{"id":"https://openalex.org/W4323240494","doi":"https://doi.org/10.5220/0011682600003411","title":"Rethinking Image-Based Table Recognition Using Weakly Supervised Methods","display_name":"Rethinking Image-Based Table Recognition Using Weakly Supervised Methods","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323240494","doi":"https://doi.org/10.5220/0011682600003411"},"language":"en","primary_location":{"id":"doi:10.5220/0011682600003411","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011682600003411","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011682600003411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018335549","display_name":"Nam Tuan Ly","orcid":"https://orcid.org/0000-0002-0856-3196"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Nam Ly","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087434029","display_name":"Atsuhiro Takasu","orcid":"https://orcid.org/0000-0002-9061-7949"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiro Takasu","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101682562","display_name":"Phuc Nguyen","orcid":"https://orcid.org/0000-0003-1679-723X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Phuc Nguyen","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043917711","display_name":"Hideaki Takeda","orcid":"https://orcid.org/0000-0002-2909-7163"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideaki Takeda","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018335549"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":2.1863,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89481249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"872","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9746999740600586,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9355999827384949,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8105611801147461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7930593490600586},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6803306937217712},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.592682957649231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5854615569114685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5012180805206299},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.48764336109161377},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48062366247177124},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.44524991512298584},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4266206622123718},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.417579710483551},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.4129064679145813},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3877636790275574},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34517642855644226},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.12309682369232178}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8105611801147461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930593490600586},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6803306937217712},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.592682957649231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5854615569114685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5012180805206299},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.48764336109161377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48062366247177124},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.44524991512298584},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4266206622123718},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.417579710483551},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.4129064679145813},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3877636790275574},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34517642855644226},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.12309682369232178},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011682600003411","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011682600003411","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.07641","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.07641","pdf_url":"https://arxiv.org/pdf/2303.07641","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0011682600003411","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011682600003411","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2121061496","https://openalex.org/W2139053978","https://openalex.org/W2194187530","https://openalex.org/W2626873800","https://openalex.org/W2786162033","https://openalex.org/W2953106684","https://openalex.org/W3003514020","https://openalex.org/W3003760744","https://openalex.org/W3038771692","https://openalex.org/W3080882316","https://openalex.org/W3109870706","https://openalex.org/W3118722740","https://openalex.org/W3157482220","https://openalex.org/W3200280307","https://openalex.org/W3204824716","https://openalex.org/W4226243553","https://openalex.org/W4286950071","https://openalex.org/W4287811359","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4300812085","https://openalex.org/W4237171675","https://openalex.org/W2949303564","https://openalex.org/W2776054962","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4287728368","https://openalex.org/W3039174484"],"abstract_inverted_index":{"Most":[0],"of":[1,58,65,89],"the":[2,87,93,128,178,190],"previous":[3],"methods":[4],"for":[5,46,71,77,85],"table":[6,16,19,47,59,79,107,118,133,145,149,154],"recognition":[7,48,119,134],"rely":[8],"on":[9,52,167,193],"training":[10],"datasets":[11],"containing":[12],"many":[13],"richly":[14],"annotated":[15],"images.":[17,60],"Detailed":[18],"image":[20],"annotation,":[21,28],"e.g.,":[22],"cell":[23,83,91,161],"or":[24,185],"text":[25],"bounding":[26,162],"box":[27],"however,":[29],"is":[30,97],"costly":[31],"and":[32,81,109,125,151,160,169,174],"often":[33],"subjective.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,123],"propose":[39],"a":[40,74,82],"weakly":[41,180],"supervised":[42,181],"model":[43,63,182],"named":[44],"WSTabNet":[45],"that":[49,177],"relies":[50],"only":[51,106],"HTML":[53,112,158],"(or":[54,113],"LaTeX)":[55,114],"code-level":[56],"annotations":[57],"The":[61,164],"proposed":[62,179],"consists":[64],"three":[66],"main":[67],"parts:":[68],"an":[69],"encoder":[70],"feature":[72],"extraction,":[73],"structure":[75],"decoder":[76,84],"generating":[78],"structure,":[80],"predicting":[86],"content":[88],"each":[90],"in":[92],"table.":[94],"Our":[95],"system":[96],"trained":[98],"end-to-end":[99],"by":[100],"stochastic":[101],"gradient":[102],"descent":[103],"algorithms,":[104],"requiring":[105],"images":[108,155],"their":[110],"ground-truth":[111],"representations.":[115],"To":[116],"facilitate":[117],"with":[120,156],"deep":[121],"learning,":[122],"create":[124],"release":[126],"WikiTableSet,":[127],"largest":[129],"publicly":[130],"available":[131],"image-based":[132],"dataset":[135],"built":[136],"from":[137],"Wikipedia.":[138],"WikiTableSet":[139,168],"contains":[140],"nearly":[141],"4":[142],"million":[143],"English":[144],"images,":[146,150],"590K":[147],"Japanese":[148],"640k":[152],"French":[153],"corresponding":[157],"representation":[159],"boxes.":[163],"extensive":[165],"experiments":[166],"two":[170],"large-scale":[171],"datasets:":[172],"FinTabNet":[173],"PubTabNet":[175],"demonstrate":[176],"achieves":[183],"better,":[184],"similar":[186],"accuracies":[187],"compared":[188],"to":[189],"state-of-the-art":[191],"models":[192],"all":[194],"benchmark":[195],"datasets.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}