{"id":"https://openalex.org/W4391594029","doi":"https://doi.org/10.1109/tpami.2024.3363508","title":"Robust Audio-Visual Contrastive Learning for Proposal-Based Self-Supervised Sound Source Localization in Videos","display_name":"Robust Audio-Visual Contrastive Learning for Proposal-Based Self-Supervised Sound Source Localization in Videos","publication_year":2024,"publication_date":"2024-02-07","ids":{"openalex":"https://openalex.org/W4391594029","doi":"https://doi.org/10.1109/tpami.2024.3363508","pmid":"https://pubmed.ncbi.nlm.nih.gov/38324443"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3363508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3363508","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5011876855","display_name":"Hanyu Xuan","orcid":"https://orcid.org/0000-0002-4633-2794"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyu Xuan","raw_affiliation_strings":["School of Big Data and Statistics, Anhui University, Heifei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-4633-2794","affiliations":[{"raw_affiliation_string":"School of Big Data and Statistics, Anhui University, Heifei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001023262","display_name":"Zhiliang Wu","orcid":"https://orcid.org/0000-0002-6597-8048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiliang Wu","raw_affiliation_strings":["CCAI, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-6597-8048","affiliations":[{"raw_affiliation_string":"CCAI, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-4800-832X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053609164","display_name":"Bo Jiang","orcid":"https://orcid.org/0000-0002-6238-1596"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Heifei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-1596","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Heifei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Luo","orcid":"https://orcid.org/0000-0002-7618-119X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Luo","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-7618-119X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA, University Grenoble Alpes, Grenoble, France","INRIA and University Grenoble Alpes, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-5354-1084","affiliations":[{"raw_affiliation_string":"INRIA, University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I899635006"]},{"raw_affiliation_string":"INRIA and University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-9976-0442"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-9976-0442","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9375,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85948718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"46","issue":"7","first_page":"4896","last_page":"4907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7558740973472595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6361178159713745},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5734980702400208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5662537217140198},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5641650557518005},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5064388513565063},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45001593232154846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38060179352760315},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2273487150669098},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09822112321853638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558740973472595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6361178159713745},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5734980702400208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5662537217140198},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5641650557518005},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5064388513565063},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45001593232154846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38060179352760315},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2273487150669098},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09822112321853638},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3363508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3363508","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38324443","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38324443","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4302041946","display_name":null,"funder_award_id":"62302006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8579109809","display_name":null,"funder_award_id":"2308085QF221","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G8715681119","display_name":null,"funder_award_id":"62276135","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/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1536680647","https://openalex.org/W2065274193","https://openalex.org/W2088049833","https://openalex.org/W2103104224","https://openalex.org/W2105582566","https://openalex.org/W2109255472","https://openalex.org/W2127608660","https://openalex.org/W2133324800","https://openalex.org/W2166563626","https://openalex.org/W2526050071","https://openalex.org/W2601113512","https://openalex.org/W2604260814","https://openalex.org/W2606831796","https://openalex.org/W2619697695","https://openalex.org/W2798991696","https://openalex.org/W2813911573","https://openalex.org/W2917551568","https://openalex.org/W2926593466","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963150697","https://openalex.org/W2963680395","https://openalex.org/W2963697527","https://openalex.org/W2963952323","https://openalex.org/W2964109005","https://openalex.org/W2964328846","https://openalex.org/W2966917182","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2991533779","https://openalex.org/W2997909293","https://openalex.org/W3003293188","https://openalex.org/W3015371781","https://openalex.org/W3034974675","https://openalex.org/W3035395201","https://openalex.org/W3035524453","https://openalex.org/W3035725276","https://openalex.org/W3035725370","https://openalex.org/W3042057498","https://openalex.org/W3046582853","https://openalex.org/W3114065519","https://openalex.org/W3114632476","https://openalex.org/W3170088426","https://openalex.org/W3171007011","https://openalex.org/W3175300676","https://openalex.org/W3190580390","https://openalex.org/W4200436929","https://openalex.org/W4212847156","https://openalex.org/W4224925617","https://openalex.org/W4226314236","https://openalex.org/W4283709432","https://openalex.org/W4285606400","https://openalex.org/W4312653918","https://openalex.org/W4312926266","https://openalex.org/W4319299730","https://openalex.org/W4319300806","https://openalex.org/W4320002812","https://openalex.org/W4394625773","https://openalex.org/W6637373629","https://openalex.org/W6682948231","https://openalex.org/W6729831399","https://openalex.org/W6754048563","https://openalex.org/W6755987414","https://openalex.org/W6776700526","https://openalex.org/W6783539077","https://openalex.org/W6789528441","https://openalex.org/W6809915981","https://openalex.org/W6843326755"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"By":[0],"observing":[1],"a":[2,60,73,78,146,164,198,205,217,235],"scene":[3],"and":[4,62,129,249],"listening":[5],"to":[6,36,86,91,192,197,242,263],"corresponding":[7,196],"audio":[8,128],"cues,":[9],"humans":[10],"can":[11,109,213],"easily":[12],"recognize":[13],"where":[14],"the":[15,30,38,66,84,88,94,102,114,124,127,141,171,226,244],"sound":[16,39,67,174],"is.":[17],"To":[18,224],"achieve":[19,257],"such":[20],"cross-modal":[21],"perception":[22],"on":[23,123,266],"machines,":[24],"existing":[25],"methods":[26,57,71],"take":[27],"advantage":[28],"of":[29,65,97,104,149,201,228],"maps":[31],"obtained":[32],"by":[33,118],"interpolation":[34],"operations":[35],"localize":[37],"source.":[40,68],"As":[41,204],"semantic":[42,172],"object-level":[43,173],"localization":[44],"is":[45,121,157,185],"more":[46],"attractive":[47],"for":[48,252],"prospective":[49],"practical":[50],"applications,":[51],"we":[52,152,162,233],"argue":[53],"that":[54,126,154,168],"these":[55,70],"map-based":[56],"only":[58],"offer":[59],"coarse-grained":[61],"indirect":[63],"description":[64],"Additionally,":[69],"utilize":[72],"single":[74],"audio-visual":[75,99],"tuple":[76],"at":[77],"time":[79],"during":[80],"self-supervised":[81],"learning,":[82],"causing":[83],"model":[85],"lose":[87],"crucial":[89],"chance":[90],"reason":[92],"about":[93],"data":[95],"distribution":[96],"large-scale":[98],"samples.":[100],"Although":[101],"introduction":[103],"Audio-Visual":[105],"Contrastive":[106,238],"Learning":[107,221],"(AVCL)":[108],"effectively":[110],"alleviate":[111],"this":[112,155,160],"issue,":[113],"contrastive":[115,143,245],"set":[116,144],"constructed":[117],"randomly":[119],"sampling":[120,230],"based":[122],"assumption":[125,156],"visual":[130],"segments":[131],"from":[132],"all":[133],"other":[134],"videos":[135],"are":[136],"not":[137],"semantically":[138],"related.":[139],"Since":[140],"resulting":[142],"contains":[145],"large":[147,199],"number":[148,200],"faulty":[150],"negatives,":[151],"believe":[153],"rough.":[158],"In":[159],"paper,":[161],"advocate":[163],"novel":[165,236],"proposal-based":[166,208],"solution":[167],"directly":[169],"localizes":[170],"source,":[175],"without":[176],"any":[177],"manual":[178],"annotations.":[179],"The":[180],"Global":[181],"Response":[182],"Map":[183],"(GRM)":[184],"incorporated":[186],"as":[187],"an":[188],"unsupervised":[189],"spatial":[190],"constraint":[191],"filter":[193],"those":[194],"instances":[195],"sound-unrelated":[202],"regions.":[203],"result,":[206],"our":[207],"Sound":[209],"Source":[210],"Localization":[211],"(SSL)":[212],"be":[214],"cast":[215],"into":[216],"simpler":[218],"Multiple":[219],"Instance":[220],"(MIL)":[222],"problem.":[223],"overcome":[225],"limitation":[227],"random":[229],"in":[231],"AVCL,":[232],"propose":[234],"Active":[237],"Set":[239],"Mining":[240],"(ACSM)":[241],"mine":[243],"sets":[246],"with":[247,270],"informative":[248],"diverse":[250,271],"negatives":[251],"robust":[253],"AVCL.":[254],"Our":[255],"approaches":[256],"state-of-the-art":[258],"(SOTA)":[259],"performance":[260],"when":[261],"compared":[262],"several":[264],"baselines":[265],"multiple":[267],"SSL":[268],"datasets":[269],"scenarios.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}