{"id":"https://openalex.org/W2515936484","doi":"https://doi.org/10.1145/2960811.2960814","title":"Embedded Textual Content for Document Image Classification with Convolutional Neural Networks","display_name":"Embedded Textual Content for Document Image Classification with Convolutional Neural Networks","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2515936484","doi":"https://doi.org/10.1145/2960811.2960814","mag":"2515936484"},"language":"en","primary_location":{"id":"doi:10.1145/2960811.2960814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2960814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 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/A5108581053","display_name":"Lucia Noce","orcid":null},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Lucia Noce","raw_affiliation_strings":["University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054778549","display_name":"Ignazio Gallo","orcid":"https://orcid.org/0000-0002-7076-8328"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ignazio Gallo","raw_affiliation_strings":["University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081791308","display_name":"Alessandro Zamberletti","orcid":null},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Zamberletti","raw_affiliation_strings":["University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087859719","display_name":"Alessandro Calefati","orcid":"https://orcid.org/0000-0003-3860-4785"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Calefati","raw_affiliation_strings":["University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108581053"],"corresponding_institution_ids":["https://openalex.org/I115752224"],"apc_list":null,"apc_paid":null,"fwci":1.6894,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.89510697,"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":"165","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9919000267982483,"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":0.9775000214576721,"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/computer-science","display_name":"Computer science","score":0.8523660898208618},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8186385631561279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7097756266593933},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6794057488441467},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.6126887798309326},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5544023513793945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5463292598724365},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5269442796707153},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5201994776725769},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.45524024963378906},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4342890977859497},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.401854008436203},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.371651828289032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36397290229797363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523660898208618},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8186385631561279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7097756266593933},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6794057488441467},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.6126887798309326},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5544023513793945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5463292598724365},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5269442796707153},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5201994776725769},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.45524024963378906},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4342890977859497},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.401854008436203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.371651828289032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36397290229797363},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2960811.2960814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2960814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:irinsubria.uninsubria.it:11383/2063104","is_oa":false,"landing_page_url":"http://hdl.handle.net/11383/2063104","pdf_url":null,"source":{"id":"https://openalex.org/S4377196351","display_name":"IrInSubria (University of Insubria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115752224","host_organization_name":"University of Insubria","host_organization_lineage":["https://openalex.org/I115752224"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W205301110","https://openalex.org/W1504337617","https://openalex.org/W1775434803","https://openalex.org/W1832693441","https://openalex.org/W1934184906","https://openalex.org/W1960182310","https://openalex.org/W1966382373","https://openalex.org/W1982746261","https://openalex.org/W2000376009","https://openalex.org/W2001642682","https://openalex.org/W2004665841","https://openalex.org/W2011929429","https://openalex.org/W2028571532","https://openalex.org/W2031408949","https://openalex.org/W2044030350","https://openalex.org/W2079017068","https://openalex.org/W2097624458","https://openalex.org/W2098345386","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2119755031","https://openalex.org/W2120615054","https://openalex.org/W2126406293","https://openalex.org/W2132368650","https://openalex.org/W2149933564","https://openalex.org/W2155893237","https://openalex.org/W2191616647","https://openalex.org/W2252215182","https://openalex.org/W2597851033","https://openalex.org/W2618530766","https://openalex.org/W2962772269","https://openalex.org/W2963921497","https://openalex.org/W4244764782","https://openalex.org/W4245031736"],"related_works":["https://openalex.org/W3204576215","https://openalex.org/W4295934125","https://openalex.org/W3160316822","https://openalex.org/W1581784047","https://openalex.org/W4283017656","https://openalex.org/W2904147048","https://openalex.org/W2774927939","https://openalex.org/W2573990671","https://openalex.org/W2131730163","https://openalex.org/W1556724143"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,66],"introduce":[4],"a":[5,51,103,117,135],"novel":[6],"document":[7,34,61,84,95,113,125,142],"image":[8,35,96],"classification":[9,36,100,114],"method":[10],"based":[11],"on":[12,140],"combined":[13],"visual":[14,152],"and":[15,71,78],"textual":[16,56,87],"information.":[17],"The":[18,41],"proposed":[19],"algorithm's":[20],"pipeline":[21],"is":[22,47,89,127],"inspired":[23],"to":[24,76,97],"the":[25,48,59,99,111,131],"ones":[26],"of":[27,44,50,102,116,148],"other":[28],"recent":[29],"state-of-the-art":[30],"methods":[31],"which":[32],"perform":[33],"using":[37,122],"Convolutional":[38,104,118],"Neural":[39,105,119],"Networks.":[40],"main":[42],"addition":[43],"our":[45],"work":[46],"introduction":[49],"preprocessing":[52],"step":[53],"embedding":[54],"additional":[55],"information":[57,88],"into":[58],"processed":[60],"images.":[62,85],"To":[63],"do":[64],"so":[65],"combine":[67],"Optical":[68],"Character":[69],"Recognition":[70],"Natural":[72],"Language":[73],"Processing":[74],"algorithms":[75],"extract":[77],"manipulate":[79],"relevant":[80],"text":[81],"concepts":[82],"from":[83],"Such":[86],"then":[90],"visually":[91],"embedded":[92],"within":[93],"each":[94],"improve":[98],"results":[101],"Network.":[106],"Our":[107],"experiments":[108],"prove":[109],"that":[110],"overall":[112],"accuracy":[115],"Network":[120],"trained":[121,138],"these":[123],"text-augmented":[124],"images":[126],"considerably":[128],"higher":[129],"than":[130],"one":[132],"achieved":[133],"by":[134],"similar":[136,151],"model":[137],"solely":[139],"classic":[141],"images,":[143],"especially":[144],"when":[145],"different":[146],"classes":[147],"documents":[149],"share":[150],"characteristics.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}