{"id":"https://openalex.org/W2074966879","doi":"https://doi.org/10.1145/2361354.2361365","title":"A methodology for evaluating algorithms for table understanding in PDF documents","display_name":"A methodology for evaluating algorithms for table understanding in PDF documents","publication_year":2012,"publication_date":"2012-09-04","ids":{"openalex":"https://openalex.org/W2074966879","doi":"https://doi.org/10.1145/2361354.2361365","mag":"2074966879"},"language":"en","primary_location":{"id":"doi:10.1145/2361354.2361365","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","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/A5039522364","display_name":"Max G\u00f6bel","orcid":"https://orcid.org/0000-0001-6756-5231"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Max G\u00f6bel","raw_affiliation_strings":["Technische Universit\u00e4t Wien, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102797774","display_name":"Tamir Hassan","orcid":"https://orcid.org/0000-0002-1940-1037"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tamir Hassan","raw_affiliation_strings":["Technische Universit\u00e4t Wien, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038972694","display_name":"Ermelinda Oro","orcid":"https://orcid.org/0000-0002-5529-1007"},"institutions":[{"id":"https://openalex.org/I197604219","display_name":"National Academies of Sciences, Engineering, and Medicine","ror":"https://ror.org/02eq2w707","country_code":"US","type":"government","lineage":["https://openalex.org/I197604219"]},{"id":"https://openalex.org/I4210142749","display_name":"Italian Resuscitation Council","ror":"https://ror.org/04y9b7t58","country_code":"IT","type":"other","lineage":["https://openalex.org/I4210142749"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"funder","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Ermelinda Oro","raw_affiliation_strings":["Italian National Research Council, Rende, Italy","Italian National Research Council, Rende, Italy#TAB#"],"affiliations":[{"raw_affiliation_string":"Italian National Research Council, Rende, Italy","institution_ids":["https://openalex.org/I4210142749","https://openalex.org/I4210155236"]},{"raw_affiliation_string":"Italian National Research Council, Rende, Italy#TAB#","institution_ids":["https://openalex.org/I197604219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008165294","display_name":"Giorgio Orsi","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giorgio Orsi","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039522364"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":1.6662,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.86052564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9961000084877014,"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":0.9940000176429749,"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":0.8786106109619141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8121274709701538},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6615663766860962},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6137600541114807},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4683149755001068},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44292357563972473},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.43032270669937134},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3646989166736603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3531303405761719},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06363308429718018}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8786106109619141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121274709701538},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6615663766860962},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6137600541114807},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4683149755001068},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44292357563972473},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.43032270669937134},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3646989166736603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3531303405761719},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06363308429718018},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2361354.2361365","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:7469462e-1e56-4490-a976-515ec0372698","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:7469462e-1e56-4490-a976-515ec0372698","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1555624686","https://openalex.org/W1569639771","https://openalex.org/W1965251585","https://openalex.org/W1971336721","https://openalex.org/W2001783238","https://openalex.org/W2044515729","https://openalex.org/W2051265407","https://openalex.org/W2103158282","https://openalex.org/W2111297753","https://openalex.org/W2137998699","https://openalex.org/W2143633261","https://openalex.org/W2153962014","https://openalex.org/W6675355980"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W4232484699","https://openalex.org/W2885323543","https://openalex.org/W2145649715"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,33,52,66],"methodology":[4,53],"for":[5,12,39,54],"the":[6],"evaluation":[7,16,45],"of":[8],"table":[9,23,25],"understanding":[10],"algorithms":[11],"PDF":[13,58],"documents.":[14],"The":[15],"takes":[17],"into":[18],"account":[19],"three":[20],"major":[21],"tasks:":[22],"detection,":[24],"structure":[26],"recognition":[27],"and":[28,35,47,56,64],"functional":[29],"analysis.":[30],"We":[31,49],"provide":[32,65],"general":[34],"flexible":[36],"output":[37],"model":[38],"each":[40],"task":[41],"along":[42],"with":[43],"corresponding":[44],"metrics":[46],"methods.":[48],"also":[50],"present":[51],"collecting":[55],"ground-truthing":[57],"documents":[59],"based":[60],"on":[61],"consensus-reaching":[62],"principles":[63],"publicly":[67],"available":[68],"ground-truthed":[69],"dataset.":[70]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
