{"id":"https://openalex.org/W4416870303","doi":"https://doi.org/10.1007/s10032-025-00562-6","title":"Data rescue of historical tables through semi-supervised table structure recognition","display_name":"Data rescue of historical tables through semi-supervised table structure recognition","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4416870303","doi":"https://doi.org/10.1007/s10032-025-00562-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/42333274"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-025-00562-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00562-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00562-6.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00562-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056117065","display_name":"Loitongbam Gyanendro Singh","orcid":"https://orcid.org/0000-0002-7594-6146"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Loitongbam Gyanendro Singh","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088719080","display_name":"Stuart E. Middleton","orcid":"https://orcid.org/0000-0001-8305-8176"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stuart E. Middleton","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056117065"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.4424,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66283012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"29","issue":"2","first_page":"429","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9406999945640564,"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":0.9406999945640564,"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":0.017500000074505806,"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/T11719","display_name":"Data Quality and Management","score":0.007400000002235174,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7138000130653381},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6593999862670898},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.49480000138282776},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.37619999051094055},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3260999917984009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900999784469604},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7138000130653381},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6593999862670898},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48890000581741333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37040001153945923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36550000309944153},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10032-025-00562-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00562-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00562-6.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmid:42333274","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42333274","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International journal on document analysis and recognition (Online)","raw_type":"Journal Article"},{"id":"pmh:oai:eprints.soton.ac.uk:507139","is_oa":false,"landing_page_url":"http://doi.org/10.1007/s10032-025-00562-6>).","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10032-025-00562-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00562-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00562-6.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2831640940","display_name":"Global Surface Air Temperature (GloSAT)","funder_award_id":"NE/S015604/1","funder_id":"https://openalex.org/F4320334631","funder_display_name":"Natural Environment Research Council"}],"funders":[{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320320331","display_name":"Met Office","ror":"https://ror.org/01ch2yn61"},{"id":"https://openalex.org/F4320334631","display_name":"Natural Environment Research Council","ror":"https://ror.org/02b5d8509"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416870303.pdf","grobid_xml":"https://content.openalex.org/works/W4416870303.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2023843250","https://openalex.org/W2028395539","https://openalex.org/W2137998699","https://openalex.org/W2162407558","https://openalex.org/W2899266989","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W3003496674","https://openalex.org/W3004042913","https://openalex.org/W3014641072","https://openalex.org/W3034997246","https://openalex.org/W3096609285","https://openalex.org/W3107064625","https://openalex.org/W3109870706","https://openalex.org/W3118722740","https://openalex.org/W3184971748","https://openalex.org/W3202465222","https://openalex.org/W3213341651","https://openalex.org/W4225829029","https://openalex.org/W4288046074","https://openalex.org/W4304014014","https://openalex.org/W4312233877","https://openalex.org/W4312554912","https://openalex.org/W4323044637","https://openalex.org/W4366975855","https://openalex.org/W4385470899","https://openalex.org/W4392547841"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"study":[2],"uses":[3],"a":[4,78,138],"novel":[5],"semi-supervised":[6,79,92,124],"learning":[7,125],"framework":[8],"to":[9,147],"explore":[10],"Tabular":[11],"Structure":[12],"Recognition":[13],"(TSR)":[14],"for":[15,27,62,85,141],"digitizing":[16],"historical":[17,59,111,154],"documents,":[18,112],"specifically":[19],"employing":[20],"the":[21,53,83,104,114,148],"CascadeTabNet":[22],"model.":[23],"TSR":[24,128],"is":[25,161],"crucial":[26],"transforming":[28],"archival":[29],"tabular":[30],"data":[31,87],"into":[32],"digital":[33],"formats,":[34],"enhancing":[35],"accessibility":[36,152],"and":[37,49,89,106,113,130,145,150],"analysis":[38],"across":[39,101],"various":[40],"research":[41,71,74],"fields.":[42],"Challenges":[43],"like":[44],"physical":[45],"degradation,":[46],"inconsistent":[47],"lighting,":[48],"non-standard":[50],"handwriting":[51],"hinder":[52],"generation":[54],"of":[55,58,153],"high-quality":[56],"annotations":[57],"documents":[60,117],"needed":[61],"effective":[63],"model":[64,95],"training.":[65],"To":[66],"address":[67],"these":[68],"issues,":[69],"this":[70,159],"explores":[72],"two":[73],"questions:":[75],"(i)":[76],"Can":[77],"training":[80,93],"approach":[81],"reduce":[82],"need":[84],"expensive":[86],"annotations?":[88],"(ii)":[90],"Does":[91],"improve":[94],"robustness?":[96],"We":[97],"applied":[98],"our":[99],"methodology":[100],"three":[102],"datasets:":[103],"GloSAT":[105],"ICDAR-2019":[107],"datasets":[108],"based":[109],"on":[110,133,164],"predominantly":[115],"modern":[116],"PubTabNet":[118],"dataset.":[119],"Our":[120],"results":[121],"indicate":[122],"that":[123],"substantially":[126],"increases":[127],"accuracy":[129],"decreases":[131],"dependency":[132],"extensive":[134],"labelled":[135],"datasets,":[136],"providing":[137],"robust":[139],"solution":[140],"large-scale":[142],"digitization":[143],"initiatives":[144],"contributing":[146],"preservation":[149],"improved":[151],"data.":[155],"All":[156],"code":[157],"from":[158],"paper":[160],"freely":[162],"available":[163],"GitHub":[165],"(":[166],"https://github.com/stuartemiddleton/glosat_table_dataset":[167],").":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-12-01T00:00:00"}