{"id":"https://openalex.org/W4385237494","doi":"https://doi.org/10.1016/j.patcog.2023.109834","title":"Hierarchical multimodal transformers for Multipage DocVQA","display_name":"Hierarchical multimodal transformers for Multipage DocVQA","publication_year":2023,"publication_date":"2023-07-25","ids":{"openalex":"https://openalex.org/W4385237494","doi":"https://doi.org/10.1016/j.patcog.2023.109834"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2023.109834","doi":"https://doi.org/10.1016/j.patcog.2023.109834","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2023.109834","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"volume":null,"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/A5066314166","display_name":"Rub\u00e8n Tito","orcid":"https://orcid.org/0000-0002-5657-9790","observed_orcids":["https://orcid.org/0000-0002-5657-9790"]},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":"ES","type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Rub\u00e8n Tito","raw_affiliation_strings":["Computer Vision Center, Universitat Autonoma de Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5657-9790","affiliations":[{"raw_affiliation_string":"Computer Vision Center, Universitat Autonoma de Barcelona, Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029375723","display_name":"D\u00ecmosthenis Karatzas","orcid":"https://orcid.org/0000-0001-8762-4454","observed_orcids":["https://orcid.org/0000-0001-8762-4454"]},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":"ES","type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dimosthenis Karatzas","raw_affiliation_strings":["Computer Vision Center, Universitat Autonoma de Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8762-4454","affiliations":[{"raw_affiliation_string":"Computer Vision Center, Universitat Autonoma de Barcelona, Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003047329","display_name":"Ernest Valveny","orcid":"https://orcid.org/0000-0002-0368-9697","observed_orcids":["https://orcid.org/0000-0002-0368-9697"]},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":"ES","type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ernest Valveny","raw_affiliation_strings":["Computer Vision Center, Universitat Autonoma de Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Universitat Autonoma de Barcelona, Spain","institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066314166"],"corresponding_institution_ids":["https://openalex.org/I123044942","https://openalex.org/I4387153096"],"apc_list":{"value":2850,"currency":"USD","value_usd":2850},"apc_paid":null,"fwci":5.6866,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.97570041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"144","issue":null,"first_page":"109834","last_page":"109834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.7954000234603882,"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":0.7954000234603882,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20239999890327454,"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/T10028","display_name":"Topic Modeling","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/document-visual-question-answering","display_name":"document visual question answering","score":0.7409999966621399},{"id":"https://openalex.org/keywords/hierarchical-transformer","display_name":"hierarchical transformer","score":0.7590000033378601},{"id":"https://openalex.org/keywords/multimodal-transformer","display_name":"multimodal transformer","score":0.890999972820282},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.6370000243186951},{"id":"https://openalex.org/keywords/long-document-processing","display_name":"long document processing","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303534984588623},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6437274217605591},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6252298355102539},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5576728582382202},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48351314663887024},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48112908005714417},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.444240540266037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4227522611618042},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40869271755218506},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09004351496696472},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2023.109834","doi":"https://doi.org/10.1016/j.patcog.2023.109834","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2023.109834","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W2947555604","https://openalex.org/W2965373594","https://openalex.org/W2981852735","https://openalex.org/W2997154779","https://openalex.org/W3015468748","https://openalex.org/W3031771644","https://openalex.org/W3035644209","https://openalex.org/W3044175177","https://openalex.org/W3045733172","https://openalex.org/W3077892130","https://openalex.org/W3086275027","https://openalex.org/W3104953317","https://openalex.org/W3120043490","https://openalex.org/W3132244696","https://openalex.org/W3158655572","https://openalex.org/W3173585224","https://openalex.org/W3176851559","https://openalex.org/W4213213306","https://openalex.org/W4285308960","https://openalex.org/W4297678984","https://openalex.org/W4304013646","https://openalex.org/W4304014014","https://openalex.org/W4312233877","https://openalex.org/W4312263373","https://openalex.org/W4320481960","https://openalex.org/W4320482280","https://openalex.org/W6800547270"],"related_works":["https://openalex.org/W4402716395","https://openalex.org/W4402395789","https://openalex.org/W4415707982","https://openalex.org/W4415537808","https://openalex.org/W4403791048","https://openalex.org/W4416035591","https://openalex.org/W4402423807","https://openalex.org/W4404404855","https://openalex.org/W4401879822","https://openalex.org/W7154570375"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-07-26T00:00:00"}
