{"id":"https://openalex.org/W4413344342","doi":"https://doi.org/10.1109/lsp.2025.3599107","title":"Altering Query Prompting With Contrastive Learning for Multimodal Intent Recognition","display_name":"Altering Query Prompting With Contrastive Learning for Multimodal Intent Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413344342","doi":"https://doi.org/10.1109/lsp.2025.3599107"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3599107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3599107","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Yuxin Jia","orcid":"https://orcid.org/0009-0005-9551-5801"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxin Jia","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xueping Wang","orcid":"https://orcid.org/0000-0003-4862-8975"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueping Wang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003260829","display_name":"Zhanpeng Shao","orcid":"https://orcid.org/0000-0002-8130-5230"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanpeng Shao","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343854","display_name":"Min Liu","orcid":"https://orcid.org/0000-0001-6406-4896"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN","IN"],"is_corresponding":false,"raw_author_name":"Min Liu","raw_affiliation_strings":["School of Artificial Intelligence and Robotics, Hunan University and National Engineering Research Center for Robot Visual Perception and Control Technology, Changsha, China","School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University and National Engineering Research Center for Robot Visual Perception and Control Technology, Changsha, China","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173759888","https://openalex.org/I3130607311"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1083402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3345","last_page":"3349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8370000123977661,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8370000123977661,"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":0.8342999815940857,"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/T10320","display_name":"Neural Networks and Applications","score":0.8047000169754028,"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":0.7634353637695312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49120160937309265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39042139053344727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35193705558776855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34520745277404785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634353637695312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49120160937309265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39042139053344727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35193705558776855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34520745277404785}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3599107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3599107","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1085509035","display_name":null,"funder_award_id":"62221002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1850154686","display_name":null,"funder_award_id":"2022M721120","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3687505393","display_name":null,"funder_award_id":"2024JJ3013","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G4999935688","display_name":null,"funder_award_id":"2025JJ50340","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G6118170862","display_name":null,"funder_award_id":"62203168","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6984645349","display_name":null,"funder_award_id":"62425305","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2146334809","https://openalex.org/W2896457183","https://openalex.org/W2964051877","https://openalex.org/W2979826702","https://openalex.org/W3034266838","https://openalex.org/W3093051361","https://openalex.org/W3100777112","https://openalex.org/W3138516171","https://openalex.org/W3163470448","https://openalex.org/W3214432797","https://openalex.org/W4206396243","https://openalex.org/W4304080418","https://openalex.org/W4385571111","https://openalex.org/W4387977958","https://openalex.org/W4392909577","https://openalex.org/W4393156689","https://openalex.org/W4399205233","https://openalex.org/W4399800695","https://openalex.org/W4402781194","https://openalex.org/W4411019705"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"intent":[1,157],"recognition":[2],"utilizes":[3],"heterogeneous":[4],"modalities":[5,98],"such":[6],"as":[7,18,101],"visual,":[8,95],"auditory,":[9],"and":[10,43,76,96,141,175],"textual":[11,154],"cues":[12],"to":[13,38,45],"infer":[14],"user":[15],"intent,":[16],"serving":[17],"a":[19,88,187],"pivotal":[20],"component":[21],"in":[22,55,103],"human-machine":[23],"interaction.":[24],"Existing":[25],"approaches,":[26],"however,":[27],"often":[28],"rely":[29],"on":[30,148,173,185],"unimodal":[31],"paradigms":[32],"or":[33],"shallow":[34],"multimodal":[35,78],"fusion,":[36],"failing":[37],"model":[39],"cross-modal":[40,169],"semantic":[41],"dependencies":[42],"struggling":[44],"extract":[46],"discriminative":[47,124],"features":[48,163],"from":[49,156],"non-verbal":[50],"modalities,":[51,115],"limiting":[52],"their":[53],"robustness":[54],"complex":[56],"scenarios.":[57],"To":[58],"mitigate":[59],"these":[60],"limitations,":[61],"we":[62],"propose":[63],"an":[64],"Altering":[65,82],"Query":[66,83],"Prompting":[67,84],"with":[68],"Contrastive":[69,129],"Learning":[70,130],"framework":[71],"(AQP-CL)":[72],"that":[73,122],"dynamically":[74],"aligns":[75],"refines":[77,160],"representations.":[79],"Specifically,":[80],"the":[81,137],"(AQP)":[85],"module":[86],"introduces":[87],"tri-modality":[89],"rotation":[90],"attention":[91],"mechanism,":[92],"where":[93],"textual,":[94],"acoustic":[97],"cyclically":[99],"alternate":[100],"queries":[102],"cross-attention":[104],"operations.":[105],"This":[106],"approach":[107],"addresses":[108],"modality":[109,162],"bias":[110],"while":[111],"strengthening":[112],"interdependencies":[113],"between":[114],"ultimately":[116],"yielding":[117],"intent-aware":[118,138],"fused":[119],"feature":[120,143],"representations":[121],"preserve":[123],"cues.":[125],"The":[126],"Label-semantic":[127],"Augmented":[128],"(LACL)":[131],"strategy":[132],"generates":[133],"augmented":[134],"samples":[135],"through":[136,164],"query":[139],"prompt":[140],"enhances":[142],"discrimination":[144],"via":[145],"NT-Xent":[146],"loss":[147],"label":[149],"tokens.":[150],"By":[151],"integrating":[152],"high-confidence":[153],"semantics":[155],"labels,":[158],"LACL":[159],"auxiliary":[161],"contrastive":[165],"alignment,":[166],"ensuring":[167],"robust":[168],"representation":[170],"learning.":[171],"Evaluations":[172],"IEMOCAP":[174],"MIntRec":[176],"validate":[177],"AQP-CL's":[178],"superiority,":[179],"achieving":[180],"state-of-the-art":[181],"precision":[182],"of":[183],"77.78%":[184],"IEMOCAP,":[186],"3.41%":[188],"improvement":[189],"over":[190],"existing":[191],"methods.":[192]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}