{"id":"https://openalex.org/W4389352613","doi":"https://doi.org/10.1109/access.2023.3339537","title":"SBVQA 2.0: Robust End-to-End Speech-Based Visual Question Answering for Open-Ended Questions","display_name":"SBVQA 2.0: Robust End-to-End Speech-Based Visual Question Answering for Open-Ended Questions","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389352613","doi":"https://doi.org/10.1109/access.2023.3339537"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3339537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3339537","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2023.3339537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062834163","display_name":"Faris Alasmary","orcid":"https://orcid.org/0000-0002-5025-4020"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Faris Alasmary","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-5025-4020","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004401480","display_name":"Saad Al-Ahmadi","orcid":"https://orcid.org/0000-0001-9406-6809"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Saad Al-Ahmadi","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-9406-6809","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3368,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60136288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"140967","last_page":"140980"},"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":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.874220609664917},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6913563013076782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6032016277313232},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5818421840667725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5676234364509583},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5361371636390686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5040737390518188},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4696483016014099},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4245387315750122},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4227231740951538},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4073490500450134},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.375954806804657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.874220609664917},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6913563013076782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6032016277313232},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5818421840667725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676234364509583},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5361371636390686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5040737390518188},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4696483016014099},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4245387315750122},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4227231740951538},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4073490500450134},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.375954806804657},{"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/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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3339537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3339537","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a6f1fa32684a401da808b8fd9af3764c","is_oa":true,"landing_page_url":"https://doaj.org/article/a6f1fa32684a401da808b8fd9af3764c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 140967-140980 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3339537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3339537","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1933349210","https://openalex.org/W1987971958","https://openalex.org/W2036963181","https://openalex.org/W2038484192","https://openalex.org/W2058556535","https://openalex.org/W2148283386","https://openalex.org/W2160815625","https://openalex.org/W2560647685","https://openalex.org/W2560730294","https://openalex.org/W2611470828","https://openalex.org/W2745461083","https://openalex.org/W2748850194","https://openalex.org/W2889326414","https://openalex.org/W2962858109","https://openalex.org/W3035160371","https://openalex.org/W3096609285","https://openalex.org/W3097777922","https://openalex.org/W3172726328","https://openalex.org/W3187011621","https://openalex.org/W3209984917","https://openalex.org/W4312563428","https://openalex.org/W4313156423","https://openalex.org/W4321319299","https://openalex.org/W6737306744","https://openalex.org/W6788335241","https://openalex.org/W6791353385","https://openalex.org/W6800217721","https://openalex.org/W6804358500","https://openalex.org/W6810653034","https://openalex.org/W6811013733","https://openalex.org/W6811470611","https://openalex.org/W6849762702"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3179968364","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4288102755","https://openalex.org/W2103247590"],"abstract_inverted_index":{"Speech-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(SBVQA)":[4],"is":[5,65,139,146],"a":[6,46,126],"challenging":[7],"task":[8,21],"that":[9,52,134,151],"aims":[10],"to":[11,116,142],"answer":[12,77,114],"spoken":[13,86],"questions":[14],"about":[15],"images.":[16,96],"The":[17,79,97],"challenges":[18],"of":[19,25,67,99],"this":[20],"involve":[22],"the":[23,27,32,36,57,60,89,100,106,113,118,180],"variability":[24],"speakers,":[26],"different":[28],"recording":[29],"environments,":[30],"and":[31,38,59,76,88,109,144,177],"various":[33],"objects":[34],"in":[35,160],"image":[37,72,90],"their":[39],"locations.":[40],"This":[41],"paper":[42],"presents":[43],"SBVQA":[44,63,121,152],"2.0,":[45],"robust":[47,141],"multimodal":[48],"neural":[49],"network":[50],"architecture":[51],"integrates":[53],"information":[54,84,94],"from":[55,85,95],"both":[56],"visual":[58,93],"speech":[61,70,80,137],"domains.":[62],"2.0":[64,122,153],"composed":[66],"four":[68],"modules:":[69],"encoder,":[71,73],"features":[74,107],"fusor,":[75],"generator.":[78],"encoder":[81,91,138],"extracts":[82,92],"semantic":[83],"questions,":[87],"outputs":[98],"two":[101],"modules":[102],"are":[103],"combined":[104],"using":[105],"fusor":[108],"then":[110],"processed":[111],"by":[112,158],"generator":[115],"predict":[117],"answer.":[119],"Although":[120],"was":[123],"trained":[124],"on":[125],"single-speaker":[127],"with":[128],"clean":[129],"background":[130],"dataset,":[131],"we":[132,149],"show":[133],"our":[135,172],"selected":[136],"more":[140],"noise":[143],"it":[145,165],"speaker-independent.":[147],"Moreover,":[148],"demonstrate":[150],"can":[154],"be":[155],"further":[156],"improved":[157],"finetuning":[159],"an":[161],"end-to-end":[162],"manner":[163],"since":[164],"uses":[166],"fully":[167],"differentiable":[168],"modules.":[169],"We":[170],"open-source":[171],"pretrained":[173],"models,":[174],"source":[175],"code,":[176],"data":[178],"for":[179],"research":[181],"community.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}