{"id":"https://openalex.org/W3162164804","doi":"https://doi.org/10.1109/icpr48806.2021.9412885","title":"Improving Visual Question Answering using Active Perception on Static Images","display_name":"Improving Visual Question Answering using Active Perception on Static Images","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3162164804","doi":"https://doi.org/10.1109/icpr48806.2021.9412885","mag":"3162164804"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412885","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03265181","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028775080","display_name":"Theodoros Bozinis","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodoros Bozinis","raw_affiliation_strings":["Faculty of Sciences, Aristotle University of Thessaloniki, Thessaloniki, Greece","Department of Informatics, Aristotle University of Thessaloniki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061050264","display_name":"Nikolaos Passalis","orcid":"https://orcid.org/0000-0003-1177-9139"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Passalis","raw_affiliation_strings":["Faculty of Sciences, Aristotle University of Thessaloniki, Thessaloniki, Greece","Department of Informatics, Aristotle University of Thessaloniki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041054091","display_name":"Anastasios Tefas","orcid":"https://orcid.org/0000-0003-1288-3667"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Anastasios Tefas","raw_affiliation_strings":["Faculty of Sciences, Aristotle University of Thessaloniki, Thessaloniki, Greece","Department of Informatics, Aristotle University of Thessaloniki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"521","issue":null,"first_page":"879","last_page":"884"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9973999857902527,"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":0.8554519414901733},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7687711715698242},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.6777527332305908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6450515389442444},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5879389047622681},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5043290853500366},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49715545773506165},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46196502447128296},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4546946585178375},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42604219913482666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554519414901733},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7687711715698242},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.6777527332305908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450515389442444},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5879389047622681},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5043290853500366},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49715545773506165},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46196502447128296},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4546946585178375},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42604219913482666},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412885","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:HAL:hal-03265181v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03265181","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"2020 25th International Conference on Pattern Recognition (ICPR), Jan 2021, Milan(virtual), Italy. pp.879-884, ⟨10.1109/ICPR48806.2021.9412885⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03265181v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03265181","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"2020 25th International Conference on Pattern Recognition (ICPR), Jan 2021, Milan(virtual), Italy. pp.879-884, ⟨10.1109/ICPR48806.2021.9412885⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2296039540","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2607151106","https://openalex.org/W2761873684","https://openalex.org/W2799846024","https://openalex.org/W2893170104","https://openalex.org/W2896457183","https://openalex.org/W2913281951","https://openalex.org/W2919115771","https://openalex.org/W2962684798","https://openalex.org/W2963177403","https://openalex.org/W2963341956","https://openalex.org/W2963656855","https://openalex.org/W2963717374","https://openalex.org/W2963890019","https://openalex.org/W2964121744","https://openalex.org/W2964291307","https://openalex.org/W4248601629","https://openalex.org/W6639102338","https://openalex.org/W6719057275","https://openalex.org/W6744838376"],"related_works":["https://openalex.org/W2788595494","https://openalex.org/W2384605597","https://openalex.org/W2244676099","https://openalex.org/W3172556642","https://openalex.org/W3157456843","https://openalex.org/W1990150827","https://openalex.org/W2036676347","https://openalex.org/W2387743295","https://openalex.org/W1589307369","https://openalex.org/W3165790285"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,19,35,120,142],"one":[5],"of":[6,12,31,84,138],"the":[7,24,29,38,46,88,97,109,113,139],"most":[8,132],"challenging":[9,147],"emerging":[10],"applications":[11],"deep":[13],"learning.":[14],"Providing":[15],"powerful":[16],"attention":[17,124],"mechanisms":[18,125],"crucial":[20],"for":[21,103],"VQA,":[22],"since":[23],"model":[25],"must":[26],"correctly":[27],"identify":[28],"region":[30],"an":[32],"image":[33],"that":[34,78],"relevant":[36],"to":[37,58,94,122],"question":[39,98],"at":[40,49,99,111],"hand.":[41,100],"However,":[42],"existing":[43,123,133],"models":[44,114],"analyze":[45],"input":[47],"images":[48,89],"a":[50,72,82,146],"fixed":[51],"and":[52,126],"typically":[53],"small":[54],"resolution,":[55],"often":[56],"leading":[57],"discarding":[59],"valuable":[60],"fine-grained":[61,105],"details.":[62],"To":[63],"overcome":[64],"this":[65,68],"limitation,":[66],"in":[67,92],"work":[69],"we":[70],"propose":[71],"reinforcement":[73],"learning-based":[74],"active":[75],"perception":[76],"approach":[77],"works":[79],"by":[80],"applying":[81],"series":[83],"transformation":[85],"operations":[86],"on":[87,145],"(translation,":[90],"zoom)":[91],"order":[93],"facilitate":[95],"answering":[96],"This":[101],"allows":[102],"performing":[104],"analysis,":[106],"effectively":[107],"increasing":[108],"resolution":[110],"which":[112],"process":[115],"information.":[116],"The":[117,136],"proposed":[118,140],"method":[119,141],"orthogonal":[121],"it":[127],"can":[128],"be":[129],"combined":[130],"with":[131],"VQA":[134,148],"methods.":[135],"effectiveness":[137],"experimentally":[143],"demonstrated":[144],"dataset.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}