{"id":"https://openalex.org/W4387925380","doi":"https://doi.org/10.1145/3606040.3617444","title":"TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content","display_name":"TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4387925380","doi":"https://doi.org/10.1145/3606040.3617444"},"language":"en","primary_location":{"id":"doi:10.1145/3606040.3617444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606040.3617444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.10305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010012157","display_name":"Avinash Anand","orcid":"https://orcid.org/0009-0003-2479-0342"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Avinash Anand","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0003-2479-0342","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078468599","display_name":"Raj Jaiswal","orcid":"https://orcid.org/0009-0008-5044-1409"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raj Jaiswal","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0008-5044-1409","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102793834","display_name":"Pijush Bhuyan","orcid":"https://orcid.org/0009-0002-2132-0882"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pijush Bhuyan","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0002-2132-0882","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622863","display_name":"Mohit Gupta","orcid":"https://orcid.org/0009-0001-8528-5169"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohit Gupta","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0001-8528-5169","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035460473","display_name":"Siddhesh Bangar","orcid":"https://orcid.org/0000-0003-4349-0196"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddhesh Bangar","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-4349-0196","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093122632","display_name":"Md. Modassir Imam","orcid":"https://orcid.org/0009-0008-8145-6574"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Md. Modassir Imam","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0008-8145-6574","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":["Indraprastha Institute of Information Technology, Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-1028-9373","affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102743927","display_name":"Shin\u2019ichi Satoh","orcid":"https://orcid.org/0000-0001-6995-6447"},"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":"Shin'ichi Satoh","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6995-6447","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5010012157"],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":0.7065,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72701052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"18"},"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/T14319","display_name":"Currency Recognition and Detection","score":0.9904000163078308,"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":0.9772999882698059,"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":0.7810742259025574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7687238454818726},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5906544923782349},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5760101079940796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384886264801025},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.47754037380218506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4408773183822632},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43879106640815735},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43730199337005615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40127235651016235},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24739351868629456},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.24413400888442993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10645544528961182}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7810742259025574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687238454818726},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5906544923782349},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5760101079940796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384886264801025},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.47754037380218506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4408773183822632},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43879106640815735},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43730199337005615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40127235651016235},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24739351868629456},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.24413400888442993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10645544528961182},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3606040.3617444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606040.3617444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.10305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.10305","pdf_url":"https://arxiv.org/pdf/2404.10305","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.10305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.10305","pdf_url":"https://arxiv.org/pdf/2404.10305","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330597","display_name":"Indraprastha Institute of Information Technology, Delhi","ror":"https://ror.org/03vfp4g33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387925380.pdf","grobid_xml":"https://content.openalex.org/works/W4387925380.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2079525773","https://openalex.org/W2121061496","https://openalex.org/W2139053978","https://openalex.org/W2321821989","https://openalex.org/W2444353601","https://openalex.org/W2787523828","https://openalex.org/W2806327167","https://openalex.org/W2901890385","https://openalex.org/W2963791035","https://openalex.org/W2978036638","https://openalex.org/W3003525420","https://openalex.org/W3004042913","https://openalex.org/W3005638477","https://openalex.org/W3022479961","https://openalex.org/W3030520226","https://openalex.org/W3034997246","https://openalex.org/W3038771692","https://openalex.org/W3085623235","https://openalex.org/W3092459250","https://openalex.org/W3167404434","https://openalex.org/W3170567417","https://openalex.org/W3198862998","https://openalex.org/W3201816303","https://openalex.org/W3204824716","https://openalex.org/W3216322859","https://openalex.org/W4225274218","https://openalex.org/W4250638538","https://openalex.org/W4251989754","https://openalex.org/W4323240494","https://openalex.org/W6781639010"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2292997772","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W3037187668","https://openalex.org/W2055970094","https://openalex.org/W4234772502","https://openalex.org/W4394193569","https://openalex.org/W4377970376","https://openalex.org/W2169209883"],"abstract_inverted_index":{"The":[0,140],"automatic":[1],"recognition":[2,55,127],"of":[3,18,33,142,148,173,179,185],"tabular":[4,135],"data":[5,136,161],"in":[6,103,188],"document":[7,138],"images":[8],"presents":[9],"a":[10,154,182],"significant":[11],"challenge":[12],"due":[13],"to":[14,83,109,193],"the":[15,30,44,146,189,194],"diverse":[16,94],"range":[17],"table":[19,49,53,87,95,119,121,125,130,149,159],"styles":[20],"and":[21,40,52,79,99,106,124,132,163,175],"complex":[22,97],"structures.":[23],"Tables":[24],"offer":[25],"valuable":[26],"content":[27,126],"representation,":[28],"enhancing":[29],"predictive":[31],"capabilities":[32],"various":[34],"systems":[35],"such":[36],"as":[37],"search":[38],"engines":[39],"Knowledge":[41],"Graphs.":[42],"Addressing":[43],"two":[45],"main":[46],"problems,":[47],"namely":[48],"detection":[50],"(TD)":[51],"structure":[54,122],"(TSR),":[56],"has":[57],"traditionally":[58],"been":[59],"approached":[60],"independently.":[61],"In":[62],"this":[63],"research,":[64],"we":[65],"propose":[66],"an":[67,171,176],"end-to-end":[68],"pipeline":[69],"that":[70],"integrates":[71],"deep":[72],"learning":[73],"models,":[74],"including":[75],"DETR,":[76],"Cascade":[77],"TabNet,":[78],"PP":[80],"OCR":[81,177,190],"v2,":[82],"achieve":[84],"comprehensive":[85],"image-based":[86,158],"recognition.":[88],"This":[89],"integrated":[90],"approach":[91,153,169],"effectively":[92],"handles":[93],"styles,":[96],"structures,":[98],"image":[100],"distortions,":[101],"resulting":[102],"improved":[104],"accuracy":[105],"efficiency":[107],"compared":[108,192],"existing":[110],"methods":[111],"like":[112],"Table":[113,196],"Transformer.":[114],"Our":[115,167],"system":[116],"achieves":[117,170],"simultaneous":[118],"detection,":[120],"recognition,":[123,150],"(TCR),":[128],"preserving":[129],"structures":[131],"accurately":[133],"extracting":[134],"from":[137],"images.":[139],"integration":[141],"multiple":[143],"models":[144],"addresses":[145],"intricacies":[147],"making":[151],"our":[152],"promising":[155],"solution":[156],"for":[157],"understanding,":[160],"extraction,":[162],"information":[164],"retrieval":[165],"applications.":[166],"proposed":[168],"IOU":[172],"0.96":[174],"Accuracy":[178,191],"78%,":[180],"showcasing":[181],"remarkable":[183],"improvement":[184],"approximately":[186],"25%":[187],"previous":[195],"Transformer":[197],"approach.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-10-25T00:00:00"}