{"id":"https://openalex.org/W4382119268","doi":"https://doi.org/10.1109/tmm.2023.3289729","title":"Resolving Zero-Shot and Fact-Based Visual Question Answering via Enhanced Fact Retrieval","display_name":"Resolving Zero-Shot and Fact-Based Visual Question Answering via Enhanced Fact Retrieval","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382119268","doi":"https://doi.org/10.1109/tmm.2023.3289729"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3289729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3289729","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"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/A5033975637","display_name":"Sen Wu","orcid":"https://orcid.org/0000-0002-6133-4122"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sen Wu","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079805574","display_name":"Guoshuai Zhao","orcid":"https://orcid.org/0000-0003-4392-8450"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoshuai Zhao","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014825654","display_name":"Xueming Qian","orcid":"https://orcid.org/0000-0002-3173-6307"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueming Qian","raw_affiliation_strings":["Ministry of Education Key Laboratory for Intelligent Networks and Network Security, School of Information and Communication Engineering, and SMILES LAB, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory for Intelligent Networks and Network Security, School of Information and Communication Engineering, and SMILES LAB, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033975637"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":1.1948,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80994205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"1790","last_page":"1800"},"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":0.995199978351593,"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":0.9835000038146973,"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/question-answering","display_name":"Question answering","score":0.8688079118728638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8616868257522583},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5388374924659729},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5296813249588013},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5244172811508179},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5172556042671204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46323060989379883},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3543342351913452}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8688079118728638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8616868257522583},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5388374924659729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5296813249588013},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5244172811508179},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5172556042671204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46323060989379883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3543342351913452},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3289729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3289729","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1070860207","display_name":null,"funder_award_id":"xxj022019003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1856004670","display_name":null,"funder_award_id":"61902309","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3353997047","display_name":null,"funder_award_id":"2020M683496","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7875560161","display_name":null,"funder_award_id":"xzd012022006","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2142192571","https://openalex.org/W2555661914","https://openalex.org/W2745461083","https://openalex.org/W2798895485","https://openalex.org/W2891394954","https://openalex.org/W2947312908","https://openalex.org/W2962749469","https://openalex.org/W2963150162","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963672682","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964303913","https://openalex.org/W2966005000","https://openalex.org/W2966317026","https://openalex.org/W2970231061","https://openalex.org/W3026441479","https://openalex.org/W3034726550","https://openalex.org/W3035454069","https://openalex.org/W3087975588","https://openalex.org/W3094071022","https://openalex.org/W3101703188","https://openalex.org/W3120213044","https://openalex.org/W3173178959","https://openalex.org/W3176634423","https://openalex.org/W3182020042","https://openalex.org/W3189827190","https://openalex.org/W3202473058","https://openalex.org/W3205632231","https://openalex.org/W3207886649","https://openalex.org/W3212436340","https://openalex.org/W4210518188","https://openalex.org/W4225942313","https://openalex.org/W4280652284","https://openalex.org/W4304091902","https://openalex.org/W6679844565","https://openalex.org/W6686883664","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6730088351","https://openalex.org/W6752083267","https://openalex.org/W6754375721","https://openalex.org/W6755207826","https://openalex.org/W6798323063","https://openalex.org/W6804218447"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W3159661535"],"abstract_inverted_index":{"Practical":[0],"applications":[1,26],"with":[2,103,168],"visual":[3],"question":[4],"answering":[5],"(VQA)":[6],"systems":[7],"are":[8,48],"challenging,":[9],"and":[10,39,60,98,140,160,164],"recent":[11],"research":[12],"has":[13],"aimed":[14],"at":[15],"investigating":[16],"this":[17],"important":[18],"field.":[19],"Many":[20],"issues":[21],"related":[22],"to":[23,43,93,133],"real-world":[24],"VQA":[25,85,162],"must":[27,74],"be":[28,75],"considered.":[29],"Although":[30],"existing":[31],"methods":[32],"have":[33],"focused":[34],"on":[35,57],"adding":[36],"external":[37,105],"knowledge":[38,106],"other":[40],"descriptive":[41],"information":[42,54,97,116,125,136],"assist":[44],"in":[45,117,137,143,158],"reasoning,":[46],"they":[47],"limited":[49],"by":[50],"the":[51,61,64,68,95,100,115,118,135,138,144,169],"impact":[52],"of":[53,63,71],"retrieval":[55],"errors":[56],"downstream":[58],"tasks":[59,163],"misalignment":[62],"aggregated":[65],"information.":[66],"Thus,":[67],"overall":[69],"performance":[70,157,167],"these":[72,79],"models":[73],"improved.":[76],"To":[77,113],"address":[78],"challenges,":[80],"we":[81,122],"propose":[82,123],"a":[83,89,109,130],"novel":[84],"model":[86,92],"that":[87,128,152],"utilizes":[88],"differentiated":[90],"pretrained":[91],"represent":[94],"input":[96,101],"connects":[99],"data":[102],"three":[104,119],"components":[107],"through":[108],"common":[110],"feature":[111,120],"space.":[112],"combine":[114],"spaces,":[121],"an":[124],"aggregation":[126],"strategy":[127],"employs":[129],"weighted":[131],"score":[132],"aggregate":[134],"relation":[139],"entity":[141],"spaces":[142],"answer":[145],"prediction":[146],"process.":[147],"The":[148],"experimental":[149],"results":[150],"show":[151],"our":[153],"method":[154],"achieves":[155,165],"good":[156],"fact-based":[159],"zero-shot":[161],"state-of-the-art":[166],"ZS-F-VQA":[170],"dataset.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}