{"id":"https://openalex.org/W4387969238","doi":"https://doi.org/10.1145/3581783.3613805","title":"SCLAV: Supervised Cross-modal Contrastive Learning for Audio-Visual Coding","display_name":"SCLAV: Supervised Cross-modal Contrastive Learning for Audio-Visual Coding","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969238","doi":"https://doi.org/10.1145/3581783.3613805"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5101659046","display_name":"Chao Sun","orcid":"https://orcid.org/0000-0002-8735-4893"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Sun","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337209","display_name":"Min Chen","orcid":"https://orcid.org/0000-0002-0960-4447"},"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":"Min Chen","raw_affiliation_strings":["South China University of Technology & Pazhou Laboratory, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology & Pazhou Laboratory, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042903318","display_name":"Jialiang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialiang Cheng","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733756","display_name":"Han Liang","orcid":"https://orcid.org/0000-0001-8493-6495"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Liang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059375680","display_name":"Chuanbo Zhu","orcid":"https://orcid.org/0000-0002-6441-1162"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanbo Zhu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062659173","display_name":"Jincai Chen","orcid":"https://orcid.org/0000-0001-7368-1677"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincai Chen","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101659046"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.5843,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65879444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9803000092506409,"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/computer-science","display_name":"Computer science","score":0.8045896291732788},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.62788325548172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5806950330734253},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5795203447341919},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5551045536994934},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5406962633132935},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.47850552201271057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4543927311897278},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3940868675708771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35881567001342773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3554871082305908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045896291732788},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.62788325548172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806950330734253},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5795203447341919},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5551045536994934},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5406962633132935},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.47850552201271057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4543927311897278},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3940868675708771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35881567001342773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3554871082305908},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1608827994","display_name":null,"funder_award_id":"62272178","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7947095792","display_name":null,"funder_award_id":"62272178, and 62276109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8383532844","display_name":null,"funder_award_id":"62276109","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2558333741","https://openalex.org/W2619697695","https://openalex.org/W2798991696","https://openalex.org/W2885201931","https://openalex.org/W2931433835","https://openalex.org/W2963524571","https://openalex.org/W2963795951","https://openalex.org/W2964109005","https://openalex.org/W2990113535","https://openalex.org/W2990408345","https://openalex.org/W2997909293","https://openalex.org/W2998388430","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3035118106","https://openalex.org/W3035524453","https://openalex.org/W3037309139","https://openalex.org/W3041053424","https://openalex.org/W3093287838","https://openalex.org/W3094454579","https://openalex.org/W3094468028","https://openalex.org/W3108655343","https://openalex.org/W3134566480","https://openalex.org/W3136793533","https://openalex.org/W3153167542","https://openalex.org/W3154596443","https://openalex.org/W3158986867","https://openalex.org/W3160045550","https://openalex.org/W3175300676","https://openalex.org/W3175514052","https://openalex.org/W3176445421","https://openalex.org/W3190580390","https://openalex.org/W4226025707","https://openalex.org/W4283811196","https://openalex.org/W4285483408","https://openalex.org/W4288054834","https://openalex.org/W4304098292","https://openalex.org/W4312415534","https://openalex.org/W4312753781","https://openalex.org/W6783802886"],"related_works":["https://openalex.org/W2895918973","https://openalex.org/W4285815173","https://openalex.org/W2946165673","https://openalex.org/W4312851439","https://openalex.org/W4376653966","https://openalex.org/W2291115585","https://openalex.org/W4307474775","https://openalex.org/W4321022102","https://openalex.org/W4385573445","https://openalex.org/W3085156009"],"abstract_inverted_index":{"Audio":[0],"and":[1,9,65,104,113,133,140,158],"vision":[2,134],"are":[3,26,59],"important":[4],"senses":[5],"for":[6,86,116],"high-level":[7],"cognition,":[8],"their":[10,51],"special":[11],"strong":[12],"correlation":[13],"makes":[14],"audio-visual":[15,30,94],"coding":[16,95],"a":[17,80,122],"crucial":[18],"factor":[19],"in":[20,29],"many":[21],"multimodal":[22,36,111,145],"tasks.":[23],"However,":[24],"there":[25],"two":[27],"challenges":[28],"coding.":[31],"First,":[32],"the":[33,46,66,129,137,149,156,165],"heterogeneity":[34],"of":[35,42,98,136,144],"data":[37,146],"often":[38],"leads":[39],"to":[40,127,147],"misalignment":[41],"cross-modal":[43,124],"features":[44,135],"under":[45],"same":[47,138],"sample,":[48],"which":[49,109],"reduces":[50],"representation":[52],"quality.":[53],"Second,":[54],"most":[55],"self-supervised":[56],"learning":[57],"frameworks":[58],"constructed":[60],"based":[61],"on":[62,155],"instance":[63],"semantics,":[64],"generated":[67],"pseudo":[68],"labels":[69,143],"introduce":[70,121],"additional":[71],"classification":[72,151],"noise.":[73,152],"To":[74],"address":[75],"these":[76],"challenges,":[77],"we":[78,120],"propose":[79],"Supervised":[81],"Cross-modal":[82],"Contrastive":[83],"Learning":[84],"Framework":[85],"Audio-Visual":[87],"Coding":[88],"(SCLAV).":[89],"Our":[90],"framework":[91],"includes":[92],"an":[93,99,105],"network":[96],"composed":[97],"inter-modal":[100],"attention":[101],"interaction":[102],"module":[103],"intra-modal":[106],"self-integration":[107],"module,":[108],"leverage":[110],"complementary":[112],"hidden":[114],"information":[115],"better":[117],"representation.":[118],"Additionally,":[119],"supervised":[123],"contrastive":[125],"loss":[126],"minimize":[128],"distance":[130],"between":[131],"audio":[132],"instance,":[139],"use":[141],"weak":[142],"eliminate":[148],"feature-oriented":[150],"Extensive":[153],"experiments":[154],"AVE":[157],"XD-Violence":[159],"datasets":[160],"demonstrate":[161],"that":[162],"SCLAV":[163],"outperforms":[164],"state-of-the-art":[166],"results,":[167],"even":[168],"with":[169],"limited":[170],"computational":[171],"resources.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}