{"id":"https://openalex.org/W4367319001","doi":"https://doi.org/10.1145/3543873.3587609","title":"A New Annotation Method and Dataset for Layout Analysis of Long Documents","display_name":"A New Annotation Method and Dataset for Layout Analysis of Long Documents","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367319001","doi":"https://doi.org/10.1145/3543873.3587609"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3587609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3587609","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587609","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587609","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107024104","display_name":"Aman Ahuja","orcid":"https://orcid.org/0009-0002-8491-0193"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aman Ahuja","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078260039","display_name":"Kevin Dinh","orcid":"https://orcid.org/0009-0000-0307-5532"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Dinh","raw_affiliation_strings":["Virginia Tech, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045658213","display_name":"Brian Dinh","orcid":"https://orcid.org/0009-0008-3552-2067"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Dinh","raw_affiliation_strings":["Virginia Tech, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062743697","display_name":"William A. Ingram","orcid":"https://orcid.org/0000-0002-8307-8844"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William A. Ingram","raw_affiliation_strings":["Virginia Tech, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049148461","display_name":"Edward A. Fox","orcid":"https://orcid.org/0000-0003-1447-6870"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Fox","raw_affiliation_strings":["Virginia Tech, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5107024104"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.7204,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7148619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"834","last_page":"842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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":0.8739542961120605},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7939277291297913},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7629377841949463},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6372241377830505},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5810816287994385},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4742946922779083},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.46484464406967163},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44686853885650635},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4260510802268982},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4137362241744995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36536091566085815},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2341785728931427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2182070016860962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8739542961120605},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7939277291297913},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7629377841949463},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6372241377830505},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5810816287994385},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4742946922779083},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.46484464406967163},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44686853885650635},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4260510802268982},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4137362241744995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36536091566085815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2341785728931427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2182070016860962},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543873.3587609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3587609","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587609","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/114867","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/114867","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/cd7f3b3a-0a4a-4330-96cc-60fa5dce5351/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3543873.3587609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3587609","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543873.3587609","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1471725967","display_name":null,"funder_award_id":"LG-37-19-0078-19","funder_id":"https://openalex.org/F4320306122","funder_display_name":"Institute of Museum and Library Services"}],"funders":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367319001.pdf","grobid_xml":"https://content.openalex.org/works/W4367319001.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2099926976","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3003711898","https://openalex.org/W3104953317","https://openalex.org/W3113753692","https://openalex.org/W3176028514","https://openalex.org/W3176851559","https://openalex.org/W3201693581","https://openalex.org/W3202466114","https://openalex.org/W4205746567","https://openalex.org/W4304013646","https://openalex.org/W4307926863","https://openalex.org/W4320487943","https://openalex.org/W4404783426"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2053943328","https://openalex.org/W3046984657","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Parsing":[0],"long":[1,116],"documents,":[2],"such":[3,45,50],"as":[4,51],"books,":[5],"theses,":[6],"and":[7,53,61,75,85,185,245,247],"dissertations,":[8],"is":[9,248],"an":[10,121],"important":[11],"component":[12],"of":[13,44,72,90,93,104,140,169,201,223,240,253],"information":[14],"extraction":[15],"from":[16,81,210,256],"scholarly":[17,48,115],"documents.":[18,97,117],"Layout":[19],"analysis":[20,113],"methods":[21,46],"based":[22,111,133],"on":[23,166,182],"object":[24,109,131,180,258],"detection":[25,110,132,181],"have":[26],"been":[27],"developed":[28],"in":[29,95,195,251],"recent":[30],"years":[31],"to":[32,64,108,125,144,164,190],"help":[33,126,145],"with":[34,215],"PDF":[35],"document":[36,241],"parsing.":[37],"However,":[38],"several":[39],"challenges":[40,106],"hinder":[41],"the":[42,58,69,76,82,87,96,105,138,150,158,191,230],"adoption":[43],"for":[47,114,130,153,179,217],"documents":[49,74],"theses":[52,184],"dissertations.":[54],"These":[55],"include":[56],"(a)":[57],"manual":[59],"effort":[60],"resources":[62],"required":[63,152],"annotate":[65],"training":[66,128,254],"datasets,":[67],"(b)":[68],"scanned":[70,212,244],"nature":[71],"many":[73],"inherent":[77],"noise":[78],"present":[79],"resulting":[80],"capture":[83],"process,":[84],"(c)":[86],"imbalanced":[88],"distribution":[89],"various":[91],"types":[92],"elements":[94],"In":[98,188],"this":[99],"paper,":[100],"we":[101,119],"address":[102],"some":[103],"related":[107],"layout":[112,134],"First,":[118],"propose":[120],"AI-aided":[122],"annotation":[123],"method":[124],"develop":[127],"datasets":[129],"analysis.":[135],"This":[136],"leverages":[137],"knowledge":[139],"existing":[141],"trained":[142],"models":[143],"human":[146],"annotators,":[147],"thus":[148,236],"reducing":[149],"time":[151],"annotation.":[154],"It":[155],"also":[156,173],"addresses":[157],"class":[159],"imbalance":[160],"problem,":[161],"guiding":[162],"annotators":[163],"focus":[165],"labeling":[167],"instances":[168],"rare":[170,224],"classes.":[171],"We":[172],"introduce":[174],"ETD-ODv2,":[175],"a":[176,238],"novel":[177],"dataset":[178,199,235],"electronic":[183],"dissertations":[186],"(ETDs).":[187],"addition":[189],"page":[192,207,219],"images":[193,208,220],"included":[194],"ETD-OD":[196],"[1],":[197],"our":[198],"consists":[200],"more":[202],"than":[203],"16K":[204],"manually":[205],"annotated":[206],"originating":[209],"100":[211],"ETDs,":[213],"along":[214],"annotations":[216],"20K":[218],"primarily":[221],"consisting":[222],"classes":[225],"that":[226],"were":[227],"labeled":[228],"using":[229],"proposed":[231],"framework.":[232],"The":[233],"new":[234],"covers":[237],"diversity":[239],"types,":[242],"viz.,":[243],"born-digital,":[246],"better":[249],"balanced":[250],"terms":[252],"samples":[255],"different":[257],"categories.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}