{"id":"https://openalex.org/W3201992929","doi":"https://doi.org/10.21227/326q-bf39","title":"Three Benchmark Datasets for Scholarly Article Layout Analysis","display_name":"Three Benchmark Datasets for Scholarly Article Layout Analysis","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3201992929","doi":"https://doi.org/10.21227/326q-bf39","mag":"3201992929"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-03229891v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03229891","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021, &#x27E8;10.21227/326q-bf39&#x27E9;","raw_type":"Other publications"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-03229891","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":["The Ohio State University","Ohio State Univ., Columbus"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State Univ., Columbus","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326436","display_name":"Jian Chen","orcid":"https://orcid.org/0000-0002-1599-0831"},"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":["The Ohio State University","Ohio State Univ., Columbus"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State Univ., Columbus","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","University of Vienna, Vienna#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Vienna","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"University of Vienna, Vienna#TAB#","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/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Isenberg, Petra","raw_affiliation_strings":["INRIA","Analysis and Visualization"],"affiliations":[{"raw_affiliation_string":"INRIA","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Analysis and Visualization","institution_ids":[]}]},{"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/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Isenberg, Tobias","raw_affiliation_strings":["INRIA","Analysis and Visualization"],"affiliations":[{"raw_affiliation_string":"INRIA","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Analysis and Visualization","institution_ids":[]}]},{"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","Univ. of Stuttgart#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Univ. of Stuttgart#TAB#","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":["University of Nottingham","University of Nottingham , UK"],"affiliations":[{"raw_affiliation_string":"University of Nottingham","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"University of Nottingham , UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065630217","display_name":"Han\u2010Wei Shen","orcid":"https://orcid.org/0000-0002-1211-2320"},"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":["The Ohio State University","Ohio State Univ., Columbus"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State Univ., Columbus","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"]},{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]}],"countries":["GH","US"],"is_corresponding":false,"raw_author_name":"Wu, Jian","raw_affiliation_strings":["Old Dominion University","Old Dominion Univ, Norfolk"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]},{"raw_affiliation_string":"Old Dominion Univ, Norfolk","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":["The Pennsylvania State University","Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":6,"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":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.8450000286102295,"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":0.8450000286102295,"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":0.7282000184059143,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8021361827850342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5968114137649536},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4515950381755829},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44913047552108765},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43127188086509705},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12273561954498291},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09266316890716553}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8021361827850342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968114137649536},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4515950381755829},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44913047552108765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43127188086509705},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12273561954498291},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09266316890716553}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-03229891v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03229891","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021, &#x27E8;10.21227/326q-bf39&#x27E9;","raw_type":"Other publications"},{"id":"doi:10.21227/326q-bf39","is_oa":true,"landing_page_url":"https://doi.org/10.21227/326q-bf39","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03229891v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03229891","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2021, &#x27E8;10.21227/326q-bf39&#x27E9;","raw_type":"Other publications"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370"],"abstract_inverted_index":{"This":[0,63,224],"dataset":[1,64,91,225],"contains":[2,65],"three":[3,94],"benchmark":[4,90],"datasets":[5],"as":[6],"part":[7],"of":[8,12,87,165,204],"the":[9,88,125,146,151,166],"scholarly":[10],"output":[11],"and":[13,36,55,78,98,115,206],"ICDAR":[14],"2021":[15],"paper:":[16],"Meng":[17],"Ling,":[18,181],"Jian":[19,34],"Chen,":[20,179],"Torsten":[21],"Moller,":[22],"Petra":[23],"Isenberg,":[24,26,185,187],"Tobias":[25],"Michael":[27],"Sedlmair,":[28,189],"Robert":[29],"S.":[30],"Laramee,":[31,193],"Han-Wei":[32],"Shen,":[33,195],"Wu,":[35],"C.":[37],"Lee":[38],"Giles,":[39],"Document":[40,46,53],"Domain":[41],"Randomization":[42],"for":[43],"Deep":[44],"Learning":[45],"Layout":[47],"Extraction,":[48],"16th":[49],"International":[50],"Conference":[51,128],"on":[52,129],"Analysis":[54],"Recognition":[56],"(ICDAR)":[57],"2021.":[58],"September":[59],"5-10,":[60],"Lausanne,":[61],"Switzerland.":[62],"nine":[66,101],"class":[67],"lables:":[68],"abstract,":[69],"algorithm,":[70],"author,":[71],"body":[72],"text,":[73],"caption,":[74],"equation,":[75],"figure,":[76],"table,":[77,97],"title.":[79],"*":[80],"Dataset":[81,134,156],"1:":[82],"CS-150x,":[83],"is":[84,226],"an":[85],"extension":[86],"classical":[89],"CS-150":[92],"from":[93,117,145,150,173,208],"classes":[95],"(figure,":[96],"caption)":[99],"to":[100,220],"classes,":[102],"1176":[103],"pages,":[104,177],"Clark,":[105],"C.,":[106],"Divvala,":[107],"S.:":[108],"Looking":[109],"beyond":[110],"text:":[111],"Extracting":[112],"figures,":[113],"tables":[114,207],"captions":[116],"com-":[118],"puter":[119],"science":[120],"papers.":[121],"In:":[122],"Workshops":[123],"at":[124,230],"29th":[126],"AAAI":[127],"Artificial":[130],"Intelligence":[131],"(2015),":[132],"https://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10092.*":[133],"2:":[135],"ACL300,":[136],"has":[137,159],"300":[138],"randomly":[139,170],"sampled":[140],"articles":[141,172],"(or":[142,162],"2508":[143],"pages)":[144,164],"55,759":[147],"papers":[148],"scraped":[149],"ACL":[152],"anthology":[153],"website;":[154],"https://www.aclweb.org/anthology/.*":[155],"3:":[157],"VIS300,":[158],"about":[160],"10%":[161],"2619":[163],"document":[167],"pages":[168],"in":[169],"partitioned":[171],"26,350":[174],"VIS":[175],"paper":[176],".":[178],"J.,":[180],"M.,":[182,190],"Li,":[183],"R.,":[184],"P.,":[186],"T.,":[188,192],"M\u00f6ller,":[191],"R.S.,":[194],"H.W.,":[196],"W\u00fcnsche,":[197],"K.,":[198],"Wang,":[199],"Q.:":[200],"VIS30K:":[201],"A":[202],"collection":[203],"figures":[205],"IEEE":[209,213],"visualization":[210],"conference":[211],"publications.":[212],"Trans.":[214],"Vis.":[215],"Comput.":[216],"Graph.":[217],"27":[218],"(2021),":[219],"appear":[221],"doi:":[222],"10.1109/TVCG.2021.3054916":[223],"also":[227],"available":[228],"online":[229],"https://web.cse.ohio-state.edu/~chen.8028/ICDAR2021Benchmark/.":[231]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
