{"id":"https://openalex.org/W3136482419","doi":"https://doi.org/10.1109/bigdata50022.2020.9377941","title":"Self-Supervised Audio-Visual Representation Learning for in-the-wild Videos","display_name":"Self-Supervised Audio-Visual Representation Learning for in-the-wild Videos","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3136482419","doi":"https://doi.org/10.1109/bigdata50022.2020.9377941","mag":"3136482419"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377941","doi":"https://doi.org/10.1109/bigdata50022.2020.9377941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377941","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"IEEE International Conference on Big Data (BigData)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5113182247","display_name":"Zishun Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zishun Feng","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334100","display_name":"Ming Tu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Tu","raw_affiliation_strings":["Bytedance Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640515","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-6899-6735","observed_orcids":["https://orcid.org/0000-0002-6899-6735","https://orcid.org/0000-0002-0621-1058"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui xia","raw_affiliation_strings":["Bytedance Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039091156","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-9153-3512","observed_orcids":["https://orcid.org/0000-0001-9153-3512","https://orcid.org/0009-0008-4674-4976","https://orcid.org/0009-0005-0354-0226"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Bytedance Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089183504","display_name":"Ashok Kumar Krishnamurthy","orcid":"https://orcid.org/0000-0002-3215-7622","observed_orcids":["https://orcid.org/0000-0002-3215-7622"]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I69048370","display_name":"Renaissance Computing Institute","ror":"https://ror.org/01s91ey96","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535","https://openalex.org/I170897317","https://openalex.org/I69048370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Krishnamurthy","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","Renaissance Computing Institute, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"Renaissance Computing Institute, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I69048370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0771,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39911168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7896000146865845,"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":0.7896000146865845,"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/T11309","display_name":"Music and Audio Processing","score":0.15629999339580536,"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/T12032","display_name":"Multisensory perception and integration","score":0.015300000086426735,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.9169999957084656},{"id":"https://openalex.org/keywords/audio-visual-representation-learning","display_name":"audio-visual representation learning","score":0.9340000152587891},{"id":"https://openalex.org/keywords/cross-modal-representation","display_name":"cross-modal representation","score":0.8090000152587891},{"id":"https://openalex.org/keywords/audio-visual-correspondence","display_name":"audio-visual correspondence","score":0.949999988079071},{"id":"https://openalex.org/keywords/in-the-wild-videos","display_name":"in-the-wild videos","score":0.9319999814033508},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"video retrieval","score":0.703000009059906},{"id":"https://openalex.org/keywords/audio-visual-retrieval","display_name":"audio-visual retrieval","score":0.49399998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010523319244385},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5798456072807312},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5530256032943726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5294649004936218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4293113648891449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4291737675666809},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30689412355422974},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377941","doi":"https://doi.org/10.1109/bigdata50022.2020.9377941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377941","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"IEEE International Conference on Big Data (BigData)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2619697695","https://openalex.org/W2963115079","https://openalex.org/W3015371781"],"related_works":["https://openalex.org/W4206677874","https://openalex.org/W4226383576","https://openalex.org/W4382318126","https://openalex.org/W3214261769","https://openalex.org/W4294690647","https://openalex.org/W3195486004","https://openalex.org/W2990408345","https://openalex.org/W3048939150","https://openalex.org/W4382237564","https://openalex.org/W3173388686"],"abstract_inverted_index":{"Humans":[0],"understand":[1],"videos":[2,29],"from":[3],"both":[4,41],"the":[5,11,31,34,47,56],"visual":[6],"and":[7,43,60],"audio":[8],"aspects":[9],"of":[10],"data.":[12],"In":[13],"this":[14],"work,":[15],"we":[16,37],"present":[17],"a":[18],"self-supervised":[19],"cross-modal":[20,42],"representation":[21],"approach":[22,62],"for":[23,28],"learning":[24,35],"audio-visual":[25],"correspondence":[26],"(AVC)":[27],"in":[30,40],"wild.":[32],"After":[33],"stage,":[36],"explore":[38],"retrieval":[39],"intra-modal":[44],"manner":[45],"with":[46],"learned":[48],"representations.":[49],"We":[50],"verify":[51],"our":[52,61],"experimental":[53],"results":[54],"on":[55],"VGGSound":[57],"dataset":[58],"[1],":[59],"achieves":[63],"promising":[64],"results.":[65]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2021-03-29T00:00:00"}