{"id":"https://openalex.org/W4393551892","doi":"https://doi.org/10.5281/zenodo.8347059","title":"TexBiG Dataset for Analysing Complex Document Layouts in the Digital Humanities","display_name":"TexBiG Dataset for Analysing Complex Document Layouts in the Digital Humanities","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4393551892","doi":"https://doi.org/10.5281/zenodo.8347059"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:8347059","is_oa":true,"landing_page_url":"https://zenodo.org/record/8347059","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://zenodo.org/record/8347059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001285622","display_name":"David Tschirschwitz","orcid":"https://orcid.org/0000-0001-5344-4172"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tschirschwitz, David","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066824669","display_name":"Franziska Klemstein","orcid":"https://orcid.org/0000-0003-3137-6732"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klemstein, Franziska","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stein, Benno","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021158971","display_name":"Volker Rodehorst","orcid":"https://orcid.org/0000-0002-4815-0118"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rodehorst, Volker","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001285622"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9789999723434448,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9789999723434448,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/digital-humanities","display_name":"Digital humanities","score":0.7280066013336182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.536173939704895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40688133239746094},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3840089440345764},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36965546011924744},{"id":"https://openalex.org/keywords/humanities","display_name":"Humanities","score":0.32981953024864197},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.15088990330696106}],"concepts":[{"id":"https://openalex.org/C24351657","wikidata":"https://www.wikidata.org/wiki/Q1026962","display_name":"Digital humanities","level":2,"score":0.7280066013336182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536173939704895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40688133239746094},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3840089440345764},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36965546011924744},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.32981953024864197},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.15088990330696106}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:8347059","is_oa":true,"landing_page_url":"https://zenodo.org/record/8347059","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.8347059","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8347059","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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:zenodo.org:8347059","is_oa":true,"landing_page_url":"https://zenodo.org/record/8347059","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3016750667","https://openalex.org/W2134911674","https://openalex.org/W2468691689","https://openalex.org/W4255837503","https://openalex.org/W2934626505","https://openalex.org/W2527879301","https://openalex.org/W1480800433","https://openalex.org/W170186150","https://openalex.org/W4366680058"],"abstract_inverted_index":{"This":[0],"is":[1,60,76],"the":[2,5,15,33,39,42,58,71,86,123,134,137],"dataset":[3,59,81,94],"for":[4,9,82,103],"paper":[6,40],"\"A":[7],"Dataset":[8],"Analysing":[10],"Complex":[11],"Document":[12],"Layouts":[13],"in":[14,25,50,85,133],"Digital":[16],"Humanities":[17],"and":[18,89,100],"its":[19,26],"Evaluation":[20],"with":[21,53,107],"Krippendorff":[22],"\u2019s":[23],"Alpha\"":[24],"second":[27],"version,":[28],"containing":[29],"an":[30],"update":[31],"of":[32,57,136],"test":[34,114],"images":[35,115],"(without":[36],"annotations)":[37],"from":[38],"\"Drawing":[41],"Same":[43],"Bounding":[44],"Box":[45],"Twice?":[46],"Coping":[47],"Noisy":[48],"Annotations":[49],"Object":[51],"Detection":[52],"Repeated":[54],"Labels\".":[55],"Organization":[56],"also":[61],"updated":[62],"to":[63,67,119],"make":[64,120],"it":[65],"easier":[66],"use.":[68],"TexBiG":[69],"(from":[70],"German":[72],"Text-Bild-Gef\u00fcge,":[73],"meaning":[74],"Text-Image-Structure)":[75],"a":[77],"document":[78],"layout":[79],"analysis":[80],"historical":[83],"documents":[84],"late":[87],"19th":[88],"early":[90],"20th":[91],"century.":[92],"The":[93,112,127],"provides":[95],"instance":[96],"segmentation":[97],"(bounding":[98],"boxes":[99],"polygons/masks)":[101],"annotations":[102],"19":[104],"different":[105],"classes":[106],"more":[108],"then":[109],"52.000":[110],"instances.":[111],"added":[113],"can":[116,130],"be":[117,131],"used":[118],"submission":[121],"on":[122,125],"leaderboard":[124],"EvalAI.":[126],"annotation":[128],"guideline":[129],"found":[132],"first":[135],"dataset.":[138]},"counts_by_year":[],"updated_date":"2026-02-05T00:54:17.221276","created_date":"2025-10-10T00:00:00"}
