{"id":"https://openalex.org/W4402208632","doi":"https://doi.org/10.1109/tbdata.2024.3453750","title":"Multi-Granularity Feature Interaction and Multi-Region Selection Based Triplet Visual Question Answering","display_name":"Multi-Granularity Feature Interaction and Multi-Region Selection Based Triplet Visual Question Answering","publication_year":2024,"publication_date":"2024-09-03","ids":{"openalex":"https://openalex.org/W4402208632","doi":"https://doi.org/10.1109/tbdata.2024.3453750"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2024.3453750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2024.3453750","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"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 Big Data","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/A5037931738","display_name":"Heng Liu","orcid":"https://orcid.org/0000-0002-0703-6255"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Liu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0703-6255","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091545406","display_name":"Boyue Wang","orcid":"https://orcid.org/0000-0002-2677-8342"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyue Wang","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2677-8342","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082380547","display_name":"Yanfeng Sun","orcid":"https://orcid.org/0000-0002-0872-384X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Sun","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0872-384X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015817857","display_name":"Junbin Gao","orcid":"https://orcid.org/0000-0001-9803-0256"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junbin Gao","raw_affiliation_strings":["Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Camperdown, NSW, Australia","Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Camperdown, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9803-0256","affiliations":[{"raw_affiliation_string":"Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Camperdown, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014727866","display_name":"Xiaoyan Li","orcid":"https://orcid.org/0000-0003-1536-4264"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Li","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1536-4264","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027329007","display_name":"Yongli Hu","orcid":"https://orcid.org/0000-0003-0440-438X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongli Hu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0440-438X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020527092","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0003-3121-1823"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3121-1823","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4087,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59771492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"11","issue":"3","first_page":"1346","last_page":"1356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9919999837875366,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9919999837875366,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9897000193595886,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9801999926567078,"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/granularity","display_name":"Granularity","score":0.8523678779602051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199536204338074},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6722203493118286},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.590977668762207},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5821461081504822},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.548629105091095},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46786072850227356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38666099309921265},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0738493800163269}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8523678779602051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199536204338074},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6722203493118286},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.590977668762207},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5821461081504822},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.548629105091095},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46786072850227356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38666099309921265},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0738493800163269},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2024.3453750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbdata.2024.3453750","pdf_url":null,"source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"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 Big Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1098515591","display_name":null,"funder_award_id":"62272015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6152166824","display_name":null,"funder_award_id":"92370102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W639708223","https://openalex.org/W1832693441","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2521367263","https://openalex.org/W2529436507","https://openalex.org/W2561529111","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2760103357","https://openalex.org/W2795758732","https://openalex.org/W2896457183","https://openalex.org/W2904885916","https://openalex.org/W2929255686","https://openalex.org/W2947312908","https://openalex.org/W2953016680","https://openalex.org/W2962779575","https://openalex.org/W2963398599","https://openalex.org/W2963717374","https://openalex.org/W2964138017","https://openalex.org/W2966350350","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2976260559","https://openalex.org/W2982461533","https://openalex.org/W2987671777","https://openalex.org/W3035454069","https://openalex.org/W3044175177","https://openalex.org/W3087516599","https://openalex.org/W3093200502","https://openalex.org/W3093609036","https://openalex.org/W3101703188","https://openalex.org/W3115476810","https://openalex.org/W3172845486","https://openalex.org/W3173038784","https://openalex.org/W3175888430","https://openalex.org/W3216470601","https://openalex.org/W4206430846","https://openalex.org/W4221155360","https://openalex.org/W4229040338","https://openalex.org/W6746052068","https://openalex.org/W6752083267","https://openalex.org/W6766904570","https://openalex.org/W6766978945","https://openalex.org/W6768324545"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Accurately":[0],"locating":[1],"the":[2,50,56,67,74,99,104,112,117,123,128,143,147,174,179,195,198],"question-related":[3],"regions":[4,28,47,71,77,141,149,164],"in":[5,55,153],"one":[6,24,43],"given":[7],"image":[8,25,46,70,76,140,163],"is":[9],"crucial":[10],"for":[11],"visual":[12],"question":[13],"answering":[14],"(VQA).":[15],"The":[16],"current":[17],"approaches":[18],"suffer":[19],"two":[20,186],"limitations:":[21],"(1)":[22],"Dividing":[23],"into":[26],"multiple":[27],"may":[29,52],"lose":[30],"parts":[31],"of":[32,60,181,197],"semantic":[33],"information":[34],"and":[35,72,90,167,192],"original":[36],"relationships":[37],"between":[38,69],"regions;":[39],"(2)":[40],"Choosing":[41],"only":[42],"or":[44,58],"all":[45],"to":[48,64,133,142,177],"predict":[49,178],"answer":[51,180],"correspondingly":[53],"result":[54],"insufficiency":[57],"redundancy":[59],"information.":[61],"Therefore,":[62],"how":[63],"effectively":[65],"mine":[66],"relationship":[68],"choose":[73],"relevant":[75,139,162],"are":[78,150],"vital.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,102,126,172],"propose":[84,103],"a":[85,156],"novel":[86],"<b>M</b>ulti-granularity":[87],"feature":[88,106],"interaction":[89,107],"<b>M</b>ulti-region":[91],"selection-based":[92],"triplet":[93,176],"VQA":[94],"model":[95],"(M2TVQA).":[96],"To":[97,121],"tackle":[98],"first":[100],"limitation,":[101,125],"multi-granularity":[105],"strategy":[108,132,157],"that":[109],"adaptively":[110,134],"supplements":[111],"global":[113],"coarse-granularity":[114],"features":[115],"with":[116],"regional":[118],"fine-granularity":[119],"features.":[120],"overcome":[122],"second":[124],"design":[127],"Top-<inline-formula><tex-math":[129],"notation=\"LaTeX\">$K$</tex-math></inline-formula>":[130,137],"learning":[131],"select":[135,159],"<inline-formula><tex-math":[136],"most":[138],"question,":[144],"even":[145],"if":[146],"selected":[148],"far":[151],"away":[152],"space.":[154],"Such":[155],"can":[158],"as":[160,165],"many":[161],"possible":[166],"reduce":[168],"introducing":[169],"noise.":[170],"Finally,":[171],"construct":[173],"multi-modality":[175],"VQA.":[182],"Extended":[183],"experiments":[184],"on":[185],"public":[187],"outside":[188],"knowledge":[189],"datasets":[190],"OK-VQA":[191],"KRVQA":[193],"verify":[194],"effectiveness":[196],"proposed":[199],"model.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
