{"id":"https://openalex.org/W4416183403","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223349","title":"Towards Zero-Shot Document Image Classification","display_name":"Towards Zero-Shot Document Image Classification","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4416183403","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223349"},"language":null,"primary_location":{"id":"doi:10.1109/sibgrapi67909.2025.11223349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5119663353","display_name":"Lucas De Almeida Bandeira Macedo","orcid":"https://orcid.org/0009-0004-6952-4731"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Macedo","raw_affiliation_strings":["University of Brasília,Department of Computer Science,Brasília,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Brasília,Department of Computer Science,Brasília,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873615","display_name":"Jo\u00e3o Paulo Costa","orcid":"https://orcid.org/0000-0001-5204-3916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Paulo Costa","raw_affiliation_strings":["University of Brasília,Department of Computer Science,Brasília,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Brasília,Department of Computer Science,Brasília,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jo\u00e3o Pedro Felix De Almeida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Pedro Felix De Almeida","raw_affiliation_strings":["University of Brasília,Department of Computer Science,Brasília,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Brasília,Department of Computer Science,Brasília,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011069017","display_name":"Pedro Garcia Freitas","orcid":"https://orcid.org/0000-0003-0866-658X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Freitas","raw_affiliation_strings":["University of Brasília,Department of Computer Science,Brasília,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Brasília,Department of Computer Science,Brasília,Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101701977","display_name":"Weigang Li","orcid":"https://orcid.org/0000-0003-3268-127X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Weigang","raw_affiliation_strings":["University of Brasília,Department of Computer Science,Brasília,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Brasília,Department of Computer Science,Brasília,Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31696489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.33329999446868896,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.33329999446868896,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.30230000615119934,"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":0.06340000033378601,"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/variety","display_name":"Variety (cybernetics)","score":0.646399974822998},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5526000261306763},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4853000044822693},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4447999894618988},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41670000553131104},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814000248908997},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.646399974822998},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048999786376953},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47290000319480896},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4447999894618988},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4311999976634979},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40799999237060547},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3276999890804291},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2278759","wikidata":"https://www.wikidata.org/wiki/Q831677","display_name":"Document management system","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sibgrapi67909.2025.11223349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1994616650","https://openalex.org/W2016381774","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2942137712","https://openalex.org/W2962772269","https://openalex.org/W2963499153","https://openalex.org/W2982083293","https://openalex.org/W2986619406","https://openalex.org/W3003484198","https://openalex.org/W3034556548","https://openalex.org/W3120043490","https://openalex.org/W3174427107","https://openalex.org/W3185830723","https://openalex.org/W4290927927","https://openalex.org/W4385570363","https://openalex.org/W4386566652","https://openalex.org/W4390874575","https://openalex.org/W4402430817","https://openalex.org/W4403616351","https://openalex.org/W4404970691"],"related_works":[],"abstract_inverted_index":{"Classification":[0,144],"is":[1,44,119,240],"a":[2,66,108,171,188,197,206,221],"fundamental":[3],"tool":[4],"to":[5,183],"automate":[6],"the":[7,101,138,156,223,237],"process":[8],"of":[9,36,40,45,57,89,104,111,199,208,236],"categorizing":[10],"documents":[11,52,91,149,185],"in":[12,55],"many":[13,33],"real-world":[14],"applications,":[15,41],"such":[16,213],"as":[17,214],"information":[18],"management,":[19,25],"financial":[20],"document":[21,42,123,131],"processing,":[22],"healthcare":[23],"records":[24],"news":[26],"categorization,":[27],"fraud":[28],"detection,":[29],"regulatory":[30],"compliance,":[31],"and":[32,59,73,82,129,218],"others.":[34,219],"Because":[35],"this":[37,114,134,175,193],"broad":[38],"spectrum":[39],"classification":[43,68,124],"paramount":[46],"importance":[47,106],"for":[48,107,122,174],"various":[49],"companies.":[50],"However,":[51],"often":[53,75],"change":[54],"terms":[56],"format":[58],"their":[60],"visual":[61],"patterns,":[62],"which":[63],"may":[64],"impair":[65],"simple":[67],"model.":[69],"Moreover,":[70],"model":[71,157],"continuance":[72],"retraining":[74,100],"demands":[76],"important":[77],"efforts,":[78],"consuming":[79],"computational":[80],"resources":[81],"demanding":[83],"new":[84,95],"data.":[85],"Therefore,":[86],"techniques":[87],"capable":[88],"classifying":[90],"by":[92,155],"simply":[93],"observing":[94],"data,":[96],"without":[97],"necessarily":[98],"requiring":[99],"classifier,":[102],"are":[103],"immense":[105],"wide":[109],"variety":[110,207],"applications.":[112],"In":[113,133],"context,":[115],"Zero-Shot":[116,141],"Learning":[117],"(ZSL)":[118],"especially":[120],"suitable":[121],"because":[125],"it":[126],"handles":[127],"diverse":[128],"ever-changing":[130],"content.":[132],"work,":[135],"we":[136,147,163,195],"tackle":[137],"gap":[139],"involving":[140],"Document":[142,167],"Image":[143],"(ZS-DIC),":[145],"where":[146],"classify":[148,184],"that":[150],"have":[151],"not":[152],"been":[153],"seen":[154],"during":[158],"training.":[159],"To":[160,191],"achieve":[161],"this,":[162],"built":[164],"Layout-Aware":[165],"Complex":[166],"Information":[168],"Processing":[169],"(LA-CDIP),":[170],"dataset":[172],"tailored":[173],"problem.":[176],"LAC-DIP":[177],"prioritizes":[178],"structural":[179],"consistency,":[180],"allowing":[181],"models":[182],"correctly":[186],"under":[187,232],"ZSL":[189],"scenario.":[190],"benchmark":[192],"dataset,":[194],"developed":[196],"series":[198],"Siamese":[200],"Neural":[201],"Networks":[202],"(NNs)":[203],"based":[204],"on":[205],"computer":[209],"vision":[210],"neural":[211],"architectures,":[212],"ResNet,":[215],"EfficientNet,":[216],"ViT":[217],"As":[220],"result,":[222],"proposed":[224,238],"ZSL-based":[225],"method":[226,239],"achieves":[227],"Equal":[228],"Error":[229],"Rates":[230],"(EERs)":[231],"5%.":[233],"The":[234],"code":[235],"available":[241],"at":[242],"https://github.com/ABMHub/doc-zsl.":[243]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-11T00:00:00"}