{"id":"https://openalex.org/W4290927927","doi":"https://doi.org/10.1145/3534678.3539043","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Segmentation","display_name":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Segmentation","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290927927","doi":"https://doi.org/10.1145/3534678.3539043"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539043","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3534678.3539043","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109863471","display_name":"Birgit Pfitzmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Birgit Pfitzmann","raw_affiliation_strings":["IBM Research, Rueschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Rueschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046722997","display_name":"Christoph Auer","orcid":"https://orcid.org/0000-0001-5761-0422"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christoph Auer","raw_affiliation_strings":["IBM Research, Rueschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Rueschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038675415","display_name":"Michele Dolfi","orcid":"https://orcid.org/0000-0001-7216-8505"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michele Dolfi","raw_affiliation_strings":["IBM Research, Rueschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Rueschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021157455","display_name":"Ahmed Nassar","orcid":"https://orcid.org/0000-0002-9468-0822"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ahmed S. Nassar","raw_affiliation_strings":["IBM Research, Rueschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Rueschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024778597","display_name":"Peter Staar","orcid":"https://orcid.org/0000-0002-8088-0823"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peter Staar","raw_affiliation_strings":["IBM Research, Rueschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research, Rueschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109863471"],"corresponding_institution_ids":["https://openalex.org/I4210126328"],"apc_list":null,"apc_paid":null,"fwci":5.6698,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.96877883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3743","last_page":"3751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9850000143051147,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9847999811172485,"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":0.8466582298278809},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6803991198539734},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6172731518745422},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5997506976127625},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5983051061630249},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5745439529418945},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5496960878372192},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5290906429290771},{"id":"https://openalex.org/keywords/page-layout","display_name":"Page layout","score":0.49321669340133667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4423266649246216},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.42359262704849243},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3863025903701782},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17730119824409485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466582298278809},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6803991198539734},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6172731518745422},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5997506976127625},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5983051061630249},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5745439529418945},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5496960878372192},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5290906429290771},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.49321669340133667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4423266649246216},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.42359262704849243},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3863025903701782},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17730119824409485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539043","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3534678.3539043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539043","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2022351003","https://openalex.org/W2102605133","https://openalex.org/W2529247374","https://openalex.org/W2806076122","https://openalex.org/W2915774443","https://openalex.org/W2954996726","https://openalex.org/W2990268359","https://openalex.org/W2997154779","https://openalex.org/W3003711898","https://openalex.org/W3004042913","https://openalex.org/W3034971973","https://openalex.org/W3096609285","https://openalex.org/W3104953317","https://openalex.org/W3113753692","https://openalex.org/W3160285664","https://openalex.org/W3175487048","https://openalex.org/W3198790561","https://openalex.org/W3201871940","https://openalex.org/W3210029908","https://openalex.org/W3210938789","https://openalex.org/W4205487349","https://openalex.org/W4289751790","https://openalex.org/W6639102338","https://openalex.org/W6735463952","https://openalex.org/W6778485988"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4308237185"],"abstract_inverted_index":{"Accurate":[0],"document":[1,11],"layout":[2,36,55,76,128,208],"analysis":[3],"is":[4,192],"a":[5,96,118,134,143,166],"key":[6],"requirement":[7],"for":[8,165,222],"high-quality":[9],"PDF":[10,125],"conversion.":[12],"With":[13],"the":[14,72,75,127,152,183,211,219],"recent":[15],"availability":[16],"of":[17,44,74,136,145,168,193,210],"public,":[18],"large":[19],"ground-truth":[20],"datasets":[21,42],"such":[22,49,65],"as":[23,66],"PubLayNet":[24],"and":[25,38,68,88,147,204,217],"DocBank,":[26],"deep-learning":[27],"models":[28,82,178,199,213],"have":[29],"proven":[30],"to":[31,47,116,150],"be":[32],"very":[33],"effective":[34],"at":[35],"detection":[37,171],"segmentation.":[39],"While":[40],"these":[41,81,177],"are":[43,59,83,214],"adequate":[45],"size":[46],"train":[48],"models,":[50],"they":[51,58],"severely":[52],"lack":[53],"in":[54,103,121],"variability":[56,120],"since":[57],"sourced":[60],"from":[61,112],"scientific":[62],"article":[63],"repositories":[64],"PubMed":[67],"arXiv":[69],"only.":[70],"Consequently,":[71],"accuracy":[73,161],"segmentation":[77],"drops":[78],"significantly":[79],"when":[80],"applied":[84],"on":[85,201],"more":[86,215],"challenging":[87],"diverse":[89,113],"layouts.":[90,122],"In":[91,155],"this":[92],"paper,":[93],"we":[94,158,187,197],"presentDocLayNet,":[95],"new,":[97],"publicly":[98],"available,":[99],"document-layout":[100,224],"annotation":[101],"dataset":[102],"COCO":[104],"format.":[105],"It":[106],"contains":[107],"80863":[108],"manually":[109],"annotated":[110],"pages":[111,149],"data":[114],"sources":[115],"represent":[117],"wide":[119],"For":[123],"each":[124],"page,":[126],"annotations":[129],"provide":[130,159,188],"labelled":[131],"bounding-boxes":[132],"with":[133],"choice":[135,221],"11":[137],"distinct":[138],"classes.":[139],"DocLayNet":[140,191],"also":[141,174],"provides":[142],"subset":[144],"double-":[146],"triple-annotated":[148],"determine":[151],"inter-annotator":[153,184],"agreement.":[154,185],"multiple":[156],"experiments,":[157],"baseline":[160],"scores":[162],"(in":[163],"mAP)":[164],"set":[167],"popular":[169],"object":[170],"models.":[172],"We":[173],"demonstrate":[175],"that":[176,190,207],"fall":[179],"approximately":[180],"10%":[181],"behind":[182],"Furthermore,":[186],"evidence":[189],"sufficient":[194],"size.":[195],"Lastly,":[196],"compare":[198],"trained":[200],"PubLayNet,":[202],"DocBank":[203],"DocLayNet,":[205],"showing":[206],"predictions":[209],"DocLayNet-trained":[212],"robust":[216],"thus":[218],"preferred":[220],"general-purpose":[223],"analysis.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":24}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2022-08-13T00:00:00"}