{"id":"https://openalex.org/W4415400938","doi":"https://doi.org/10.1145/3746266.3762161","title":"Mamba-Based Multimodal Continual Learning for Audio-Visual Classification with Prototype-Enhanced Anti-Forgetting Mechanism","display_name":"Mamba-Based Multimodal Continual Learning for Audio-Visual Classification with Prototype-Enhanced Anti-Forgetting Mechanism","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415400938","doi":"https://doi.org/10.1145/3746266.3762161"},"language":null,"primary_location":{"id":"doi:10.1145/3746266.3762161","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746266.3762161","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746266.3762161","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114148193","display_name":"Jingyang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyang Lin","raw_affiliation_strings":["School of Computer and Computing Science, Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-0100-018X","affiliations":[{"raw_affiliation_string":"School of Computer and Computing Science, Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinru Ying","orcid":"https://orcid.org/0009-0007-4831-9220"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinru Ying","raw_affiliation_strings":["School of Computer and Computing Science, Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4831-9220","affiliations":[{"raw_affiliation_string":"School of Computer and Computing Science, Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113708851","display_name":"Mo Jia-Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Mo","raw_affiliation_strings":["College of Letters & Science, University of Wisconsin\u2013Madison, Madison, WI, USA"],"raw_orcid":"https://orcid.org/0009-0004-2728-1751","affiliations":[{"raw_affiliation_string":"College of Letters & Science, University of Wisconsin\u2013Madison, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087178581","display_name":"Wei Li-na","orcid":"https://orcid.org/0009-0004-0077-2905"},"institutions":[{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Wei","raw_affiliation_strings":["Hangzhou City University, Hangzhou, China and Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-0077-2905","affiliations":[{"raw_affiliation_string":"Hangzhou City University, Hangzhou, China and Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, Hangzhou, China","institution_ids":["https://openalex.org/I4210114441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391381","display_name":"Fangfang Wang","orcid":"https://orcid.org/0000-0002-7685-5705"},"institutions":[{"id":"https://openalex.org/I163151501","display_name":"Hangzhou Normal University","ror":"https://ror.org/014v1mr15","country_code":"CN","type":"education","lineage":["https://openalex.org/I163151501"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Wang","raw_affiliation_strings":["School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7685-5705","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China","institution_ids":["https://openalex.org/I163151501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037349726","display_name":"Canghong Jin","orcid":"https://orcid.org/0000-0002-9774-9688"},"institutions":[{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Canghong Jin","raw_affiliation_strings":["Hangzhou City University, Hangzhou, China and Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9774-9688","affiliations":[{"raw_affiliation_string":"Hangzhou City University, Hangzhou, China and Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, Hangzhou, China","institution_ids":["https://openalex.org/I4210114441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000082590","display_name":"Guanlin Chen","orcid":"https://orcid.org/0000-0002-4255-658X"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanlin Chen","raw_affiliation_strings":["School of Computer and Computing Science, Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4255-658X","affiliations":[{"raw_affiliation_string":"School of Computer and Computing Science, Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I4400573310"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9954000115394592,"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/T11309","display_name":"Music and Audio Processing","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6317999958992004},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6154999732971191},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5070000290870667},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4763000011444092},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3635999858379364},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.35830000042915344},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3375999927520752},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.33550000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777899980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7013999819755554},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6317999958992004},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5401999950408936},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4763000011444092},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746266.3762161","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746266.3762161","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746266.3762161","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746266.3762161","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2619697695","https://openalex.org/W2962865004","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2964189064","https://openalex.org/W2990113535","https://openalex.org/W3015371781","https://openalex.org/W3107810305","https://openalex.org/W3163939464","https://openalex.org/W4214924370","https://openalex.org/W4312309344","https://openalex.org/W4312415534","https://openalex.org/W4386065620","https://openalex.org/W4386071707","https://openalex.org/W4389600552","https://openalex.org/W4390754261","https://openalex.org/W4390872637","https://openalex.org/W4390873759","https://openalex.org/W4392492373","https://openalex.org/W4402702936"],"related_works":[],"abstract_inverted_index":{"Class-incremental":[0],"learning":[1,205],"commonly":[2],"encounters":[3],"the":[4,56,189],"issue":[5],"of":[6],"catastrophic":[7,40],"forgetting":[8,41],"when":[9],"adapting":[10],"to":[11,38,60,76,167],"new":[12,139],"classes,":[13],"a":[14,29,71,113],"problem":[15],"that":[16,50,164],"is":[17,68],"especially":[18],"severe":[19],"in":[20,42,202],"multimodal":[21,44,203],"settings.":[22],"To":[23],"tackle":[24],"this":[25],"challenge,":[26],"we":[27,54],"propose":[28],"novel":[30],"framework":[31,83],"based":[32],"on":[33,52,160],"State":[34],"Space":[35],"Models":[36],"(SSMs)":[37],"alleviate":[39],"audio-visual":[43,63,90,104,161],"incremental":[45,204],"learning.":[46],"Unlike":[47],"conventional":[48],"approaches":[49],"rely":[51],"Transformers,":[53],"employ":[55],"efficient":[57],"Mamba":[58],"architecture":[59],"design":[61],"an":[62],"attention":[64,105,116],"alignment":[65,106],"mechanism,":[66,172],"which":[67],"integrated":[69],"with":[70,127],"class":[72,129,143,149,190,209],"prototype-enhanced":[73],"classification":[74,125,200],"strategy":[75,193],"preserve":[77],"cross-modal":[78,109],"semantic":[79,210],"relationships.":[80],"The":[81],"proposed":[82],"comprises":[84],"four":[85],"key":[86],"components:":[87],"(1)":[88],"Mamba-based":[89],"feature":[91,110,155],"encoders:":[92],"efficiently":[93,183],"extract":[94],"spatiotemporal":[95],"features":[96],"from":[97],"both":[98],"audio":[99,178],"and":[100,138,154,179,198],"visual":[101,180],"modalities;":[102],"(2)":[103],"module:":[107],"enables":[108],"fusion":[111],"through":[112,151],"dual":[114],"spatial-temporal":[115],"mechanism;":[117],"(3)":[118],"PrototypeCILClassifier:":[119],"makes":[120],"predictions":[121],"by":[122,207],"combining":[123],"linear":[124],"weights":[126],"normalized":[128],"prototypes,":[130],"thereby":[131],"effectively":[132],"reducing":[133],"prediction":[134],"bias":[135],"between":[136],"old":[137],"classes;":[140],"(4)":[141],"dynamic":[142],"prototype":[144,191],"update":[145],"mechanism:":[146],"maintains":[147],"high-quality":[148],"representations":[150],"momentum":[152],"updates":[153],"standardization":[156],"strategies.":[157],"Extensive":[158],"experiments":[159],"datasets":[162],"show":[163],"Mamba,":[165],"due":[166],"its":[168],"selective":[169],"state":[170],"retention":[171],"can":[173],"model":[174],"temporal":[175],"dependencies":[176],"across":[177],"modalities":[181],"more":[182],"than":[184],"traditional":[185],"attention-based":[186],"methods.":[187],"Furthermore,":[188],"enhancement":[192],"demonstrates":[194],"notable":[195],"computational":[196],"efficiency":[197],"superior":[199],"performance":[201],"scenarios":[206],"stabilizing":[208],"centers.":[211]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-22T00:00:00"}