{"id":"https://openalex.org/W4406890739","doi":"https://doi.org/10.1109/tmm.2025.3535359","title":"Listen With Seeing: Cross-Modal Contrastive Learning for Audio-Visual Event Localization","display_name":"Listen With Seeing: Cross-Modal Contrastive Learning for Audio-Visual Event Localization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406890739","doi":"https://doi.org/10.1109/tmm.2025.3535359"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535359","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5101659046","display_name":"Chao Sun","orcid":"https://orcid.org/0000-0002-8735-4893"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"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":"Chao Sun","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8735-4893","affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","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":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0960-4447","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"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/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"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":["Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-6441-1162","affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394010","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0002-1993-1660"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"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":"Sheng Zhang","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021981517","display_name":"Ping L\u00fc","orcid":"https://orcid.org/0000-0002-0199-3783"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"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":"Ping Lu","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","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/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"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":["Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7368-1677","affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Information Storage System, Engineering Research Center of Data Storage Systems and Technology, Ministry of Education of China, and School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.0243,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98189874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"2650","last_page":"2665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9915000200271606,"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":0.916100025177002,"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":0.8569660782814026},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6460499167442322},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5300003886222839},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4766683876514435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4744378626346588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.461182177066803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38030529022216797},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3401522636413574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569660782814026},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6460499167442322},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5300003886222839},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4766683876514435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4744378626346588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.461182177066803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38030529022216797},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3401522636413574},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535359","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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/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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1957718552","https://openalex.org/W2104396257","https://openalex.org/W2125105611","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2618530766","https://openalex.org/W2619697695","https://openalex.org/W2777342313","https://openalex.org/W2921491036","https://openalex.org/W2925312408","https://openalex.org/W2931433835","https://openalex.org/W2960737790","https://openalex.org/W2962960500","https://openalex.org/W2963061824","https://openalex.org/W2963795951","https://openalex.org/W2964109005","https://openalex.org/W2981905048","https://openalex.org/W2987228832","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3004413500","https://openalex.org/W3015190346","https://openalex.org/W3015925607","https://openalex.org/W3019533076","https://openalex.org/W3021321555","https://openalex.org/W3033208854","https://openalex.org/W3035118106","https://openalex.org/W3089682612","https://openalex.org/W3093287838","https://openalex.org/W3094378471","https://openalex.org/W3108655343","https://openalex.org/W3110606395","https://openalex.org/W3118548710","https://openalex.org/W3153167542","https://openalex.org/W3175300676","https://openalex.org/W3175514052","https://openalex.org/W3190580390","https://openalex.org/W3203741465","https://openalex.org/W3214311327","https://openalex.org/W4211154280","https://openalex.org/W4236398794","https://openalex.org/W4285293775","https://openalex.org/W4312383651","https://openalex.org/W4312415534","https://openalex.org/W4312444556","https://openalex.org/W4367146821","https://openalex.org/W4383428585","https://openalex.org/W4384820833","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6751395999","https://openalex.org/W6762573206","https://openalex.org/W6766008006","https://openalex.org/W6774314701","https://openalex.org/W6776700526"],"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":{"In":[0,102],"real-world":[1],"physiological":[2,109],"and":[3,15,34,98,123,146,199,235],"psychological":[4],"scenarios,":[5],"there":[6],"often":[7],"exists":[8],"a":[9,85,95,99,137,201],"robust":[10],"complementary":[11],"correlation":[12,153],"between":[13,176],"audio":[14,33],"visual":[16,35],"signals.":[17],"Audio-Visual":[18,27],"Event":[19,162],"Localization":[20,244],"(AVEL)":[21],"aims":[22],"to":[23,62,190,255],"identify":[24],"segments":[25],"with":[26,142],"Events":[28],"(AVEs)":[29],"that":[30],"contain":[31],"both":[32,232],"tracks":[36],"in":[37,218],"unconstrained":[38],"videos.":[39],"Prior":[40],"studies":[41],"have":[42],"predominantly":[43],"focused":[44],"on":[45,227],"audio-visual":[46,76,119,143,152,197],"cross-modal":[47,56,193,204],"fusion":[48,58,77,144,216],"methods,":[49],"overlooking":[50],"the":[51,55,63,75,103,116,130,151,167,174,192,213,219,228,248],"fine-grained":[52],"exploration":[53],"of":[54,66,111,118,150,169,196,215,251],"information":[57,120],"mechanism.":[59],"Moreover,":[60],"due":[61],"inherent":[64],"heterogeneity":[65],"multi-modal":[67],"data,":[68],"inevitable":[69],"new":[70],"noise":[71],"is":[72,136],"introduced":[73],"during":[74,179],"process.":[78],"To":[79],"address":[80],"these":[81],"challenges,":[82],"we":[83,114,185],"propose":[84],"novel":[86],"Cross-modal":[87],"Contrastive":[88],"Learning":[89],"Network":[90],"(CCLN)":[91],"for":[92,231],"AVEL,":[93],"comprising":[94],"backbone":[96,104],"network":[97],"branch":[100],"network.":[101],"network,":[105],"drawing":[106],"inspiration":[107],"from":[108,125],"theories":[110],"sensory":[112],"integration,":[113],"elucidate":[115],"process":[117],"fusion,":[121],"interaction,":[122],"integration":[124],"an":[126],"information-flow":[127],"perspective.":[128],"Notably,":[129],"Self-constrained":[131],"Bi-modal":[132],"Interaction":[133],"(SBI)":[134],"module":[135,165],"bi-modal":[138],"attention":[139],"structure":[140],"integrated":[141],"information,":[145],"through":[147,181],"gated":[148],"processing":[149],"matrix,":[154],"it":[155],"effectively":[156],"captures":[157],"inter-modal":[158],"correlation.":[159],"The":[160],"Foreground":[161],"Enhancement":[163],"(FEE)":[164],"emphasizes":[166],"significance":[168],"event-level":[170],"boundaries":[171],"by":[172],"elongating":[173],"distance":[175],"scene":[177],"events":[178,198],"training":[180],"adaptive":[182],"weights.":[183],"Furthermore,":[184],"introduce":[186],"weak":[187],"video-level":[188],"labels":[189],"constrain":[191],"semantic":[194],"alignment":[195],"design":[200],"weakly":[202,236],"supervised":[203,234,237],"contrastive":[205,221],"learning":[206,222],"loss":[207],"(WCCL":[208],"Loss)":[209],"function,":[210],"which":[211],"enhances":[212],"quality":[214],"representation":[217],"dual-branch":[220],"framework.":[223],"Extensive":[224],"experiments":[225],"conducted":[226],"AVE":[229],"dataset":[230],"fully":[233],"event":[238],"localization,":[239],"as":[240,242],"well":[241],"Cross-Modal":[243],"(CML)":[245],"tasks,":[246],"demonstrate":[247],"superior":[249],"performance":[250],"our":[252],"model":[253],"compared":[254],"state-of-the-art":[256],"approaches.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}