{"id":"https://openalex.org/W4411270826","doi":"https://doi.org/10.1109/tcsvt.2025.3579549","title":"Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation","display_name":"Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation","publication_year":2025,"publication_date":"2025-06-13","ids":{"openalex":"https://openalex.org/W4411270826","doi":"https://doi.org/10.1109/tcsvt.2025.3579549"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3579549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3579549","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":"https://openalex.org/A5018498977","display_name":"Runhao Zeng","orcid":"https://orcid.org/0000-0001-8694-4245"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Runhao Zeng","raw_affiliation_strings":["Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China","Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8694-4245","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China","institution_ids":["https://openalex.org/I4388482657"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101447665","display_name":"Qi Deng","orcid":"https://orcid.org/0009-0004-7475-0127"},"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":"Qi Deng","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086603059","display_name":"Ronghao Zhang","orcid":null},"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":"Ronghao Zhang","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064880801","display_name":"Shuaicheng Niu","orcid":"https://orcid.org/0000-0001-8212-1831"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuaicheng Niu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore","College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326501","display_name":"Jian Chen","orcid":"https://orcid.org/0000-0003-4769-1526"},"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":"Jian Chen","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4769-1526","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007941489","display_name":"Xiping Hu","orcid":"https://orcid.org/0000-0002-4952-699X"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Xiping Hu","raw_affiliation_strings":["Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China","Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4952-699X","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China","institution_ids":["https://openalex.org/I4388482657"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035919267","display_name":"Victor C. M. Leung","orcid":"https://orcid.org/0000-0003-3529-2640"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Victor C. M. Leung","raw_affiliation_strings":["Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China","Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3529-2640","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University, Shenzhen, China","institution_ids":["https://openalex.org/I4388482657"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University and Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71000539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"12","first_page":"12292","last_page":"12305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9905999898910522,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9905999898910522,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9799000024795532,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.960099995136261,"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/computer-science","display_name":"Computer science","score":0.7761132717132568},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.57218337059021},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47256794571876526},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4685583710670471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4556789994239807},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4116699695587158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38405001163482666},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3594076335430145},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2846187353134155},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.15507882833480835},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09906762838363647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761132717132568},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.57218337059021},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47256794571876526},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4685583710670471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4556789994239807},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4116699695587158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38405001163482666},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3594076335430145},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2846187353134155},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.15507882833480835},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09906762838363647},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3579549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3579549","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/217698","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/217698","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4860469773","display_name":null,"funder_award_id":"62202311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6320596113","display_name":null,"funder_award_id":"2024A1515010989","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G657063301","display_name":null,"funder_award_id":"2023A1515011512","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8216305697","display_name":null,"funder_award_id":"62376099","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"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2551491964","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2896457183","https://openalex.org/W2964109005","https://openalex.org/W2971680695","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3035333188","https://openalex.org/W3168126734","https://openalex.org/W3168565360","https://openalex.org/W3194397797","https://openalex.org/W3196974791","https://openalex.org/W3206366488","https://openalex.org/W3206570195","https://openalex.org/W3215113235","https://openalex.org/W4214727094","https://openalex.org/W4297697565","https://openalex.org/W4312263092","https://openalex.org/W4312276384","https://openalex.org/W4312960652","https://openalex.org/W4313025443","https://openalex.org/W4379984311","https://openalex.org/W4385245566","https://openalex.org/W4386075698","https://openalex.org/W4386083076","https://openalex.org/W4387968053","https://openalex.org/W4389065381","https://openalex.org/W4391216149","https://openalex.org/W4394625772","https://openalex.org/W4399451175","https://openalex.org/W4399526356","https://openalex.org/W4402727889","https://openalex.org/W4403511013","https://openalex.org/W4403758862","https://openalex.org/W4406983084","https://openalex.org/W4409366805"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1526712007","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W4250131624"],"abstract_inverted_index":{"Test-time":[0],"adaptation":[1,138,146,165,207],"(TTA)":[2],"aims":[3],"to":[4,69,96,109],"boost":[5],"the":[6,18,36,63,77,106,122,131,142,198],"generalization":[7],"capability":[8],"of":[9,39,67,79,145,200],"a":[10,49,73,119,136,163,216],"trained":[11],"model":[12],"by":[13,90],"conducting":[14],"self-/unsupervised":[15],"learning":[16],"during":[17],"testing":[19],"phase.":[20],"While":[21],"most":[22],"existing":[23],"TTA":[24,188],"methods":[25],"for":[26,148,167],"video":[27,57,80,110,126,211,225],"primarily":[28],"utilize":[29],"visual":[30],"supervisory":[31],"signals,":[32],"they":[33],"often":[34],"overlook":[35],"potential":[37],"contribution":[38],"inherent":[40],"audio":[41,54,68,94,98,123,222],"data.":[42],"To":[43,128],"address":[44],"this":[45],"gap,":[46],"we":[47,83,134],"propose":[48,84],"novel":[50],"approach":[51],"that":[52,140],"incorporates":[53],"information":[55,223],"into":[56,224],"TTA.":[58,81,226],"Our":[59,203],"method":[60,89,204],"capitalizes":[61],"on":[62,152,172,183],"rich":[64],"semantic":[65],"content":[66],"generate":[70],"audio-assisted":[71],"pseudo-labels,":[72,133],"new":[74],"concept":[75],"in":[76,154,220],"context":[78],"Specifically,":[82],"an":[85],"audio-to-video":[86],"label":[87,111],"mapping":[88,105],"first":[91],"employing":[92],"pre-trained":[93],"models":[95,213],"classify":[97],"signals":[99],"extracted":[100],"from":[101],"videos":[102],"and":[103,125,156,178,191,214,229],"then":[104],"audio-based":[107],"predictions":[108],"spaces":[112],"through":[113],"large":[114],"language":[115],"models,":[116],"thereby":[117],"establishing":[118],"connection":[120],"between":[121],"categories":[124],"labels.":[127],"effectively":[129],"leverage":[130],"generated":[132],"present":[135],"flexible":[137],"cycle":[139],"determines":[141],"optimal":[143],"number":[144],"iterations":[147],"each":[149,168],"sample,":[150],"based":[151],"changes":[153],"loss":[155],"consistency":[157],"across":[158,209],"different":[159,210],"views.":[160],"This":[161],"enables":[162],"customized":[164],"process":[166],"sample.":[169],"Experimental":[170],"results":[171],"two":[173,184],"widely":[174],"used":[175],"datasets":[176,189,230],"(UCF101-C":[177],"Kinetics-Sounds-C),":[179],"as":[180,182],"well":[181],"newly":[185],"constructed":[186],"audio-video":[187],"(AVE-C":[190],"AVMIT-C)":[192],"with":[193],"various":[194],"corruption":[195],"types,":[196],"demonstrate":[197],"superiority":[199],"our":[201],"approach.":[202],"consistently":[205],"improves":[206],"performance":[208],"classification":[212],"represents":[215],"significant":[217],"step":[218],"forward":[219],"integrating":[221],"The":[227],"code":[228],"will":[231],"be":[232],"made":[233],"publicly":[234],"available.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}