{"id":"https://openalex.org/W4411631854","doi":"https://doi.org/10.1145/3731715.3733320","title":"Efficient Prompt-based Multimodal Interaction for Audio-Visual Event Localization","display_name":"Efficient Prompt-based Multimodal Interaction for Audio-Visual Event Localization","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631854","doi":"https://doi.org/10.1145/3731715.3733320"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5114237466","display_name":"Longzhuo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longzhuo Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420741","display_name":"Liang Li","orcid":"https://orcid.org/0009-0009-2440-2905"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079007635","display_name":"Xueyang Fu","orcid":"https://orcid.org/0000-0001-8036-4071"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyang Fu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengjun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114237466"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20998926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9908000230789185,"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":0.7744029760360718},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.6926476955413818},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6905099153518677},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5626773238182068},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49846816062927246},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4226526618003845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4092569947242737},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3849182426929474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3490886092185974},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2960958480834961},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10633352398872375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744029760360718},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.6926476955413818},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6905099153518677},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5626773238182068},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49846816062927246},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4226526618003845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4092569947242737},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3849182426929474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3490886092185974},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2960958480834961},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10633352398872375},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2593116425","https://openalex.org/W2793262076","https://openalex.org/W2931433835","https://openalex.org/W2964121744","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3093287838","https://openalex.org/W3094502228","https://openalex.org/W3118366136","https://openalex.org/W3119438769","https://openalex.org/W3145042111","https://openalex.org/W3152764302","https://openalex.org/W3166396011","https://openalex.org/W4286527741","https://openalex.org/W4287113836","https://openalex.org/W4287208373","https://openalex.org/W4287251776","https://openalex.org/W4295312788","https://openalex.org/W4297795751","https://openalex.org/W4297801719","https://openalex.org/W4303648967","https://openalex.org/W4312349930","https://openalex.org/W4312415534","https://openalex.org/W4312583638","https://openalex.org/W4319300466","https://openalex.org/W4323568442","https://openalex.org/W4378194725","https://openalex.org/W4383180628","https://openalex.org/W4385327627","https://openalex.org/W4387210338","https://openalex.org/W4387918603","https://openalex.org/W4387968342","https://openalex.org/W4387969348","https://openalex.org/W4388266798","https://openalex.org/W4388585791","https://openalex.org/W4392693771","https://openalex.org/W4400679250","https://openalex.org/W4403780792","https://openalex.org/W4403791272","https://openalex.org/W4403791622","https://openalex.org/W4404207656","https://openalex.org/W7093349750"],"related_works":["https://openalex.org/W2968820833","https://openalex.org/W2068964259","https://openalex.org/W2013013717","https://openalex.org/W66256988","https://openalex.org/W4302857920","https://openalex.org/W1987340722","https://openalex.org/W199123384","https://openalex.org/W2739856905","https://openalex.org/W4405250584","https://openalex.org/W4239305747"],"abstract_inverted_index":{"Audio-Visual":[0],"Event":[1],"Localization":[2],"(AVEL)":[3],"requires":[4],"localizing":[5],"an":[6,74],"event":[7,82,114],"by":[8],"jointly":[9],"processing":[10],"audio":[11,29,171],"and":[12,28,34,55,92,95,102,161,165,170],"visual":[13,154],"information.":[14],"Most":[15],"existing":[16],"AVEL":[17],"methods":[18],"commonly":[19],"utilize":[20],"two":[21],"distinct":[22],"models":[23,51],"independently":[24],"trained":[25],"on":[26,175],"image":[27],"datasets":[30],"to":[31,61,65,98,113,157,186],"encode":[32],"features":[33,38,46],"take":[35],"the":[36,40,43,125,134,142,150,153,168,176,195],"extracted":[37,47],"as":[39],"input":[41],"of":[42,127,152,197],"model.":[44,145],"However,":[45],"from":[48,110],"unimodal":[49],"pre-trained":[50,89,155],"lack":[52],"cross-modal":[53],"interaction":[54,78],"may":[56],"also":[57],"contain":[58],"noise":[59],"irrelevant":[60],"AVEL,":[62],"which":[63],"leads":[64],"sub-optimal":[66],"performance.":[67],"To":[68],"address":[69],"this":[70],"issue,":[71],"we":[72],"propose":[73],"efficient":[75],"prompt-based":[76],"multimodal":[77],"approach":[79],"for":[80],"audio-visual":[81,159],"localization.":[83],"Specifically,":[84],"our":[85,116,131,147,182],"method":[86,117,132,148],"freezes":[87],"a":[88],"transformer":[90,144],"model":[91,156],"designs":[93],"query":[94],"global":[96],"prompt":[97],"facilitate":[99],"information":[100,163],"exchange":[101,164],"fusion":[103,166],"across":[104],"modalities.":[105,172],"Combined":[106],"with":[107,140],"end-to-end":[108],"training":[109],"raw":[111],"data":[112],"localization,":[115],"can":[118],"obtain":[119],"more":[120],"task-relevant":[121],"features.":[122],"Since":[123],"only":[124],"parameters":[126],"prompts":[128],"are":[129],"updated,":[130],"avoids":[133],"significant":[135],"computational":[136],"resource":[137],"consumption":[138],"associated":[139],"fine-tuning":[141],"entire":[143],"Additionally,":[146],"enables":[149],"adaptation":[151],"downstream":[158],"tasks":[160],"facilitates":[162],"between":[167],"video":[169],"Experimental":[173],"results":[174],"public":[177],"AVE":[178],"dataset":[179],"demonstrate":[180],"that":[181],"method,":[183],"when":[184],"compared":[185],"state-of-the-art":[187],"approaches,":[188],"achieves":[189],"competitive":[190],"performance":[191],"while":[192],"significantly":[193],"reducing":[194],"number":[196],"trainable":[198],"parameters.":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}