{"id":"https://openalex.org/W4392909577","doi":"https://doi.org/10.1109/icassp48485.2024.10446922","title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-Modal Intent Detection","display_name":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-Modal Intent Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909577","doi":"https://doi.org/10.1109/icassp48485.2024.10446922"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067715252","display_name":"Shijue Huang","orcid":"https://orcid.org/0000-0001-9443-7948"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210102458","display_name":"Novel (United States)","ror":"https://ror.org/00z5k4y41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shijue Huang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),School of Computer Science","Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","School of Computer Science, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),School of Computer Science","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","institution_ids":["https://openalex.org/I4210102458"]},{"raw_affiliation_string":"School of Computer Science, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering","School of Computer Science and Engineering, Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760972","display_name":"Bingbing Wang","orcid":"https://orcid.org/0000-0001-9659-8892"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210102458","display_name":"Novel (United States)","ror":"https://ror.org/00z5k4y41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Bingbing Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),School of Computer Science","Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","School of Computer Science, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),School of Computer Science","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","institution_ids":["https://openalex.org/I4210102458"]},{"raw_affiliation_string":"School of Computer Science, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077104771","display_name":"Geng Tu","orcid":"https://orcid.org/0000-0002-3524-1408"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210102458","display_name":"Novel (United States)","ror":"https://ror.org/00z5k4y41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102458"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Geng Tu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),School of Computer Science","Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","School of Computer Science, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),School of Computer Science","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","institution_ids":["https://openalex.org/I4210102458"]},{"raw_affiliation_string":"School of Computer Science, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026719663","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0002-4009-5679"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210102458","display_name":"Novel (United States)","ror":"https://ror.org/00z5k4y41","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102458"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ruifeng Xu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),School of Computer Science","Peng Cheng Laboratory","Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","School of Computer Science, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),School of Computer Science","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","institution_ids":["https://openalex.org/I4210102458"]},{"raw_affiliation_string":"School of Computer Science, Harbin Institute of Technology (Shenzhen)","institution_ids":["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":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10206","last_page":"10210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9829999804496765,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9829999804496765,"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/modal","display_name":"Modal","score":0.7335403561592102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6294003129005432},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.3496971130371094},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09749752283096313}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7335403561592102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6294003129005432},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.3496971130371094},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09749752283096313},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G2230680632","display_name":null,"funder_award_id":"PCL2023A09","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6312846351","display_name":null,"funder_award_id":"62176076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7349572720","display_name":null,"funder_award_id":"2022B1212010005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8139119493","display_name":null,"funder_award_id":"2023A1515012922","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2964051877","https://openalex.org/W2970217405","https://openalex.org/W2971167298","https://openalex.org/W3009260245","https://openalex.org/W3016006013","https://openalex.org/W3034266838","https://openalex.org/W3093051361","https://openalex.org/W3173549566","https://openalex.org/W3188188945","https://openalex.org/W3204260746","https://openalex.org/W4287889588","https://openalex.org/W4297841597","https://openalex.org/W4304080418","https://openalex.org/W4308236449","https://openalex.org/W4322759378","https://openalex.org/W4385245566","https://openalex.org/W4404658388","https://openalex.org/W6620707391","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6798297070","https://openalex.org/W6850462617","https://openalex.org/W6850627791"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2324615561","https://openalex.org/W2086120259","https://openalex.org/W2390279801","https://openalex.org/W2245170124","https://openalex.org/W2076393078","https://openalex.org/W2358668433","https://openalex.org/W3186982001","https://openalex.org/W1984402782"],"abstract_inverted_index":{"Multi-modal":[0],"intent":[1,31,51],"detection":[2,32],"aims":[3],"to":[4,8,36,67,79,101],"utilize":[5],"various":[6],"modalities":[7,44],"understand":[9],"the":[10,17,47,69,129,139],"user\u2019s":[11],"intentions,":[12],"which":[13],"is":[14],"essential":[15],"for":[16,29],"deployment":[18],"of":[19,43],"dialogue":[20],"systems":[21],"in":[22],"real-world":[23],"scenarios.":[24],"The":[25],"two":[26],"core":[27],"challenges":[28],"multi-modal":[30,50,117],"are":[33],"(1)":[34],"how":[35],"effectively":[37,82,113],"align":[38,83,114],"and":[39,45,81,84,90,115],"fuse":[40,85,116],"different":[41],"features":[42,86,118],"(2)":[46],"limited":[48],"labeled":[49],"training":[52,105],"data.":[53,106],"In":[54,123],"this":[55],"work,":[56],"we":[57,94],"introduce":[58],"a":[59,75,96],"shallow-to-deep":[60,76],"interaction":[61,77],"framework":[62],"with":[63],"data":[64,98,131],"augmentation":[65,99,132],"(SDIF-DA)":[66],"address":[68],"above":[70],"challenges.":[71],"Firstly,":[72],"SDIF-DA":[73,111],"leverages":[74],"module":[78],"progressively":[80],"across":[87],"text,":[88],"video,":[89],"audio":[91],"modalities.":[92],"Secondly,":[93],"propose":[95],"ChatGPT-based":[97],"approach":[100,133],"automatically":[102],"augment":[103],"sufficient":[104],"Experimental":[107],"results":[108],"demonstrate":[109],"that":[110,128],"can":[112,134],"by":[119],"achieving":[120],"state-of-the-art":[121],"performance.":[122],"addition,":[124],"extensive":[125],"analyses":[126],"show":[127],"introduced":[130],"successfully":[135],"distill":[136],"knowledge":[137],"from":[138],"large":[140],"language":[141],"model.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}