{"id":"https://openalex.org/W4285185970","doi":"https://doi.org/10.1109/taslp.2022.3178236","title":"Interpretable Multimodal Capsule Fusion","display_name":"Interpretable Multimodal Capsule Fusion","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285185970","doi":"https://doi.org/10.1109/taslp.2022.3178236"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3178236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3178236","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5101473339","display_name":"Jianfeng Wu","orcid":"https://orcid.org/0000-0002-5583-0867"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Wu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-5583-0867","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010270301","display_name":"Sijie Mai","orcid":"https://orcid.org/0000-0001-9763-375X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijie Mai","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9763-375X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-4884-323X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.5104,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.845164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1815","last_page":"1826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9972000122070312,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8210466504096985},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7493672370910645},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7282723784446716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264468669891357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6226822733879089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6126258969306946},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5917997360229492},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5213293433189392},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.49996447563171387},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4791233539581299},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4522536098957062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4392687976360321},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.37762561440467834}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8210466504096985},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7493672370910645},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7282723784446716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264468669891357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6226822733879089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126258969306946},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5917997360229492},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5213293433189392},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.49996447563171387},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4791233539581299},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4522536098957062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4392687976360321},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.37762561440467834},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3178236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3178236","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6370073915","display_name":null,"funder_award_id":"62 076 262","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1133916940","https://openalex.org/W1670132599","https://openalex.org/W1983364832","https://openalex.org/W2029996593","https://openalex.org/W2064675550","https://openalex.org/W2079725295","https://openalex.org/W2085662862","https://openalex.org/W2093428321","https://openalex.org/W2095176743","https://openalex.org/W2146334809","https://openalex.org/W2250539671","https://openalex.org/W2306941105","https://openalex.org/W2583643061","https://openalex.org/W2619383789","https://openalex.org/W2787581402","https://openalex.org/W2790404832","https://openalex.org/W2883409523","https://openalex.org/W2886193235","https://openalex.org/W2921734165","https://openalex.org/W2943547402","https://openalex.org/W2949391930","https://openalex.org/W2950404230","https://openalex.org/W2962931510","https://openalex.org/W2962986764","https://openalex.org/W2963032608","https://openalex.org/W2963702064","https://openalex.org/W2963710346","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W2964266095","https://openalex.org/W2964346351","https://openalex.org/W2990629080","https://openalex.org/W2997573100","https://openalex.org/W2998470965","https://openalex.org/W3016138882","https://openalex.org/W3034897750","https://openalex.org/W3089044119","https://openalex.org/W3094173182","https://openalex.org/W3105484484","https://openalex.org/W3120680448","https://openalex.org/W3141688548","https://openalex.org/W3153807302","https://openalex.org/W3163767300","https://openalex.org/W6631190155","https://openalex.org/W6633048663","https://openalex.org/W6636510571","https://openalex.org/W6636883489","https://openalex.org/W6739901393","https://openalex.org/W6743446608","https://openalex.org/W6748053814","https://openalex.org/W6752724743","https://openalex.org/W6758623387","https://openalex.org/W6760133027","https://openalex.org/W6763665168","https://openalex.org/W6770782798"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"With":[0],"the":[1,31,49,109,130,137,153,161],"development":[2],"of":[3,33,70,90,104,112,117,132,139,156,163],"social":[4],"networking":[5],"platform,":[6],"multimodal":[7],"sentiment":[8],"analysis":[9],"has":[10],"become":[11],"increasingly":[12],"prominent.":[13],"Existing":[14],"models":[15],"focus":[16],"on":[17,178],"capturing":[18],"intramodal":[19],"and":[20,43,74,84,127,188],"intermodal":[21,105],"interactions":[22],"to":[23,48,79,99,108,114],"produce":[24,80,115],"effective":[25,183],"modality":[26,45,82,125,164,184],"representations.":[27],"However,":[28],"they":[29],"overlook":[30],"study":[32],"interpretability":[34],"which":[35,44,66,144,159],"reveals":[36],"how":[37],"modalities":[38,92,141],"interact":[39],"with":[40,182],"each":[41],"other":[42],"contributes":[46],"most":[47],"final":[50],"prediction.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,96],"propose":[56],"an":[57],"interpretable":[58],"model":[59,174],"called":[60],"Interpretable":[61],"Multimodal":[62],"Capsule":[63,71],"Fusion":[64],"(IMCF)":[65],"integrates":[67],"routing":[68,120,133,148,192],"mechanism":[69,121,149],"Network":[72],"(CapsNet)":[73],"Long":[75],"Short-Term":[76],"Memory":[77],"(LSTM)":[78],"refined":[81],"representations":[83],"provide":[85],"interpretation.":[86,146],"By":[87],"constructing":[88],"features":[89],"different":[91,140,157],"into":[93],"input":[94],"sequence,":[95],"are":[97],"able":[98],"obtain":[100],"highly":[101],"expressive":[102],"representation":[103,116],"dynamics":[106],"due":[107],"strong":[110],"ability":[111],"LSTM":[113,187],"sequence.":[118],"As":[119],"is":[122],"applied":[123],"during":[124],"fusion":[126,165,185],"prediction":[128],"stages,":[129],"value":[131],"coefficient":[134],"can":[135,150],"reveal":[136],"contributions":[138],"or":[142],"dynamics,":[143],"provides":[145],"Meanwhile,":[147],"iteratively":[151],"adjust":[152],"information":[154],"flows":[155],"modalities,":[158],"makes":[160],"process":[162],"more":[166],"reasonable.":[167],"The":[168],"experimental":[169],"results":[170],"show":[171],"that":[172],"our":[173],"achieves":[175],"competitive":[176],"performance":[177],"two":[179],"benchmark":[180],"datasets":[181],"by":[186,191],"interpretation":[189],"provided":[190],"mechanism.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}