{"id":"https://openalex.org/W3090872036","doi":null,"title":"Component Analysis for Visual Question Answering Architectures","display_name":"Component Analysis for Visual Question Answering Architectures","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3090872036","mag":"3090872036"},"language":"en","primary_location":{"id":"pmh:oai:repositorio.pucrs.br:10923/20334","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10923/20334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196369","display_name":"PUCRS Repository (Pontifical Catholic University of Rio Grande do Sul)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45643870","host_organization_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","host_organization_lineage":["https://openalex.org/I45643870"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10923/20334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Camila Kolling dos Reis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Camila Kolling dos Reis","raw_affiliation_strings":["Machine Intelligence and Robotics Research Group, Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul, Porto Alegre, RS, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence and Robotics Research Group, Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul, Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I45643870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018120863","display_name":"J\u00f4natas Wehrmann","orcid":"https://orcid.org/0000-0001-9930-0908","observed_orcids":["https://orcid.org/0000-0001-9930-0908"]},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"J\u00f4natas Wehrmann","raw_affiliation_strings":["Machine Intelligence and Robotics Research Group, Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul, Porto Alegre, RS, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence and Robotics Research Group, Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul, Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I45643870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039629929","display_name":"Rodrigo Coelho Barros","orcid":"https://orcid.org/0000-0002-0782-9482","observed_orcids":["https://orcid.org/0000-0002-0782-9482"]},"institutions":[{"id":"https://openalex.org/I45643870","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","ror":"https://ror.org/025vmq686","country_code":"BR","type":"education","lineage":["https://openalex.org/I45643870"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo Coelho Barros","raw_affiliation_strings":["Machine Intelligence and Robotics Research Group, Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul, Porto Alegre, RS, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence and Robotics Research Group, Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul, Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I45643870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45643870"],"apc_list":null,"apc_paid":null,"fwci":0.084,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.32488048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.9879999756813049},{"id":"https://openalex.org/keywords/component-analysis","display_name":"component analysis","score":0.8690000176429749},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7630000114440918},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.8799999952316284},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.9570000171661377},{"id":"https://openalex.org/keywords/image-text-fusion","display_name":"image-text fusion","score":0.6510000228881836}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9208264350891113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288058042526245},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.7304844260215759},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6800149083137512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6268520951271057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5812278985977173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.552477240562439},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5314838886260986},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.529689371585846},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5186675786972046},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.49530425667762756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4264925718307495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33806753158569336},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11751800775527954},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09286090731620789},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:repositorio.pucrs.br:10923/20334","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10923/20334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196369","display_name":"PUCRS Repository (Pontifical Catholic University of Rio Grande do Sul)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45643870","host_organization_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","host_organization_lineage":["https://openalex.org/I45643870"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositorio.pucrs.br:10923/20334","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10923/20334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196369","display_name":"PUCRS Repository (Pontifical Catholic University of Rio Grande do Sul)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45643870","host_organization_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio Grande do Sul","host_organization_lineage":["https://openalex.org/I45643870"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895641373","https://openalex.org/W1895989618","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W2023615143","https://openalex.org/W2058556535","https://openalex.org/W2064675550","https://openalex.org/W2090048052","https://openalex.org/W2131774270","https://openalex.org/W2142192571","https://openalex.org/W2157331557","https://openalex.org/W2179022885","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2293453011","https://openalex.org/W2339712187","https://openalex.org/W2463565445","https://openalex.org/W2532034655","https://openalex.org/W2560730294","https://openalex.org/W2616125804","https://openalex.org/W2620683660","https://openalex.org/W2626778328","https://openalex.org/W2745132836","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2753474648","https://openalex.org/W2791148095","https://openalex.org/W2792643794","https://openalex.org/W2794902630","https://openalex.org/W2798782720","https://openalex.org/W2894842749","https://openalex.org/W2896457183","https://openalex.org/W2914484425","https://openalex.org/W2916723116","https://openalex.org/W2920151874","https://openalex.org/W2962808042","https://openalex.org/W2962964995","https://openalex.org/W2963066927","https://openalex.org/W2963341956","https://openalex.org/W2963383024","https://openalex.org/W2963656855","https://openalex.org/W2963668159","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2964121744","https://openalex.org/W2967344709","https://openalex.org/W2978390373","https://openalex.org/W2991118492","https://openalex.org/W2995753487","https://openalex.org/W2997525715","https://openalex.org/W4255949318"],"related_works":["https://openalex.org/W7081573595","https://openalex.org/W4415988745","https://openalex.org/W2971373693","https://openalex.org/W2964138343","https://openalex.org/W4379742243","https://openalex.org/W3154330572","https://openalex.org/W7084149046","https://openalex.org/W4256401083","https://openalex.org/W3091170609","https://openalex.org/W3104271516"],"abstract_inverted_index":{"Recent":[0],"research":[1],"advances":[2],"in":[3,120,164,186],"Computer":[4],"Vision":[5],"and":[6,38,47,94,112,175,190],"Natural":[7],"Language":[8],"Processing":[9],"have":[10],"introduced":[11],"novel":[12],"tasks":[13,26],"that":[14,73],"are":[15],"paving":[16],"the":[17,45,54,64,77,100,114,117,133,140,144,159,181],"way":[18],"for":[19,139,201],"solving":[20],"AI-complete":[21],"problems.":[22],"One":[23],"of":[24,71,82,92,116,136,143,149,161,170,183,188],"those":[25],"is":[27,152,196],"called":[28],"Visual":[29],"Question":[30],"Answering":[31],"(VQA).":[32],"This":[33],"system":[34],"takes":[35],"an":[36],"image":[37],"a":[39,49,57,69,155],"free-form,":[40],"open-ended":[41],"natural-language":[42],"question":[43],"about":[44],"image,":[46],"produce":[48],"natural":[50,121],"language":[51],"answer":[52,109,119],"as":[53,178,180,206],"output.":[55],"Such":[56],"task":[58],"has":[59],"drawn":[60],"great":[61],"attention":[62,191],"from":[63,105],"scientific":[65],"community,":[66],"which":[67],"generated":[68],"plethora":[70],"approaches":[72,126],"aim":[74],"to":[75,108,153,197,207],"improve":[76],"VQA":[78,165,203],"predictive":[79,210],"accuracy.":[80],"Most":[81],"them":[83],"comprise":[84],"three":[85],"major":[86,194],"components:":[87],"(i)":[88],"independent":[89],"representation":[90],"learning":[91],"images":[93],"questions;":[95,111],"(ii)":[96],"feature":[97],"fusion":[98,189],"so":[99,124,205],"model":[101],"can":[102],"use":[103],"information":[104],"both":[106,173],"sources":[107],"visual":[110,174],"(iii)":[113],"generation":[115],"correct":[118],"language.":[122],"With":[123],"many":[125],"being":[127],"recently":[128],"introduced,":[129],"it":[130],"became":[131],"unclear":[132],"real":[134],"contribution":[135,195],"each":[137,162],"component":[138,163],"ultimate":[141],"performance":[142],"model.":[145],"The":[146],"main":[147],"goal":[148],"this":[150],"paper":[151],"provide":[154],"comprehensive":[156],"analysis":[157],"regarding":[158],"impact":[160],"models.":[166],"Our":[167,193],"extensive":[168],"set":[169],"experiments":[171],"cover":[172],"textual":[176],"elements,":[177],"well":[179],"combination":[182],"these":[184],"representations":[185],"form":[187],"mechanisms.":[192],"identify":[198],"core":[199],"components":[200],"training":[202],"models":[204],"maximize":[208],"their":[209],"performance.":[211]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2020-10-08T00:00:00"}