{"id":"https://openalex.org/W4402979780","doi":"https://doi.org/10.1109/icme57554.2024.10688018","title":"Multi-modal Intent Detection with LVAMoE: the Language-Visual-Audio Mixture of Experts","display_name":"Multi-modal Intent Detection with LVAMoE: the Language-Visual-Audio Mixture of Experts","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979780","doi":"https://doi.org/10.1109/icme57554.2024.10688018"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5100662726","display_name":"Tingyu Li","orcid":"https://orcid.org/0000-0002-5785-1178"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tingyu Li","raw_affiliation_strings":["Xi’an Jiaotong University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110615440","display_name":"Junpeng Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junpeng Bao","raw_affiliation_strings":["Xi’an Jiaotong University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101290650","display_name":"Jiaqi Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Qin","raw_affiliation_strings":["Xi’an Jiaotong University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015157242","display_name":"Yuping Liang","orcid":"https://orcid.org/0009-0001-0969-6038"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuping Liang","raw_affiliation_strings":["Guangdong OPPO Mobile Telecommunications Corp.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Guangdong OPPO Mobile Telecommunications Corp.,Shenzhen,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruijiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijiang Zhang","raw_affiliation_strings":["Guangdong OPPO Mobile Telecommunications Corp.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Guangdong OPPO Mobile Telecommunications Corp.,Shenzhen,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100700440","display_name":"Jason Wang","orcid":"https://orcid.org/0009-0003-1875-7693"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jason Wang","raw_affiliation_strings":["Guangdong OPPO Mobile Telecommunications Corp.,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Guangdong OPPO Mobile Telecommunications Corp.,Shenzhen,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100662726"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.6738,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75602182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.916700005531311,"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/T12031","display_name":"Speech and dialogue systems","score":0.916700005531311,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9049000144004822,"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":0.7864441275596619},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.775977373123169},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6729937791824341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4671425521373749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45709484815597534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4222480058670044},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24756601452827454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864441275596619},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.775977373123169},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6729937791824341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4671425521373749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45709484815597534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4222480058670044},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24756601452827454},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2767249564","https://openalex.org/W2772633765","https://openalex.org/W2787581402","https://openalex.org/W2924126491","https://openalex.org/W2958722525","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W2964346351","https://openalex.org/W3034266838","https://openalex.org/W3034849760","https://openalex.org/W3037572520","https://openalex.org/W3048195943","https://openalex.org/W3093051361","https://openalex.org/W3206529771","https://openalex.org/W4304080418","https://openalex.org/W4372349258"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"Intent":[1],"Detection":[2],"is":[3,18,76,98,113,124],"an":[4],"important":[5],"task":[6],"for":[7],"understanding":[8],"human":[9],"language":[10],"in":[11,55,89],"real-world":[12],"multimodal":[13,120],"scenarios,":[14],"where":[15],"the":[16,19,46,56,61,70,79,83,90,137,152],"key":[17],"representation":[20,47,92,107],"and":[21,30,122],"fusion":[22,39,57,123],"of":[23,48,73,81,111],"different":[24,49,87],"modal":[25,91],"information":[26],"(e.g.,":[27],"language,":[28],"visual,":[29],"audio).":[31],"Most":[32],"previous":[33],"research":[34],"focus":[35],"on":[36,143,155],"exploring":[37],"modality":[38],"methods":[40],"to":[41,60,100,115],"improve":[42],"model":[43,138,154],"performance.":[44],"However,":[45],"modalities":[50,88],"presents":[51],"a":[52,95,105,127],"great":[53],"challenge":[54],"stage":[58],"due":[59],"heterogeneity":[62],"gap":[63,85],"between":[64,86],"them.":[65],"To":[66,135],"address":[67],"this":[68],"problem,":[69],"Language-Visual-Audio":[71],"Mixture":[72,110],"Experts":[74],"(LVAMoE)":[75],"proposed":[77],"with":[78,109,132],"aim":[80],"minimizing":[82],"distribution":[84],"stage.":[93],"Firstly,":[94],"dense":[96],"encoder":[97,108],"used":[99],"obtain":[101,116],"modality-invariant":[102],"representations.":[103,118],"Secondly,":[104],"sparse":[106],"Experts(MoE)":[112],"utilized":[114],"modality-specific":[117],"Finally,":[119],"interaction":[121],"achieved":[125],"through":[126],"cross-modal":[128],"attention":[129],"approach":[130],"combined":[131],"contrast":[133],"learning.":[134],"validate":[136],"performance,":[139],"experiments":[140],"are":[141],"conducted":[142],"three":[144],"datasets.":[145],"The":[146],"results":[147],"show":[148],"that":[149],"LVAMoE":[150],"outperforms":[151],"baseline":[153],"several":[156],"evaluation":[157],"metrics.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}