{"id":"https://openalex.org/W4387197110","doi":"https://doi.org/10.1109/tip.2023.3318949","title":"Semantic-Aware Modular Capsule Routing for Visual Question Answering","display_name":"Semantic-Aware Modular Capsule Routing for Visual Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387197110","doi":"https://doi.org/10.1109/tip.2023.3318949","pmid":"https://pubmed.ncbi.nlm.nih.gov/37773902"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3318949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3318949","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5054031708","display_name":"Yudong Han","orcid":"https://orcid.org/0000-0002-7830-9679"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Han","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-7830-9679","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianhua Yin","orcid":"https://orcid.org/0000-0002-4611-2986"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Yin","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-4611-2986","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654190","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0247-5221","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039731055","display_name":"Yinwei Wei","orcid":"https://orcid.org/0000-0003-1791-3159"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yinwei Wei","raw_affiliation_strings":["NExT++, National University of Singapore, Queenstown, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1791-3159","affiliations":[{"raw_affiliation_string":"NExT++, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2763,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82432669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"5537","last_page":"5549"},"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":0.9988999962806702,"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":0.9987000226974487,"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":0.8514035940170288},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.701200008392334},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6226273775100708},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5738640427589417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5574634671211243},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4820059835910797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45465919375419617},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4490804672241211},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.426037073135376},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09808674454689026},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09647125005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514035940170288},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.701200008392334},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6226273775100708},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5738640427589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5574634671211243},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4820059835910797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45465919375419617},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4490804672241211},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.426037073135376},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09808674454689026},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09647125005722046},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3318949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3318949","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37773902","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37773902","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3596831556","display_name":null,"funder_award_id":"62172261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3981135610","display_name":null,"funder_award_id":"62276155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4068028691","display_name":null,"funder_award_id":"ZR2021MF040","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2471094925","https://openalex.org/W2560730294","https://openalex.org/W2561529111","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2775221064","https://openalex.org/W2787119853","https://openalex.org/W2808877322","https://openalex.org/W2883104598","https://openalex.org/W2886641317","https://openalex.org/W2889792105","https://openalex.org/W2891394954","https://openalex.org/W2892259963","https://openalex.org/W2896902935","https://openalex.org/W2905524945","https://openalex.org/W2916723116","https://openalex.org/W2947312908","https://openalex.org/W2949197413","https://openalex.org/W2962749469","https://openalex.org/W2962944050","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963521239","https://openalex.org/W2963703618","https://openalex.org/W2963717374","https://openalex.org/W2963938081","https://openalex.org/W2964067226","https://openalex.org/W2964072591","https://openalex.org/W2964118342","https://openalex.org/W2964303913","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969541233","https://openalex.org/W2969679616","https://openalex.org/W2969876226","https://openalex.org/W2981578638","https://openalex.org/W2983995706","https://openalex.org/W2997545008","https://openalex.org/W3004349648","https://openalex.org/W3034787499","https://openalex.org/W3035454069","https://openalex.org/W3037773948","https://openalex.org/W3092767330","https://openalex.org/W3093200502","https://openalex.org/W3095718427","https://openalex.org/W3099884329","https://openalex.org/W3113117059","https://openalex.org/W3175703099","https://openalex.org/W3203022498","https://openalex.org/W3203354307","https://openalex.org/W4289421997","https://openalex.org/W4299522971","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6739901393","https://openalex.org/W6743446608","https://openalex.org/W6746901506","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6754375721","https://openalex.org/W6754553780","https://openalex.org/W6754733129","https://openalex.org/W6766904570","https://openalex.org/W6767105951","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6780226713","https://openalex.org/W6785465245"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W3088304681"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,178,184,199],"fundamentally":[5],"compositional":[6],"in":[7,59,121,191],"nature,":[8],"and":[9,75,102,128,146,159,209],"many":[10],"questions":[11],"are":[12,119,133],"simply":[13],"answered":[14],"by":[15],"decomposing":[16],"them":[17],"into":[18],"modular":[19],"sub-problems.":[20],"The":[21],"recent":[22],"proposed":[23,164],"Neural":[24],"Module":[25],"Network":[26],"(NMN)":[27],"employ":[28],"this":[29,82,182],"strategy":[30],"to":[31,63,95,186,201],"question":[32],"answering,":[33],"whereas":[34],"heavily":[35],"rest":[36],"with":[37],"off-the-shelf":[38],"layout":[39],"parser":[40],"or":[41],"additional":[42],"expert":[43],"policy":[44],"regarding":[45],"the":[46,54,60,64,68,72,78,98,104,125,129,147,157,174,188],"network":[47],"architecture":[48,207],"design":[49],"instead":[50],"of":[51,67,77,124,139,162],"learning":[52,208],"from":[53],"data.":[55],"These":[56],"strategies":[57],"result":[58],"unsatisfactory":[61],"adaptability":[62],"semantically-complicated":[65],"variance":[66],"inputs,":[69],"thereby":[70],"hindering":[71],"representational":[73],"capacity":[74],"generalizability":[76],"model.":[79],"To":[80],"tackle":[81],"problem,":[83],"we":[84,194],"propose":[85],"a":[86,137,203],"Semantic-aware":[87],"modUlar":[88],"caPsulE":[89],"Routing":[90],"framework,":[91],"termed":[92],"as":[93,114,116,171,173],"SUPER,":[94],"better":[96],"capture":[97],"instance-specific":[99],"vision-semantic":[100,148],"characteristics":[101],"refine":[103],"discriminative":[105],"representations":[106,149],"for":[107,212],"prediction.":[108],"Particularly,":[109],"five":[110,168],"powerful":[111],"specialized":[112],"modules":[113],"well":[115,172],"dynamic":[117],"routers":[118],"tailored":[120],"each":[122],"layer":[123],"SUPER":[126,165],"network,":[127],"compact":[130],"routing":[131],"spaces":[132],"constructed":[134],"such":[135],"that":[136,181,196],"variety":[138],"customizable":[140],"routes":[141],"can":[142,150],"be":[143,151],"sufficiently":[144],"exploited":[145],"explicitly":[152],"calibrated.":[153],"We":[154],"comparatively":[155],"justify":[156],"effectiveness":[158],"generalization":[160],"ability":[161],"our":[163,197],"scheme":[166],"over":[167],"benchmark":[169],"datasets,":[170],"parametric-efficient":[175],"advantage.":[176],"It":[177],"worth":[179],"emphasizing":[180],"work":[183],"not":[185],"pursue":[187],"state-of-the-art":[189],"results":[190],"VQA.":[192,213],"Instead,":[193],"expect":[195],"model":[198],"responsible":[200],"provide":[202],"novel":[204],"perspective":[205],"towards":[206],"representation":[210],"calibration":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}