{"id":"https://openalex.org/W4391884292","doi":"https://doi.org/10.3390/make6010023","title":"VisFormers\u2014Combining Vision and Transformers for Enhanced Complex Document Classification","display_name":"VisFormers\u2014Combining Vision and Transformers for Enhanced Complex Document Classification","publication_year":2024,"publication_date":"2024-02-16","ids":{"openalex":"https://openalex.org/W4391884292","doi":"https://doi.org/10.3390/make6010023"},"language":"en","primary_location":{"id":"doi:10.3390/make6010023","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6010023","pdf_url":"https://www.mdpi.com/2504-4990/6/1/23/pdf?version=1708087186","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/6/1/23/pdf?version=1708087186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002987222","display_name":"Subhayu Dutta","orcid":"https://orcid.org/0009-0003-0674-2785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhayu Dutta","raw_affiliation_strings":["Department of Computer Science & Engineering, Dr. B.C. Roy Engineering College, Durgapur 713206, West Bengal, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Dr. B.C. Roy Engineering College, Durgapur 713206, West Bengal, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083276631","display_name":"Subhrangshu Adhikary","orcid":"https://orcid.org/0000-0003-1779-3070"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Subhrangshu Adhikary","raw_affiliation_strings":["Department of Research & Development, Spiraldevs Automation Industries Pvt. Ltd., Raiganj 733123, West Bengal, India"],"affiliations":[{"raw_affiliation_string":"Department of Research & Development, Spiraldevs Automation Industries Pvt. Ltd., Raiganj 733123, West Bengal, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022807772","display_name":"Ashutosh Dhar Dwivedi","orcid":"https://orcid.org/0000-0001-8010-6275"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ashutosh Dhar Dwivedi","raw_affiliation_strings":["Cyber Security Group, Aalborg University, DK-2000 Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Cyber Security Group, Aalborg University, DK-2000 Copenhagen, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083276631"],"corresponding_institution_ids":[],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.5179,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89973831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"1","first_page":"448","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9751999974250793,"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":0.9736999869346619,"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":0.7871798276901245},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7581115961074829},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6775504946708679},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.6608515381813049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5736464262008667},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5483959913253784},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.45064789056777954},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.444827139377594},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4127906560897827},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39102140069007874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16049718856811523},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13196781277656555},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0804157555103302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871798276901245},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7581115961074829},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6775504946708679},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.6608515381813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5736464262008667},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5483959913253784},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.45064789056777954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.444827139377594},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4127906560897827},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39102140069007874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16049718856811523},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13196781277656555},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0804157555103302},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/make6010023","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6010023","pdf_url":"https://www.mdpi.com/2504-4990/6/1/23/pdf?version=1708087186","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/0d8bbb51-5be9-4db3-a381-3e76ff64c165","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/0d8bbb51-5be9-4db3-a381-3e76ff64c165","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dutta, S, Adhikary, S & Dwivedi, A D 2024, 'VisFormers\u2014Combining Vision and Transformers for Enhanced Complex Document Classification', Machine Learning and Knowledge Extraction, vol. 6, no. 1, pp. 448-463. https://doi.org/10.3390/make6010023","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:3190703a95fa4ab795b891a8055d9550","is_oa":true,"landing_page_url":"https://doaj.org/article/3190703a95fa4ab795b891a8055d9550","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 6, Iss 1, Pp 448-463 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make6010023","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6010023","pdf_url":"https://www.mdpi.com/2504-4990/6/1/23/pdf?version=1708087186","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391884292.pdf"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W2897098357","https://openalex.org/W2952230191","https://openalex.org/W2953662108","https://openalex.org/W2955109214","https://openalex.org/W2962772269","https://openalex.org/W2962933419","https://openalex.org/W2964036463","https://openalex.org/W2997956517","https://openalex.org/W3008736151","https://openalex.org/W3013022628","https://openalex.org/W3021667312","https://openalex.org/W3034556548","https://openalex.org/W3041133507","https://openalex.org/W3120013103","https://openalex.org/W3135857201","https://openalex.org/W3155418184","https://openalex.org/W3175901146","https://openalex.org/W3196808215","https://openalex.org/W3202255656","https://openalex.org/W3210517762","https://openalex.org/W3216197972","https://openalex.org/W4200211261","https://openalex.org/W4205377807","https://openalex.org/W4205471199","https://openalex.org/W4211234505","https://openalex.org/W4225983561","https://openalex.org/W4287118527","https://openalex.org/W4293493277","https://openalex.org/W4295296320","https://openalex.org/W4296771024","https://openalex.org/W4306704716","https://openalex.org/W4309221560","https://openalex.org/W4311459452","https://openalex.org/W4313558932","https://openalex.org/W4320482280","https://openalex.org/W4320918637","https://openalex.org/W4323663595","https://openalex.org/W4366376357","https://openalex.org/W4382935536","https://openalex.org/W4385990946","https://openalex.org/W4386065837","https://openalex.org/W4388516975","https://openalex.org/W4388646466","https://openalex.org/W4389401563","https://openalex.org/W4390643562","https://openalex.org/W4391183066","https://openalex.org/W6797227296","https://openalex.org/W6803587658","https://openalex.org/W6842399359","https://openalex.org/W6846131055"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W2592115649","https://openalex.org/W4322582183","https://openalex.org/W1937392525","https://openalex.org/W2347632764"],"abstract_inverted_index":{"Complex":[0,164],"documents":[1,19,41,48,95,187,224],"have":[2,49,69,89],"text,":[3],"figures,":[4],"tables,":[5],"and":[6,24,55,62,99,136,149,201],"other":[7],"elements.":[8],"The":[9,180,213],"classification":[10,92],"of":[11,14,17,52,75,86,93,154,159,222],"scanned":[12,39,220],"copies":[13,221],"different":[15,147,171,226],"categories":[16],"complex":[18,40,80,94],"like":[20],"memos,":[21],"newspapers,":[22],"letters,":[23,56],"more":[25,106],"is":[26,34,45],"essential":[27],"for":[28,59,143,146],"rapid":[29],"digitization.":[30],"However,":[31],"this":[32,111],"task":[33],"very":[35,63],"challenging":[36],"as":[37],"most":[38],"look":[42],"similar.":[43],"This":[44],"because":[46],"all":[47,60],"similar":[50,57,97],"colors":[51],"the":[53,73,76,91,102,124,140,155,160,178,186,219],"page":[54],"textures":[58],"papers,":[61],"few":[64,85],"contrasting":[65],"features.":[66],"Several":[67],"attempts":[68],"been":[70],"made":[71],"in":[72,151],"state":[74],"art":[77],"to":[78,116,122,131,176,190,210],"classify":[79],"documents;":[81],"however,":[82],"only":[83,208],"a":[84,114,128,194],"these":[87],"works":[88],"addressed":[90],"with":[96,188],"features,":[98],"among":[100],"these,":[101],"performances":[103],"could":[104,206],"be":[105],"satisfactory.":[107],"To":[108],"overcome":[109],"this,":[110],"paper":[112],"presents":[113],"method":[115],"use":[117],"an":[118],"optical":[119],"character":[120],"reader":[121],"extract":[123],"texts.":[125],"It":[126],"proposes":[127],"multi-headed":[129,182],"model":[130,214],"combine":[132],"vision-based":[133,202],"transfer":[134,204],"learning":[135,205],"natural-language-based":[137],"Transformers":[138],"within":[139],"same":[141],"network":[142,184,198],"simultaneous":[144],"training":[145],"inputs":[148],"optimizers":[150],"specific":[152],"parts":[153],"network.":[156],"A":[157],"subset":[158],"Ryers":[161],"Vision":[162],"Lab":[163],"Document":[165],"Information":[166],"Processing":[167],"dataset":[168],"containing":[169],"16":[170],"document":[172],"classes":[173],"was":[174],"used":[175],"evaluate":[177],"performances.":[179],"proposed":[181],"VisFormers":[183],"classified":[185],"up":[189,209],"94.2%":[191],"accuracy,":[192],"while":[193],"regular":[195],"natural-language-processing-based":[196],"Transformer":[197],"achieved":[199],"83%,":[200],"VGG19":[203],"achieve":[207],"90%":[211],"accuracy.":[212],"deployment":[215],"can":[216],"help":[217],"sort":[218],"various":[223],"into":[225],"categories.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2024-02-17T00:00:00"}