{"id":"https://openalex.org/W7138033248","doi":"https://doi.org/10.1609/aaai.v40i4.37273","title":"Vision-language Incremental Learning with Dual Class-individual Memory","display_name":"Vision-language Incremental Learning with Dual Class-individual Memory","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138033248","doi":"https://doi.org/10.1609/aaai.v40i4.37273"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i4.37273","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37273","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i4.37273","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129739836","display_name":"Fuhai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuhai Chen","raw_affiliation_strings":["Fuzhou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou University","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738303","display_name":"Feng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Fuzhou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou University","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718044","display_name":"Xiaoguang Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"XiaoGuang Ma","raw_affiliation_strings":["Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693319","display_name":"Yiyi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662121","display_name":"Jiarong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarong Liu","raw_affiliation_strings":["Fuzhou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou University","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129672262","display_name":"Xuri Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuri Ge","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]}],"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":"40","issue":"4","first_page":"2832","last_page":"2840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.642300009727478,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.642300009727478,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.32659998536109924,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0044999998062849045,"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/closed-captioning","display_name":"Closed captioning","score":0.8052999973297119},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7652999758720398},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5127000212669373},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.429500013589859},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.39169999957084656},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37400001287460327},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8052999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736999988555908},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7652999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5918999910354614},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3504999876022339},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i4.37273","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37273","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37273","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37273","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37273","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,157,185],"multimodal":[3],"technologies":[4],"has":[5],"propelled":[6],"Vision-Language":[7],"Incremental":[8],"Learning":[9],"(VLIL)":[10],"into":[11],"a":[12,93],"research":[13],"spotlight.":[14],"Current":[15],"VLIL":[16],"approaches":[17],"predominantly":[18],"inherit":[19],"unimodal":[20],"paradigms,":[21],"failing":[22],"to":[23,124,152],"address":[24],"fundamental":[25],"distinctions":[26],"between":[27,36],"visual":[28,44,170],"and":[29,38,55,79,126,155,174,181],"linguistic":[30],"modalities.":[31],"Crucially,":[32],"the":[33,128,140,179],"semantic":[34],"gap":[35],"images":[37,66],"text":[39],"creates":[40],"divergent":[41],"learning":[42,193],"dynamics:":[43],"data":[45],"exhibits":[46],"rich,":[47],"distributed":[48],"information":[49],"while":[50],"textual":[51,58],"representations":[52],"remain":[53],"explicit":[54],"compact.":[56],"Consequently,":[57],"elements":[59],"align":[60],"with":[61],"class-specific":[62],"tasks,":[63,71,168],"whereas":[64],"individual":[65],"inherently":[67],"span":[68],"multiple":[69],"such":[70],"creating":[72],"dual":[73],"bottlenecks":[74],"in":[75],"class-level":[76,104],"memory":[77,115],"allocation":[78],"scene-level":[80,138],"knowledge":[81,135],"transfer.":[82],"To":[83],"overcome":[84],"these":[85],"challenges,":[86],"we":[87],"propose":[88],"DCIM":[89],"(Dual":[90],"Class-Individual":[91],"Memory),":[92],"novel":[94,153],"framework":[95],"featuring":[96],"complementary":[97],"mechanisms":[98],"for":[99],"vision-language":[100,167],"continual":[101,192],"learning.":[102],"For":[103,137],"constraints,":[105],"our":[106,186],"Hierarchical":[107],"Class":[108],"Memory":[109],"Management":[110],"(HCMM)":[111],"strategy":[112],"dynamically":[113],"allocates":[114],"resources":[116],"across":[117],"object":[118],"categories.":[119],"It":[120],"employs":[121],"forgetting":[122],"simulation":[123],"identify":[125],"preserve":[127],"most":[129],"vulnerable":[130],"samples,":[131],"ensuring":[132],"robust":[133],"long-term":[134],"retention.":[136],"adaptation,":[139],"Scene":[141],"Reconstruction":[142],"Memory(SRM)":[143],"module":[144],"captures":[145],"generalized":[146],"environmental":[147],"representations,":[148],"enabling":[149],"contextual":[150],"transfer":[151],"classes":[154],"disambiguation":[156],"semantically":[158],"related":[159],"concepts":[160],"within":[161],"shared":[162],"scenes.Extensive":[163],"experiments":[164],"on":[165],"two":[166],"i.e.,":[169],"question":[171],"answering":[172],"(VQA)":[173],"Image":[175],"captioning":[176],"(IC),":[177],"demonstrate":[178],"effectiveness":[180],"excellent":[182],"generalization":[183],"ability":[184],"approach,":[187],"achieving":[188],"superior":[189],"performance":[190],"under":[191],"settings.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
