{"id":"https://openalex.org/W3198763628","doi":"https://doi.org/10.1007/978-3-030-86549-8_32","title":"Document Domain Randomization for Deep Learning Document Layout Extraction","display_name":"Document Domain Randomization for Deep Learning Document Layout Extraction","publication_year":2021,"publication_date":"2021-05-20","ids":{"openalex":"https://openalex.org/W3198763628","doi":"https://doi.org/10.1007/978-3-030-86549-8_32","mag":"3198763628"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2105.14931","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14931","pdf_url":"https://arxiv.org/pdf/2105.14931","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"type":"book-chapter","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.14931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058228488","display_name":"Meng Ling","orcid":"https://orcid.org/0000-0001-6597-5448"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ling, Meng","raw_affiliation_strings":["OSU - Ohio State University [Columbus] (Ohio State University Enarson Hall 154 W 12th Avenue Columbus, Ohio 43210 - \u00c9tats-Unis)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OSU - Ohio State University [Columbus] (Ohio State University Enarson Hall 154 W 12th Avenue Columbus, Ohio 43210 - \u00c9tats-Unis)","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326501","display_name":"Jian Chen","orcid":"https://orcid.org/0000-0003-4769-1526"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Jian","raw_affiliation_strings":["OSU - Ohio State University [Columbus] (Ohio State University Enarson Hall 154 W 12th Avenue Columbus, Ohio 43210 - \u00c9tats-Unis)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OSU - Ohio State University [Columbus] (Ohio State University Enarson Hall 154 W 12th Avenue Columbus, Ohio 43210 - \u00c9tats-Unis)","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060664606","display_name":"Torsten M\u00f6ller","orcid":"https://orcid.org/0000-0003-1192-0710"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"M\u00f6ller, Torsten","raw_affiliation_strings":["University of Vienna [Vienna] (Universit\u00e4tsring 1,  1010 Wien - Autriche)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vienna [Vienna] (Universit\u00e4tsring 1,  1010 Wien - Autriche)","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024860629","display_name":"Petra Isenberg","orcid":"https://orcid.org/0000-0002-2948-6417"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Isenberg, Petra","raw_affiliation_strings":["AVIZ - Analysis and Visualization (DIGITEO, B\u00e2t. Claude Shannon - Universit\u00e9 Paris-Saclay, B\u00e2timent 660, 91190 Gif-sur-Yvette  - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AVIZ - Analysis and Visualization (DIGITEO, B\u00e2t. Claude Shannon - Universit\u00e9 Paris-Saclay, B\u00e2timent 660, 91190 Gif-sur-Yvette  - France)","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083454802","display_name":"Tobias Isenberg","orcid":"https://orcid.org/0000-0001-7953-8644"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Isenberg, Tobias","raw_affiliation_strings":["AVIZ - Analysis and Visualization (DIGITEO, B\u00e2t. Claude Shannon - Universit\u00e9 Paris-Saclay, B\u00e2timent 660, 91190 Gif-sur-Yvette  - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AVIZ - Analysis and Visualization (DIGITEO, B\u00e2t. Claude Shannon - Universit\u00e9 Paris-Saclay, B\u00e2timent 660, 91190 Gif-sur-Yvette  - France)","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037110552","display_name":"Michael Sedlmair","orcid":"https://orcid.org/0000-0001-7048-9292"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sedlmair, Michael","raw_affiliation_strings":["University of Stuttgart (Allemagne)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart (Allemagne)","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031570473","display_name":"Robert S. Laramee","orcid":"https://orcid.org/0000-0002-3874-6145"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laramee, Robert S.","raw_affiliation_strings":["UON - University of Nottingham, UK (University of Nottingham\r\nUniversity Park\r\nNottingham\r\nNG7 2RD - Royaume-Uni)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UON - University of Nottingham, UK (University of Nottingham\r\nUniversity Park\r\nNottingham\r\nNG7 2RD - Royaume-Uni)","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112684709","display_name":"Han-Wei Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Han-Wei","raw_affiliation_strings":["OSU - Ohio State University [Columbus] (Ohio State University Enarson Hall 154 W 12th Avenue Columbus, Ohio 43210 - \u00c9tats-Unis)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OSU - Ohio State University [Columbus] (Ohio State University Enarson Hall 154 W 12th Avenue Columbus, Ohio 43210 - \u00c9tats-Unis)","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Jian","raw_affiliation_strings":["ODU - Old Dominion University [Norfolk] (5115 Hampton Boulevard, Norfolk, VA 23529 - \u00c9tats-Unis)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ODU - Old Dominion University [Norfolk] (5115 Hampton Boulevard, Norfolk, VA 23529 - \u00c9tats-Unis)","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giles, C. Lee","raw_affiliation_strings":["Penn State - Pennsylvania State University (201 Old Main, University Park, Pennsylvania 16802 - \u00c9tats-Unis)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State - Pennsylvania State University (201 Old Main, University Park, Pennsylvania 16802 - \u00c9tats-Unis)","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5058228488"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.3884,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61305177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9975000023841858,"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":0.8382961750030518},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.605853259563446},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5834235548973083},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.545526385307312},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5164570808410645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5156337022781372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5109235644340515},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48820096254348755},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4337446391582489},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4150623083114624},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3448585271835327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382961750030518},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.605853259563446},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5834235548973083},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.545526385307312},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5164570808410645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5156337022781372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5109235644340515},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48820096254348755},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4337446391582489},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4150623083114624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3448585271835327},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2105.14931","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14931","pdf_url":"https://arxiv.org/pdf/2105.14931","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.14931","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.14931","pdf_url":"https://arxiv.org/pdf/2105.14931","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W167911094","https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1603719052","https://openalex.org/W1923184257","https://openalex.org/W1932742904","https://openalex.org/W2016753842","https://openalex.org/W2027929866","https://openalex.org/W2054901814","https://openalex.org/W2168190036","https://openalex.org/W2253675773","https://openalex.org/W2259424905","https://openalex.org/W2277195237","https://openalex.org/W2416987009","https://openalex.org/W2520300089","https://openalex.org/W2521863123","https://openalex.org/W2577020101","https://openalex.org/W2605102758","https://openalex.org/W2735449164","https://openalex.org/W2786480153","https://openalex.org/W2795424778","https://openalex.org/W2910897241","https://openalex.org/W2952610664","https://openalex.org/W2962957005","https://openalex.org/W2963201472","https://openalex.org/W2963427688","https://openalex.org/W2964346820","https://openalex.org/W2972004258","https://openalex.org/W3003711898","https://openalex.org/W3015453090","https://openalex.org/W3021218348","https://openalex.org/W3034069517","https://openalex.org/W3088290493","https://openalex.org/W3098562592","https://openalex.org/W3100388886","https://openalex.org/W3104049173","https://openalex.org/W3113753692","https://openalex.org/W3133525783","https://openalex.org/W3137959340","https://openalex.org/W3201992929","https://openalex.org/W3213038366"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"We":[0,52,88,110],"present":[1],"document":[2,24,63],"domain":[3],"randomization":[4],"(DDR),":[5],"the":[6,66,107],"first":[7],"successful":[8],"transfer":[9],"of":[10,37,49,78,93],"convolutional":[11],"neural":[12],"networks":[13],"(CNNs)":[14],"trained":[15],"only":[16],"on":[17],"graphically":[18],"rendered":[19],"pseudo-paper":[20],"pages":[21,29],"to":[22,45,60,91,119],"real-world":[23],"segmentation.":[25],"DDR":[26,58,90],"renders":[27],"pseudo-document":[28],"by":[30],"modeling":[31],"randomized":[32],"textual":[33],"and":[34,42,69,84,128],"non-textual":[35],"contents":[36],"interest,":[38],"with":[39],"user-defined":[40],"layout":[41],"font":[43],"styles":[44],"support":[46],"joint":[47],"learning":[48],"fine-grained":[50],"classes.":[51,164],"demonstrate":[53],"competitive":[54],"results":[55],"using":[56],"our":[57],"approach":[59],"extract":[61],"nine":[62],"classes":[64,122],"from":[65],"benchmark":[67],"CS-150":[68],"papers":[70],"published":[71],"in":[72,106],"two":[73],"domains,":[74],"namely":[75],"annual":[76],"meetings":[77],"Association":[79],"for":[80],"Computational":[81],"Linguistics":[82],"(ACL)":[83],"IEEE":[85],"Visualization":[86],"(VIS).":[87],"compare":[89],"conditions":[92],"style":[94,124],"mismatch,":[95],"fewer":[96],"or":[97],"more":[98,103],"noisy":[99],"samples":[100,137],"that":[101,112],"are":[102,154],"easily":[104],"obtained":[105],"real":[108],"world.":[109],"show":[111],"high-fidelity":[113],"semantic":[114,121],"information":[115],"is":[116],"not":[117],"necessary":[118],"label":[120],"but":[123],"mismatch":[125],"between":[126],"train":[127],"test":[129,149],"can":[130],"lower":[131],"model":[132],"accuracy.":[133],"Using":[134],"smaller":[135],"training":[136],"had":[138],"a":[139],"slightly":[140],"detrimental":[141],"effect.":[142],"Finally,":[143],"network":[144],"models":[145],"still":[146],"achieved":[147],"high":[148],"accuracy":[150],"when":[151],"correct":[152],"labels":[153],"diluted":[155],"towards":[156],"confusing":[157],"labels;":[158],"this":[159],"behavior":[160],"hold":[161],"across":[162],"several":[163]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2021-09-13T00:00:00"}