{"id":"https://openalex.org/W3033514332","doi":"https://doi.org/10.1109/tkde.2020.2998805","title":"Answer Again: Improving VQA with Cascaded-Answering Model","display_name":"Answer Again: Improving VQA with Cascaded-Answering Model","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3033514332","doi":"https://doi.org/10.1109/tkde.2020.2998805","mag":"3033514332"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.2998805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2998805","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","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/A5063303076","display_name":"Liang Peng","orcid":"https://orcid.org/0000-0002-0576-1429"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Peng","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China (UESTC), Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China (UESTC), Guangdong, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113750896","display_name":"Xiaopeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068950059","display_name":"Yanli Ji","orcid":"https://orcid.org/0000-0001-9122-6141"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Ji","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019035804","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0001-9794-3221"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Kitakyushu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Kitakyushu, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3129,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.89161667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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":0.9909999966621399,"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":0.9794999957084656,"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":0.9387049674987793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8003145456314087},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7091057300567627},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6500041484832764},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5892674922943115},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5141634941101074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508815586566925},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5024731159210205},{"id":"https://openalex.org/keywords/questions-and-answers","display_name":"Questions and answers","score":0.4541586637496948},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4397010803222656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3492491841316223},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12608188390731812}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9387049674987793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003145456314087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7091057300567627},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6500041484832764},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5892674922943115},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5141634941101074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508815586566925},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5024731159210205},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.4541586637496948},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4397010803222656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3492491841316223},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12608188390731812},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2020.2998805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2998805","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2127615881","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2442626797","https://openalex.org/W2546696630","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2597425697","https://openalex.org/W2608030593","https://openalex.org/W2732016772","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2755385356","https://openalex.org/W2765440071","https://openalex.org/W2766237723","https://openalex.org/W2767171539","https://openalex.org/W2790777763","https://openalex.org/W2803620531","https://openalex.org/W2807941860","https://openalex.org/W2884093133","https://openalex.org/W2884326683","https://openalex.org/W2885380450","https://openalex.org/W2887712318","https://openalex.org/W2887967003","https://openalex.org/W2894842749","https://openalex.org/W2896902935","https://openalex.org/W2916723116","https://openalex.org/W2926818924","https://openalex.org/W2962861647","https://openalex.org/W2962958773","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963560969","https://openalex.org/W2963644680","https://openalex.org/W2963717374","https://openalex.org/W2963770662","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2964199361","https://openalex.org/W2964303913","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2979382951","https://openalex.org/W2981578638","https://openalex.org/W2982461533","https://openalex.org/W2988326850","https://openalex.org/W6634232107","https://openalex.org/W6637373629","https://openalex.org/W6717487601","https://openalex.org/W6728881024","https://openalex.org/W6729948091","https://openalex.org/W6736769356","https://openalex.org/W6743792510","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6753027577","https://openalex.org/W6754553780"],"related_works":["https://openalex.org/W2118632115","https://openalex.org/W2020521331","https://openalex.org/W101162712","https://openalex.org/W2555213299","https://openalex.org/W4256618828","https://openalex.org/W2786691313","https://openalex.org/W2576107865","https://openalex.org/W3215363805","https://openalex.org/W1846393350","https://openalex.org/W3154330131"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,100],"a":[5,48,66,81,131],"very":[6],"challenging":[7],"task,":[8,24],"which":[9,51,73],"requires":[10],"to":[11,80,159],"understand":[12],"visual":[13],"images":[14],"and":[15,33,112,147,175,190],"natural":[16],"language":[17],"questions":[18],"simultaneously.":[19],"In":[20,61,118],"the":[21,31,45,55,75,85,91,95,127,143,151,155,161,168,177],"open-ended":[22],"VQA":[23,78,133],"most":[25],"previous":[26],"solutions":[27],"focus":[28],"on":[29,180],"understanding":[30],"question":[32,146],"image":[34],"contents,":[35],"as":[36,38],"well":[37],"their":[39],"correlations.":[40],"However,":[41],"they":[42],"mostly":[43],"reason":[44],"answers":[46,57,129,158,174],"in":[47,53,94,138],"one-stage":[49,77],"way,":[50],"results":[52,165],"that":[54,167],"generated":[56,128],"are":[58],"significantly":[59],"ignored.":[60],"this":[62],"paper,":[63],"we":[64,121,141],"propose":[65],"novel":[67],"approach,":[68],"termed":[69],"Cascaded-Answering":[70],"Model":[71],"(CAM),":[72],"extends":[74],"conventional":[76],"model":[79,87,170],"two-stage":[82],"model.":[83],"Hence,":[84],"proposed":[86,169],"can":[88],"fully":[89],"explore":[90],"semantics":[92,152],"embedded":[93],"predicted":[96],"answers.":[97],"Specifically,":[98],"CAM":[99],"composed":[101],"of":[102,145],"two":[103],"cascaded":[104],"answering":[105],"modules:":[106],"Candidate":[107],"Answer":[108,114],"Generation":[109],"(CAG)":[110],"module":[111],"Final":[113],"Prediction":[115],"(FAP)":[116],"module.":[117],"CAG":[119],"module,":[120,140],"select":[122],"multiple":[123],"relevant":[124],"candidates":[125],"from":[126,154],"using":[130],"typical":[132],"approach":[134],"with":[135,150],"Co-Attention.":[136],"While":[137],"FAP":[139],"integrate":[142],"information":[144],"image,":[148],"together":[149],"explored":[153],"selected":[156],"candidate":[157,173],"predict":[160],"final":[162],"answer.":[163],"Experimental":[164],"demonstrate":[166],"produces":[171],"high-quality":[172],"achieves":[176],"state-of-the-art":[178],"performance":[179],"five":[181],"large":[182],"benchmark":[183],"datasets,":[184],"VQA-1.0,":[185],"VQA-2.0,":[186],"VQA-CP":[187],"v2,":[188],"TDIUC":[189],"COCO-QA.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}