper,":[47],"we":[48,86],"propose":[49],"LayoutLM":[51,157],"to":[52,91,137,143,151],"jointly":[53,114],"model":[54],"interactions":[55],"between":[56],"text":[57,110],"across":[61],"scanned":[62,83],"images,":[64],"which":[65],"beneficial":[67],"great":[70],"number":[71],"real-world":[73],"understanding":[76,134,140],"such":[78],"as":[79],"extraction":[81],"from":[82],"documents.":[84],"Furthermore,":[85],"also":[87],"leverage":[88],"features":[90],"incorporate":[92],"words'":[93],"visual":[94],"into":[96],"LayoutLM.":[97],"To":[98],"best":[100],"our":[102],"knowledge,":[103],"first":[107],"time":[108],"are":[113,159],"learned":[115],"single":[118],"framework":[119],"document-level":[121],"pre-training.":[122],"It":[123],"achieves":[124],"new":[125],"state-of-the-art":[126],"results":[127],"several":[129],"downstream":[130],"tasks,":[131],"including":[132],"form":[133],"(from":[135,141,149],"70.72":[136],"79.27),":[138],"receipt":[139],"94.02":[142],"95.24)":[144],"classification":[148],"93.07":[150],"94.42).":[152],"The":[153],"code":[154],"pre-trained":[156],"publicly":[160],"available":[161],"at":[162],"https://aka.ms/layoutlm.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":168},{"year":2024,"cited_by_count":128},{"year":2023,"cited_by_count":124},{"year":2022,"cited_by_count":63},{"year":2021,"cited_by_count":43},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2020-01-10T00:00:00"}