{"id":"https://openalex.org/W4323240651","doi":"https://doi.org/10.5220/0011685000003417","title":"An End-to-End Multi-Task Learning Model for Image-based Table Recognition","display_name":"An End-to-End Multi-Task Learning Model for Image-based Table Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323240651","doi":"https://doi.org/10.5220/0011685000003417"},"language":"en","primary_location":{"id":"doi:10.5220/0011685000003417","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011685000003417","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 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011685000003417","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":false,"raw_author_name":"Nam Ly","raw_affiliation_strings":["National Institute of Informatics (NII), Tokyo, Japan, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics (NII), Tokyo, Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","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 (NII), Tokyo, Japan, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics (NII), Tokyo, Japan, --- Select a Country ---","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":3.1559,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94267987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"634"},"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/T14319","display_name":"Currency Recognition and Detection","score":0.9969000220298767,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9951000213623047,"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/table","display_name":"Table (database)","score":0.8120805025100708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7972062826156616},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6288190484046936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596170961856842},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5815850496292114},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5417329668998718},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4957598149776459},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45861437916755676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4234457015991211},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41799378395080566},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32992810010910034},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2839093804359436}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8120805025100708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972062826156616},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6288190484046936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596170961856842},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5815850496292114},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5417329668998718},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4957598149776459},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45861437916755676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4234457015991211},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41799378395080566},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32992810010910034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2839093804359436},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011685000003417","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011685000003417","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 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.08648","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.08648","pdf_url":"https://arxiv.org/pdf/2303.08648","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:10.5220/0011685000003417","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011685000003417","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 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2121061496","https://openalex.org/W2139053978","https://openalex.org/W2626873800","https://openalex.org/W2786162033","https://openalex.org/W2953106684","https://openalex.org/W2962826786","https://openalex.org/W3003206728","https://openalex.org/W3003514020","https://openalex.org/W3003760744","https://openalex.org/W3038771692","https://openalex.org/W3080882316","https://openalex.org/W3118722740","https://openalex.org/W3157482220","https://openalex.org/W3200280307","https://openalex.org/W3204824716","https://openalex.org/W4226243553","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W3179968364","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Image-based":[0],"table":[1,12,18,38,68,93,95],"recognition":[2,43],"is":[3],"a":[4,27],"challenging":[5],"task":[6],"due":[7],"to":[8,47],"the":[9,15,22,32,117,121,124,139,143],"diversity":[10],"of":[11,17,21,74,92,123],"styles":[13],"and":[14,41,44,81,100,110,132],"complexity":[16],"structures.":[19],"Most":[20],"previous":[23],"methods":[24,145],"focus":[25],"on":[26,127],"non-end-to-end":[28],"approach":[29],"which":[30,85],"divides":[31],"problem":[33],"into":[34],"two":[35,53,128],"separate":[36,54,83],"sub-problems:":[37],"structure":[39,96],"recognition;":[40],"cell-content":[42,101],"then":[45],"attempts":[46],"solve":[48],"each":[49],"sub-problem":[50],"independently":[51],"using":[52],"systems.":[55],"In":[56,116],"this":[57],"paper,":[58],"we":[59,119],"propose":[60],"an":[61,113],"end-to-end":[62,114],"multi-task":[63],"learning":[64,89],"model":[65,72,126,141],"for":[66,88],"image-based":[67],"recognition.":[69,102],"The":[70,103,134],"proposed":[71,125,140],"consists":[73],"one":[75,78],"shared":[76,79],"encoder,":[77],"decoder,":[80],"three":[82,90],"decoders":[84],"are":[86],"used":[87],"sub-tasks":[91],"recognition:":[94],"recognition,":[97],"cell":[98],"detection,":[99],"whole":[104],"system":[105],"can":[106],"be":[107],"easily":[108],"trained":[109],"inferred":[111],"in":[112,146],"approach.":[115],"experiments,":[118],"evaluate":[120],"performance":[122],"large-scale":[129],"datasets:":[130],"FinTabNet":[131],"PubTabNet.":[133],"experiment":[135],"results":[136],"show":[137],"that":[138],"outperforms":[142],"state-of-the-art":[144],"all":[147],"benchmark":[148],"datasets.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-03-06T00:00:00"}