{"id":"https://openalex.org/W4224917197","doi":"https://doi.org/10.1109/icassp43922.2022.9747579","title":"Navigating Audio-Visual Event Detection Across Mismatched Modalities","display_name":"Navigating Audio-Visual Event Detection Across Mismatched Modalities","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917197","doi":"https://doi.org/10.1109/icassp43922.2022.9747579"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747579","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5002348751","display_name":"Guangwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwei Li","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-LANCE Lab,Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01164621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2021 janua","issue":null,"first_page":"1975","last_page":"1979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8808122277259827},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8377981185913086},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6475357413291931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6140111684799194},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5677393078804016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5647725462913513},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.556891679763794},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5074319243431091},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4918506145477295},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4335116147994995},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38153186440467834},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08916738629341125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808122277259827},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8377981185913086},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6475357413291931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140111684799194},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5677393078804016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5647725462913513},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.556891679763794},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5074319243431091},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4918506145477295},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4335116147994995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38153186440467834},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08916738629341125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747579","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":33,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2117539524","https://openalex.org/W2593116425","https://openalex.org/W2931433835","https://openalex.org/W2962960500","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2964109005","https://openalex.org/W2970231061","https://openalex.org/W3015371781","https://openalex.org/W3035323656","https://openalex.org/W3096936581","https://openalex.org/W3097450720","https://openalex.org/W3099388488","https://openalex.org/W3118120400","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3126757411","https://openalex.org/W3145444543","https://openalex.org/W3162999565","https://openalex.org/W3169064633","https://openalex.org/W3173978205","https://openalex.org/W3205743929","https://openalex.org/W4385245566","https://openalex.org/W6600983433","https://openalex.org/W6739901393","https://openalex.org/W6749633790","https://openalex.org/W6750591037","https://openalex.org/W6766632297","https://openalex.org/W6778999438","https://openalex.org/W6785194926","https://openalex.org/W6790830454","https://openalex.org/W6797307915"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2185469136","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2011264131","https://openalex.org/W3137890128","https://openalex.org/W1984634519"],"abstract_inverted_index":{"Previous":[0],"audio-visual":[1,99],"(AV)":[2],"alignment":[3],"mainly":[4],"focuses":[5],"on":[6,15,18,41,66,82,91],"frame-level":[7],"synchronization":[8],"while":[9],"neglecting":[10],"clip-wise":[11,68],"matching.":[12],"We":[13],"focus":[14],"AV":[16,59],"parsing":[17,40,61,80,88],"fully":[19],"unconstrained":[20],"data":[21],"where":[22,58],"the":[23,55],"audio":[24],"and":[25,62,84],"visual":[26],"events":[27,48],"do":[28],"not":[29],"necessarily":[30],"co-present.":[31],"A":[32],"video-enhanced":[33],"Audioset":[34],"dataset":[35,93],"is":[36,54],"provided":[37],"to":[38],"investigate":[39],"such":[42],"a":[43,67,87],"mismatching":[44],"setting,":[45],"with":[46],"376":[47],"included.":[49],"To":[50],"our":[51,74,92],"knowledge,":[52],"this":[53],"first":[56],"time":[57,101],"event":[60],"detection":[63],"are":[64],"inspected":[65],"matching":[69],"scenario.":[70],"Experiments":[71],"show":[72],"that":[73],"proposed":[75],"method":[76],"largely":[77],"improves":[78],"video":[79],"accuracy":[81],"tagging":[83],"detection.":[85],"Further,":[86],"model":[89],"pre-trained":[90],"can":[94],"assist":[95],"in":[96],"accurately":[97],"locating":[98],"syncing":[100],"spans.":[102]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
