{"id":"https://openalex.org/W3023893410","doi":"https://doi.org/10.1109/icpr48806.2021.9413269","title":"A Novel Attention-based Aggregation Function to Combine Vision and Language","display_name":"A Novel Attention-based Aggregation Function to Combine Vision and Language","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3023893410","doi":"https://doi.org/10.1109/icpr48806.2021.9413269","mag":"3023893410"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.13073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016738355","display_name":"Matteo Stefanini","orcid":"https://orcid.org/0000-0001-6153-926X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Matteo Stefanini","raw_affiliation_strings":["University of Modena and Reggio Emilia","Univ. of Modena and Reggio Emilia#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"Univ. of Modena and Reggio Emilia#TAB#","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066519737","display_name":"Marcella Cornia","orcid":"https://orcid.org/0000-0001-9640-9385"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcella Cornia","raw_affiliation_strings":["University of Modena and Reggio Emilia","Univ. of Modena and Reggio Emilia#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"Univ. of Modena and Reggio Emilia#TAB#","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928616","display_name":"Lorenzo Baraldi","orcid":"https://orcid.org/0000-0001-5125-4957"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Baraldi","raw_affiliation_strings":["University of Modena and Reggio Emilia","Univ. of Modena and Reggio Emilia#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"Univ. of Modena and Reggio Emilia#TAB#","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948871","display_name":"Rita Cucchiara","orcid":"https://orcid.org/0000-0002-2239-283X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rita Cucchiara","raw_affiliation_strings":["University of Modena and Reggio Emilia","Univ. of Modena and Reggio Emilia#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"Univ. of Modena and Reggio Emilia#TAB#","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016738355"],"corresponding_institution_ids":["https://openalex.org/I122346577"],"apc_list":null,"apc_paid":null,"fwci":0.30665844,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52561596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1212","last_page":"1219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.7473154664039612},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7299636602401733},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6700624227523804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6483643651008606},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6220555901527405},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.586225152015686},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5625665783882141},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5339068174362183},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5239596366882324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5221472382545471},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5200285911560059},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5036429762840271},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4613281786441803},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.45575493574142456},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44069114327430725},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41808032989501953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37825632095336914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1056567132472992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473154664039612},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7299636602401733},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6700624227523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6483643651008606},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6220555901527405},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.586225152015686},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5625665783882141},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5339068174362183},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5239596366882324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5221472382545471},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5200285911560059},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5036429762840271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4613281786441803},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.45575493574142456},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44069114327430725},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41808032989501953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37825632095336914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1056567132472992},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.13073","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.13073","pdf_url":"https://arxiv.org/pdf/2004.13073","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:iris.unimore.it:11380/1204118","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1204118","pdf_url":"http://hdl.handle.net/11380/1204118","source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3023893410","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2004.13073.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.13073","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.13073","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.13073","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.13073","pdf_url":"https://arxiv.org/pdf/2004.13073","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2097117768","https://openalex.org/W2151498684","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2549139847","https://openalex.org/W2560730294","https://openalex.org/W2565639579","https://openalex.org/W2745461083","https://openalex.org/W2903416914","https://openalex.org/W2916723116","https://openalex.org/W2954598292","https://openalex.org/W2962835968","https://openalex.org/W2962964995","https://openalex.org/W2963224792","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963467339","https://openalex.org/W2963499204","https://openalex.org/W2963521239","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964118342","https://openalex.org/W2964121744","https://openalex.org/W2964276596","https://openalex.org/W2965848243","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2970641574","https://openalex.org/W2988823324","https://openalex.org/W2989596775","https://openalex.org/W2995289474","https://openalex.org/W3002557610","https://openalex.org/W3004349648","https://openalex.org/W3034655362","https://openalex.org/W3088493063","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6682086655","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6746421592","https://openalex.org/W6747225742","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6766645339","https://openalex.org/W6771430711"],"related_works":["https://openalex.org/W3083505552","https://openalex.org/W2963532541","https://openalex.org/W3018278137","https://openalex.org/W3126337491","https://openalex.org/W3145544011","https://openalex.org/W3163761993","https://openalex.org/W3186187670","https://openalex.org/W3195654169","https://openalex.org/W2009788881","https://openalex.org/W3004349648","https://openalex.org/W3031771644","https://openalex.org/W3042804260","https://openalex.org/W3044471495","https://openalex.org/W2751608058","https://openalex.org/W3159630763","https://openalex.org/W3110123786","https://openalex.org/W3017098848","https://openalex.org/W3119595400","https://openalex.org/W3017081412","https://openalex.org/W3011819854"],"abstract_inverted_index":{"The":[0],"joint":[1],"understanding":[2],"of":[3,13,28,52,69,102,107,114,180,183],"vision":[4,93],"and":[5,20,36,43,57,94,116,120,130,139,153],"language":[6],"has":[7],"been":[8],"recently":[9],"gaining":[10],"a":[11,67,73,77,87,100,111,118,165],"lot":[12],"attention":[14],"in":[15],"both":[16,41,128,151,169],"the":[17,26,178,184],"Computer":[18],"Vision":[19],"Natural":[21],"Language":[22],"Processing":[23],"communities,":[24],"with":[25,146],"emergence":[27],"tasks":[29],"such":[30],"as":[31,48],"image":[32],"captioning,":[33],"image-text":[34,137],"matching,":[35],"visual":[37,140],"question":[38,141],"answering.":[39],"As":[40],"images":[42],"text":[44],"can":[45,124],"be":[46,125],"encoded":[47,70],"sets":[49],"or":[50,79],"sequences":[51],"elements":[53,71],"--":[54,59],"like":[55,76],"regions":[56],"words":[58],"proper":[60],"reduction":[61,90,148],"functions":[62],"are":[63],"needed":[64],"to":[65,164,176],"transform":[66],"set":[68,101],"into":[72],"single":[74],"response,":[75],"classification":[78,129],"similarity":[80],"score.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,158,172],"propose":[86],"novel":[88,112],"fully-attentive":[89],"method":[91],"for":[92,104,127],"language.":[95],"Specifically,":[96],"our":[97,134,161],"approach":[98,135,162],"computes":[99],"scores":[103],"each":[105,108,181],"element":[106],"modality":[109],"employing":[110],"variant":[113],"cross-attention,":[115],"performs":[117],"learnable":[119],"cross-modal":[121],"reduction,":[122],"which":[123],"used":[126],"ranking.":[131],"We":[132],"test":[133],"on":[136,150,168],"matching":[138],"answering,":[142],"building":[143],"fair":[144],"comparisons":[145],"other":[147],"choices,":[149],"COCO":[152],"VQA":[154],"2.0":[155],"datasets.":[156],"Experimentally,":[157],"demonstrate":[159],"that":[160],"leads":[163],"performance":[166],"increase":[167],"tasks.":[170],"Further,":[171],"conduct":[173],"ablation":[174],"studies":[175],"validate":[177],"role":[179],"component":[182],"approach.":[185]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}