{"id":"https://openalex.org/W4403792310","doi":"https://doi.org/10.1145/3664647.3681607","title":"MMAL: Multi-Modal Analytic Learning for Exemplar-Free Audio-Visual Class Incremental Tasks","display_name":"MMAL: Multi-Modal Analytic Learning for Exemplar-Free Audio-Visual Class Incremental Tasks","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792310","doi":"https://doi.org/10.1145/3664647.3681607"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681607","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681607","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/A5060201191","display_name":"Xianghu Yue","orcid":"https://orcid.org/0000-0003-3527-6034"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xianghu Yue","raw_affiliation_strings":["Department of Electrical and Computer and Engineering, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103064052","display_name":"Xueyi Zhang","orcid":"https://orcid.org/0009-0008-2394-3518"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyi Zhang","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047957154","display_name":"Yiming Chen","orcid":"https://orcid.org/0009-0006-9016-6646"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiming Chen","raw_affiliation_strings":["Department of Electrical and Computer and Engineering, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer and Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102710394","display_name":"Chengwei Zhang","orcid":"https://orcid.org/0000-0002-3375-2458"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Zhang","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering, University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028043255","display_name":"Mingrui Lao","orcid":"https://orcid.org/0000-0001-8413-7220"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Lao","raw_affiliation_strings":["National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061256037","display_name":"Huiping Zhuang","orcid":"https://orcid.org/0000-0002-4612-5445"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiping Zhuang","raw_affiliation_strings":["Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"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":"Xinyuan Qian","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5060201191"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71313845,"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":"2428","last_page":"2437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9944999814033508,"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":0.7751641273498535},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7367678880691528},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.7193588018417358},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6590334177017212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120411515235901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4051866829395294},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36757993698120117},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3294486105442047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751641273498535},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7367678880691528},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7193588018417358},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6590334177017212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120411515235901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4051866829395294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36757993698120117},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3294486105442047},{"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:10.1145/3664647.3681607","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681607","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2125485651","https://openalex.org/W2473930607","https://openalex.org/W2547701628","https://openalex.org/W2560647685","https://openalex.org/W2596164567","https://openalex.org/W2619697695","https://openalex.org/W2786446225","https://openalex.org/W2884282566","https://openalex.org/W2948734064","https://openalex.org/W2954929116","https://openalex.org/W2962865004","https://openalex.org/W2963218389","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2964189064","https://openalex.org/W2981822321","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2988200020","https://openalex.org/W3007041883","https://openalex.org/W3007589762","https://openalex.org/W3013325675","https://openalex.org/W3015371781","https://openalex.org/W3017343282","https://openalex.org/W3095687795","https://openalex.org/W3098511564","https://openalex.org/W3100156920","https://openalex.org/W3105120247","https://openalex.org/W3107810305","https://openalex.org/W3118366136","https://openalex.org/W3136174377","https://openalex.org/W3144281354","https://openalex.org/W3157898411","https://openalex.org/W3168149265","https://openalex.org/W3170088426","https://openalex.org/W3172472082","https://openalex.org/W3175514052","https://openalex.org/W3177116139","https://openalex.org/W3178686235","https://openalex.org/W3206008172","https://openalex.org/W3214679265","https://openalex.org/W4226301259","https://openalex.org/W4226338831","https://openalex.org/W4281711933","https://openalex.org/W4287608901","https://openalex.org/W4307286264","https://openalex.org/W4312309344","https://openalex.org/W4312367758","https://openalex.org/W4312415534","https://openalex.org/W4312653918","https://openalex.org/W4312800393","https://openalex.org/W4312926266","https://openalex.org/W4319300051","https://openalex.org/W4386072368","https://openalex.org/W4386075780","https://openalex.org/W4386075783","https://openalex.org/W4387969641","https://openalex.org/W4390873486","https://openalex.org/W4390873759","https://openalex.org/W4393160296"],"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/W2393726419"],"abstract_inverted_index":{"Class-incremental":[0],"learning":[1,122],"poses":[2],"a":[3,79,88,98,105],"significant":[4],"challenge":[5],"under":[6],"an":[7,72,177],"exemplar-free":[8,73,178],"constraint,":[9],"leading":[10],"to":[11,113,120,170],"catastrophic":[12],"forgetting":[13],"and":[14,46,54,129,154,159,184],"sub-par":[15],"incremental":[16,192],"accuracy.":[17,193],"Previous":[18],"attempts":[19],"have":[20],"focused":[21],"primarily":[22],"on":[23,156],"single-modality":[24],"tasks,":[25],"such":[26],"as":[27],"image":[28],"classification":[29],"or":[30],"audio":[31,128],"event":[32],"classification.":[33],"However,":[34],"in":[35,132],"the":[36,43,66,94,116,149],"context":[37],"of":[38,48,151],"Audio-Visual":[39],"Class-Incremental":[40],"Learning":[41,69],"(AVCIL),":[42],"effective":[44],"integration":[45],"utilization":[47],"heterogeneous":[49],"modalities,":[50],"with":[51,137,148],"their":[52],"complementary":[53],"enhancing":[55],"characteristics,":[56],"remains":[57],"largely":[58],"unexplored.":[59],"To":[60,83],"bridge":[61],"this":[62],"gap,":[63],"we":[64],"propose":[65],"Multi-Modal":[67],"Analytic":[68],"(MMAL)":[70],"framework,":[71],"solution":[74],"for":[75,190],"AVCIL":[76,95,166],"that":[77,92,141],"employs":[78],"closed-form,":[80],"linear":[81],"approach.":[82],"be":[84],"specific,":[85],"MMAL":[86,144],"introduces":[87],"modality":[89,131],"fusion":[90],"module":[91,110],"re-formulates":[93],"problem":[96],"through":[97],"Recursive":[99],"Least-Square":[100],"(RLS)":[101],"perspective.":[102],"Complementing":[103],"this,":[104],"Modality-Specific":[106],"Knowledge":[107],"Compensation":[108],"(MSKC)":[109],"is":[111],"designed":[112],"further":[114],"alleviate":[115],"under-fitting":[117],"limitation":[118],"intrinsic":[119],"analytic":[121],"by":[123],"harnessing":[124],"individual":[125],"knowledge":[126],"from":[127],"visual":[130],"tandem.":[133],"Comprehensive":[134],"experimental":[135],"comparisons":[136],"existing":[138],"methods":[139],"show":[140],"our":[142,174],"proposed":[143],"demonstrates":[145],"superior":[146],"performance":[147],"accuracy":[150],"76.71%,":[152],"78.98%,":[153],"76.19%":[155],"AVE,":[157],"Kinetics-Sounds,":[158],"VGGSounds100":[160],"datasets,":[161],"respectively,":[162],"setting":[163],"new":[164],"state-of-the-art":[165],"performance.":[167],"Notably,":[168],"compared":[169],"those":[171],"memory-based":[172],"methods,":[173],"MMAL,":[175],"being":[176],"approach,":[179],"provides":[180],"good":[181],"data":[182],"privacy":[183],"can":[185],"better":[186],"leverage":[187],"multi-modal":[188],"information":[189],"improved":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}