{"id":"https://openalex.org/W4406219286","doi":"https://doi.org/10.1145/3711860","title":"Multimodal Cascaded Framework with Multimodal Latent Loss Functions Robust to Missing Modalities","display_name":"Multimodal Cascaded Framework with Multimodal Latent Loss Functions Robust to Missing Modalities","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406219286","doi":"https://doi.org/10.1145/3711860"},"language":"en","primary_location":{"id":"doi:10.1145/3711860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711860","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5007962043","display_name":"Vijay John","orcid":"https://orcid.org/0000-0002-9553-0906"},"institutions":[{"id":"https://openalex.org/I4210108837","display_name":"Guardian Industries (United States)","ror":"https://ror.org/023x6j183","country_code":"US","type":"company","lineage":["https://openalex.org/I4210108837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay John","raw_affiliation_strings":["Guardian Robot Project, RIKEN, Seika, Japan","Guardian Robot Project, RIKEN, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9553-0906","affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Seika, Japan","institution_ids":["https://openalex.org/I4210108837"]},{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[{"id":"https://openalex.org/I4210108837","display_name":"Guardian Industries (United States)","ror":"https://ror.org/023x6j183","country_code":"US","type":"company","lineage":["https://openalex.org/I4210108837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["Guardian Robot Project, RIKEN, Seika, Japan","Guardian Robot Project, RIKEN, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3799-4550","affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Seika, Japan","institution_ids":["https://openalex.org/I4210108837"]},{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210108837"],"apc_list":null,"apc_paid":null,"fwci":1.8049,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81320581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"21","issue":"9","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9923999905586243,"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":0.8525418043136597},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6820405721664429},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.42849239706993103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42728984355926514},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3925971984863281}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525418043136597},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6820405721664429},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.42849239706993103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42728984355926514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3925971984863281},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711860","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2017034896","https://openalex.org/W2110363498","https://openalex.org/W2140477882","https://openalex.org/W2523267570","https://openalex.org/W2770960269","https://openalex.org/W2799429369","https://openalex.org/W2803193013","https://openalex.org/W2809410879","https://openalex.org/W2936134684","https://openalex.org/W2997819898","https://openalex.org/W3008568651","https://openalex.org/W3008785076","https://openalex.org/W3012721484","https://openalex.org/W3026006730","https://openalex.org/W3097741049","https://openalex.org/W3114214226","https://openalex.org/W3161402421","https://openalex.org/W3168463823","https://openalex.org/W3175825020","https://openalex.org/W3193504637","https://openalex.org/W4307076504","https://openalex.org/W4313164293","https://openalex.org/W4376891663","https://openalex.org/W4379928393","https://openalex.org/W6608829506"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W2199184806","https://openalex.org/W127837312","https://openalex.org/W2922283411","https://openalex.org/W4384789578","https://openalex.org/W4387421317"],"abstract_inverted_index":{"Despite":[0],"interest":[1],"in":[2,13,62,75,177],"multimodal":[3,17,63,88,92,97,134,219],"classification,":[4],"few":[5],"studies":[6],"have":[7],"addressed":[8],"the":[9,28,39,43,47,58,76,81,105,172,178,183,210],"missing":[10,23,32,59,82,147],"modality":[11,33,60,83,148,188],"problem":[12,34,61,84],"which":[14],"an":[15,95],"incomplete":[16,91,133,218],"input":[18],"with":[19,217],"one":[20],"or":[21,185],"more":[22],"modalities":[24],"is":[25,35,51,73,99,126,140,193],"classified":[26],"as":[27,42],"target":[29],"class.":[30],"The":[31,70,110,124,137,190,205],"shown":[36],"to":[37,79,128,167],"reduce":[38],"classification":[40,64,214],"accuracy":[41,215],"discriminative":[44],"power":[45],"of":[46,104,115,182,187],"obtained":[48,100],"feature":[49,77,102,118,120],"space":[50,78,180],"reduced.":[52],"In":[53],"this":[54],"study,":[55],"we":[56],"address":[57,80],"using":[65,142],"a":[66],"novel":[67,143],"cascaded":[68,112,138,191,211],"framework.":[69],"proposed":[71,111],"framework":[72,113,125,139,192,212],"formulated":[74,127],"by":[85,101],"generating":[86],"complete":[87,131],"data":[89,98,135,170],"from":[90,171],"data.":[93,109,189,220],"Subsequently,":[94],"optimal":[96],"selection":[103],"generated":[106],"and":[107,122,132,154,199],"original":[108],"consists":[114],"three":[116],"steps:":[117],"extraction,":[119],"generation,":[121],"classification.":[123],"handle":[129],"both":[130],"simultaneously.":[136],"trained":[141],"latent":[144,155,179],"loss":[145,159],"functions:":[146],"joint":[149,152],"loss,":[150,153],"centroid":[151],"prior":[156],"loss.":[157],"These":[158],"functions,":[160],"based":[161],"on":[162,195],"metric":[163],"learning,":[164],"are":[165],"designed":[166],"ensure":[168],"that":[169,209],"same":[173],"class":[174],"remain":[175],"proximate":[176],"irrespective":[181],"presence":[184],"absence":[186],"validated":[194],"bimodal":[196],"audio-visible":[197],"RAVDESS":[198],"trimodal":[200],"audio-visible-thermal":[201],"Speaking":[202],"Faces":[203],"datasets.":[204],"experimental":[206],"results":[207],"show":[208],"improves":[213],"even":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}