{"id":"https://openalex.org/W4313066026","doi":"https://doi.org/10.1109/etfa52439.2022.9921455","title":"Towards Tabular Data Extraction From Richly-Structured Documents Using Supervised and Weakly-Supervised Learning","display_name":"Towards Tabular Data Extraction From Richly-Structured Documents Using Supervised and Weakly-Supervised Learning","publication_year":2022,"publication_date":"2022-09-06","ids":{"openalex":"https://openalex.org/W4313066026","doi":"https://doi.org/10.1109/etfa52439.2022.9921455"},"language":"en","primary_location":{"id":"doi:10.1109/etfa52439.2022.9921455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/etfa52439.2022.9921455","pdf_url":null,"source":{"id":"https://openalex.org/S4363607916","display_name":"2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061813638","display_name":"Arnab Ghosh Chowdhury","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arnab Ghosh Chowdhury","raw_affiliation_strings":["Osnabrück University,Semantic Information Systems (SIS) Group,Osnabrück,Germany"],"affiliations":[{"raw_affiliation_string":"Osnabrück University,Semantic Information Systems (SIS) Group,Osnabrück,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067884909","display_name":"Martin ben Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin ben Ahmed","raw_affiliation_strings":["Osnabrück University,Semantic Information Systems (SIS) Group,Osnabrück,Germany"],"affiliations":[{"raw_affiliation_string":"Osnabrück University,Semantic Information Systems (SIS) Group,Osnabrück,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011835245","display_name":"Martin Atzmueller","orcid":"https://orcid.org/0000-0002-2480-6901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Atzmueller","raw_affiliation_strings":["Osnabrück University,Semantic Information Systems (SIS) Group,Osnabrück,Germany"],"affiliations":[{"raw_affiliation_string":"Osnabrück University,Semantic Information Systems (SIS) Group,Osnabrück,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061813638"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45180379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9919999837875366,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9745000004768372,"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":0.8352020978927612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6568498015403748},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6378445029258728},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5979846119880676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5495973825454712},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5484868884086609},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.47311684489250183},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42443156242370605},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3931012749671936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31966930627822876},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13772791624069214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352020978927612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568498015403748},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6378445029258728},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5979846119880676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5495973825454712},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5484868884086609},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.47311684489250183},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42443156242370605},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3931012749671936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31966930627822876},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13772791624069214},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/etfa52439.2022.9921455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/etfa52439.2022.9921455","pdf_url":null,"source":{"id":"https://openalex.org/S4363607916","display_name":"2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337753","display_name":"Interreg","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W145709626","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2786162033","https://openalex.org/W2948818729","https://openalex.org/W2963073614","https://openalex.org/W2963420691","https://openalex.org/W2970042171","https://openalex.org/W2987932197","https://openalex.org/W3003711898","https://openalex.org/W3034997246","https://openalex.org/W3035011051","https://openalex.org/W3038771692","https://openalex.org/W3107064625","https://openalex.org/W3124372372","https://openalex.org/W4229909500","https://openalex.org/W4320013936","https://openalex.org/W6620707391","https://openalex.org/W6763233178","https://openalex.org/W6780118464","https://openalex.org/W6791742336","https://openalex.org/W6803287389"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W3158004940","https://openalex.org/W2001652754","https://openalex.org/W2549006548","https://openalex.org/W4214932115","https://openalex.org/W2807311372","https://openalex.org/W3043252291","https://openalex.org/W2379065761","https://openalex.org/W2972035100","https://openalex.org/W98693656"],"abstract_inverted_index":{"Tabular":[0],"information":[1,145],"extraction":[2,146],"from":[3,148],"richly":[4,149],"structured":[5,150],"documents":[6],"is":[7,37,49],"a":[8,68,111,132],"challenging":[9],"task,":[10],"due":[11],"to":[12,40],"rich":[13],"table":[14,20,82,90,116],"and":[15,26,118],"document":[16,19,81],"structures.":[17],"Supervised":[18],"detection":[21,79,117],"approaches":[22,106,142],"include":[23],"image":[24,70],"classification":[25],"object":[27,78],"localization":[28],"methods,":[29],"typically":[30],"relying":[31],"on":[32,43,94,124],"manually":[33],"annotated":[34],"data":[35],"which":[36],"often":[38],"costly":[39],"acquire":[41],"specially":[42],"domain":[44,133],"specific":[45,134],"dataset.":[46],"Self-supervised":[47],"learning":[48,113],"quickly":[50],"closing":[51],"the":[52,65,73,95,108,137,140],"gap":[53],"with":[54],"supervised":[55,77],"methods":[56],"in":[57,76],"computer":[58],"vision":[59],"research":[60],"[1].":[61],"This":[62],"paper":[63],"investigates":[64],"impact":[66],"of":[67,110,139],"self-supervised":[69],"classifier":[71],"as":[72,107,129,131],"primary":[74],"backbone":[75],"for":[80,89,115],"detection.":[83],"Furthermore,":[84],"we":[85],"study":[86],"an":[87],"approach":[88,101],"structure":[91,119],"recognition":[92],"based":[93],"pix2pix":[96],"Generative":[97],"Adversarial":[98],"Networks":[99],"(GAN)":[100],"[2].":[102],"We":[103],"propose":[104],"these":[105],"basis":[109],"machine":[112],"pipeline":[114],"recognition.":[120],"Our":[121],"evaluation":[122],"results":[123],"different":[125],"publicly":[126],"available":[127],"datasets,":[128],"well":[130],"dataset":[135],"demonstrate":[136],"efficacy":[138],"presented":[141],"towards":[143],"tabular":[144],"pipelines":[147],"documents.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}