{"id":"https://openalex.org/W4403791749","doi":"https://doi.org/10.1145/3664647.3681623","title":"<scp>InMu-Net:</scp> Advancing Multi-modal Intent Detection via Information Bottleneck and Multi-sensory Processing","display_name":"<scp>InMu-Net:</scp> Advancing Multi-modal Intent Detection via Information Bottleneck and Multi-sensory Processing","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791749","doi":"https://doi.org/10.1145/3664647.3681623"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5102856192","display_name":"Zhihong Zhu","orcid":"https://orcid.org/0009-0001-4530-5516"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihong Zhu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018420548","display_name":"Xuxin Cheng","orcid":"https://orcid.org/0009-0002-6244-2931"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuxin Cheng","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032213685","display_name":"Zhaorun Chen","orcid":"https://orcid.org/0000-0002-2668-6587"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaorun Chen","raw_affiliation_strings":["The University of Chicago, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"The University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060201245","display_name":"Yuyan Chen","orcid":"https://orcid.org/0009-0003-5888-5518"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyan Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752462","display_name":"Yunyan Zhang","orcid":"https://orcid.org/0000-0003-1306-5746"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunyan Zhang","raw_affiliation_strings":["Jarvis Research Center, Tencent YouTu Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Jarvis Research Center, Tencent YouTu Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352418","display_name":"Xian Wu","orcid":"https://orcid.org/0000-0003-1118-9710"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Wu","raw_affiliation_strings":["Jarvis Research Center, Tencent YouTu Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Jarvis Research Center, Tencent YouTu Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051649145","display_name":"Yefeng Zheng","orcid":"https://orcid.org/0000-0003-2195-2847"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefeng Zheng","raw_affiliation_strings":["Medical Artificial Intelligence Lab, Westlake University &amp; Jarvis Research Center, Tencent YouTu Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Medical Artificial Intelligence Lab, Westlake University &amp; Jarvis Research Center, Tencent YouTu Lab, Hangzhou, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102786375","display_name":"Bowen Xing","orcid":"https://orcid.org/0000-0001-7722-1520"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Xing","raw_affiliation_strings":["Beijing Key Laboratory of Knowledge Engineering for Materials Science, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Knowledge Engineering for Materials Science, School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102856192"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.7376,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87313847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9965999722480774,"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":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bottleneck","display_name":"Bottleneck","score":0.8190270662307739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.710918664932251},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5742511749267578},{"id":"https://openalex.org/keywords/sensory-system","display_name":"Sensory system","score":0.49420931935310364},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3630761504173279},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22894597053527832},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06342709064483643}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8190270662307739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710918664932251},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5742511749267578},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.49420931935310364},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3630761504173279},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22894597053527832},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06342709064483643},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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:10.1145/3664647.3681623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W285471286","https://openalex.org/W2000031724","https://openalex.org/W2101214486","https://openalex.org/W2122925692","https://openalex.org/W2166944917","https://openalex.org/W2307937785","https://openalex.org/W2883409523","https://openalex.org/W2899575547","https://openalex.org/W2915889284","https://openalex.org/W2950811190","https://openalex.org/W2962858109","https://openalex.org/W2964051877","https://openalex.org/W2979826702","https://openalex.org/W3034266838","https://openalex.org/W3035342001","https://openalex.org/W3035473672","https://openalex.org/W3037572520","https://openalex.org/W3093051361","https://openalex.org/W3128412859","https://openalex.org/W3173203577","https://openalex.org/W3175530672","https://openalex.org/W3188188945","https://openalex.org/W3211495814","https://openalex.org/W3214432797","https://openalex.org/W4224318508","https://openalex.org/W4225985623","https://openalex.org/W4285149123","https://openalex.org/W4304080418","https://openalex.org/W4312305353","https://openalex.org/W4320008876","https://openalex.org/W4385565675","https://openalex.org/W4385569851","https://openalex.org/W4385801378","https://openalex.org/W4392366643","https://openalex.org/W4393160357","https://openalex.org/W4394625517","https://openalex.org/W4402683962"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000"],"abstract_inverted_index":{"Multi-modal":[0],"intent":[1,51],"detection":[2],"(MID)":[3],"aims":[4],"to":[5,56,93,110,122],"comprehend":[6],"users'":[7],"intentions":[8],"through":[9],"diverse":[10],"modalities,":[11],"which":[12],"has":[13],"received":[14],"widespread":[15],"attention":[16],"in":[17,24,40,83,99,166],"dialogue":[18],"systems.":[19],"Despite":[20],"the":[21,58,73,96,100,112,127,131,135,147],"promising":[22],"advancements":[23],"complex":[25],"fusion":[26],"mechanisms":[27],"or":[28],"architecture":[29],"designs,":[30],"challenges":[31],"remain":[32],"due":[33],"to:":[34],"(1)":[35],"various":[36],"noise":[37],"and":[38,43,46,76,151,164,171],"redundancy":[39],"both":[41],"visual":[42],"audio":[44],"modalities":[45],"(2)":[47],"long-tailed":[48],"distributions":[49],"of":[50,114,134,149,158],"categories.":[52],"In":[53],"this":[54],"paper,":[55],"tackle":[57],"above":[59],"two":[60,142],"issues,":[61],"we":[62,87,104],"propose":[63],"InMu-Net,":[64],"a":[65,89,106,156],"simple":[66],"yet":[67],"effective":[68],"framework":[69],"for":[70],"MID":[71,143],"from":[72],"Information":[74],"bottleneck":[75,91],"Multi-sensory":[77],"processing":[78],"perspective.":[79],"Our":[80],"contributions":[81],"lie":[82],"three":[84],"aspects.":[85],"First,":[86],"devise":[88],"denoising":[90,162],"module":[92],"filter":[94],"out":[95],"intent-irrelevant":[97],"information":[98],"fused":[101],"feature;":[102],"Second,":[103],"introduce":[105],"saliency":[107],"preservation":[108],"loss":[109],"prevent":[111],"dropping":[113],"intent-relevant":[115],"information;":[116],"Ultimately,":[117],"kurtosis":[118],"regulation":[119],"is":[120],"introduced":[121],"maintain":[123],"representation":[124],"smoothness":[125],"during":[126],"filtering":[128],"process,":[129],"mitigating":[130],"adverse":[132],"impact":[133],"long":[136],"tail":[137],"distribution.":[138],"Comprehensive":[139],"experiments":[140],"on":[141],"benchmark":[144],"datasets":[145],"demonstrate":[146],"effectiveness":[148],"InMu-Net":[150],"its":[152],"vital":[153],"components.":[154],"Impressively,":[155],"series":[157],"analyses":[159],"reveal":[160],"our":[161],"potential":[163],"robustness":[165],"low-resource,":[167],"modality":[168],"corruption,":[169],"cross-architecture":[170],"cross-task":[172],"scenarios.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}