{"id":"https://openalex.org/W7128526745","doi":"https://doi.org/10.1109/tcsvt.2026.3662386","title":"AVQACL++: Toward a Robust Framework and Benchmark for Audio-Visual Question Answering Continual Learning","display_name":"AVQACL++: Toward a Robust Framework and Benchmark for Audio-Visual Question Answering Continual Learning","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128526745","doi":"https://doi.org/10.1109/tcsvt.2026.3662386"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3662386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662386","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Kaixuan Wu","orcid":"https://orcid.org/0009-0006-5132-9502"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Wu","raw_affiliation_strings":["Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-5132-9502","affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinde Li","orcid":"https://orcid.org/0000-0002-1529-4537"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinde Li","raw_affiliation_strings":["Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1529-4537","affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000882722","display_name":"X. Z. Li","orcid":"https://orcid.org/0009-0009-1594-6361"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglin Li","raw_affiliation_strings":["Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125482503","display_name":"Kezhu Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kezhu Zuo","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9426-1599","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125584466","display_name":"Zhiwei Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Lv","raw_affiliation_strings":["Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95891875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"6","first_page":"8232","last_page":"8245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9807000160217285,"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":0.9807000160217285,"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":0.009100000374019146,"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/T10028","display_name":"Topic Modeling","score":0.000699999975040555,"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/question-answering","display_name":"Question answering","score":0.6284000277519226},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6071000099182129},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.5259000062942505},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4893999993801117},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4603999853134155},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45910000801086426},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.387800008058548},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.359499990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715399980545044},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5726000070571899},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3061000108718872},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3662386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3662386","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6149225315","display_name":null,"funder_award_id":"U25A20477","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8035212347","display_name":null,"funder_award_id":"62233003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2593116425","https://openalex.org/W2896457183","https://openalex.org/W2963588172","https://openalex.org/W2964189064","https://openalex.org/W2964213933","https://openalex.org/W2972313371","https://openalex.org/W2973131617","https://openalex.org/W2996320484","https://openalex.org/W3007041883","https://openalex.org/W3013325675","https://openalex.org/W3044495139","https://openalex.org/W3107810305","https://openalex.org/W3116298410","https://openalex.org/W3180392831","https://openalex.org/W4214524539","https://openalex.org/W4214604251","https://openalex.org/W4214924370","https://openalex.org/W4304084136","https://openalex.org/W4304098310","https://openalex.org/W4312380001","https://openalex.org/W4312780067","https://openalex.org/W4312849014","https://openalex.org/W4362653417","https://openalex.org/W4382202615","https://openalex.org/W4386065591","https://openalex.org/W4386075840","https://openalex.org/W4387247768","https://openalex.org/W4388192054","https://openalex.org/W4389164266","https://openalex.org/W4390873486","https://openalex.org/W4390873759","https://openalex.org/W4392796474","https://openalex.org/W4393154284","https://openalex.org/W4394744883","https://openalex.org/W4399880765","https://openalex.org/W4401806093","https://openalex.org/W4402754307","https://openalex.org/W4402912714","https://openalex.org/W4403183280","https://openalex.org/W4403730139","https://openalex.org/W4403780004","https://openalex.org/W4403791445","https://openalex.org/W4404562858","https://openalex.org/W4409250956","https://openalex.org/W4409367415","https://openalex.org/W4409985187","https://openalex.org/W4410614351","https://openalex.org/W4413146928","https://openalex.org/W4413394426","https://openalex.org/W7133196460","https://openalex.org/W7133238718"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,74,83,146],"unified":[4],"framework":[5],"for":[6],"continual":[7,75],"learning":[8,32,66],"in":[9,23,73,192],"Audio-Visual":[10],"Question":[11,127],"Answering":[12],"(AVQACL),":[13],"designed":[14],"to":[15,137,167],"enhance":[16],"fine-grained":[17],"scene":[18],"understanding":[19],"and":[20,41,62,70,120,155,162,173,197],"spatio-temporal":[21],"reasoning":[22,122],"dynamic":[24],"multimodal":[25,101],"task":[26],"environments.":[27],"To":[28,77],"simulate":[29],"realistic":[30],"incremental":[31],"scenarios,":[33],"we":[34,81],"construct":[35],"two":[36],"large-scale":[37],"benchmark":[38],"datasets,":[39],"Split-AVQA":[40],"Split-MUSIC-AVQA,":[42],"by":[43],"reorganizing":[44],"existing":[45],"AVQA":[46],"corpora":[47],"into":[48],"sequential":[49],"tasks.":[50],"Empirical":[51],"results":[52],"show":[53],"that":[54,86,150,183],"conventional":[55],"models":[56],"suffer":[57],"from":[58],"severe":[59],"performance":[60],"degradation":[61],"catastrophic":[63],"forgetting":[64],"when":[65],"across":[67,124],"audio,":[68],"visual,":[69],"textual":[71],"modalities":[72],"setup.":[76],"address":[78],"these":[79],"challenges,":[80],"propose":[82],"novel":[84],"approach":[85],"integrates":[87],"four":[88],"key":[89],"modules:":[90],"(1)":[91],"Question-Guided":[92],"Cross-modal":[93],"Information":[94],"Fusion":[95],"(QCIF),":[96],"which":[97,115,132],"dynamically":[98],"extracts":[99],"task-relevant":[100],"features":[102],"via":[103],"question-aware":[104],"attention;":[105],"(2)":[106],"Task-specific":[107],"Knowledge":[108],"Distillation":[109],"with":[110],"Spatial-Temporal":[111],"Feature":[112],"Constraints":[113],"(TKD-STFC),":[114],"preserves":[116],"semantic":[117],"output":[118],"behavior":[119],"internal":[121],"trajectories":[123],"tasks;":[125],"(3)":[126],"Semantic":[128],"Consistency":[129],"Constraint":[130],"(QSCC),":[131],"regularizes":[133],"evolving":[134],"question":[135],"representations":[136],"maintain":[138],"linguistic":[139],"stability.":[140],"(4)":[141],"Dual-Strategy":[142],"Exemplar":[143],"Selection":[144],"(DSES),":[145],"memory-efficient":[147],"replay":[148],"strategy":[149],"jointly":[151],"maximizes":[152],"sample":[153],"informativeness":[154],"diversity.":[156],"All":[157],"components":[158],"are":[159],"theoretically":[160],"grounded,":[161],"formal":[163],"analysis":[164],"is":[165],"provided":[166],"ensure":[168],"modality":[169],"alignment,":[170],"spatial-temporal":[171],"coherence,":[172],"exemplar":[174],"selection":[175],"reliability.":[176],"Extensive":[177],"experiments":[178],"on":[179],"both":[180],"datasets":[181],"demonstrate":[182],"our":[184],"method":[185],"consistently":[186],"outperforms":[187],"prior":[188],"state-of-the-art":[189],"AVQACL":[190],"baselines":[191],"terms":[193],"of":[194],"accuracy,":[195],"retention,":[196],"robustness.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2026-02-11T00:00:00"}