{"id":"https://openalex.org/W4367146821","doi":"https://doi.org/10.1109/tmm.2023.3270624","title":"CSS-Net: A Consistent Segment Selection Network for Audio-Visual Event Localization","display_name":"CSS-Net: A Consistent Segment Selection Network for Audio-Visual Event Localization","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4367146821","doi":"https://doi.org/10.1109/tmm.2023.3270624"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3270624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3270624","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/A5101581669","display_name":"Fan Feng","orcid":"https://orcid.org/0000-0001-7959-2472"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Feng","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China"],"raw_orcid":"https://orcid.org/0000-0001-7959-2472","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089582342","display_name":"Yue Ming","orcid":"https://orcid.org/0000-0001-7105-4207"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Ming","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China"],"raw_orcid":"https://orcid.org/0000-0001-7105-4207","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014620591","display_name":"Nannan Hu","orcid":"https://orcid.org/0000-0002-4080-7891"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Hu","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006580423","display_name":"Hui Yu","orcid":"https://orcid.org/0000-0002-7655-9228"},"institutions":[{"id":"https://openalex.org/I63072094","display_name":"University of Portsmouth","ror":"https://ror.org/03ykbk197","country_code":"GB","type":"education","lineage":["https://openalex.org/I63072094"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui Yu","raw_affiliation_strings":["School of Creative Technologies, University of Portsmouth, Portsmouth, U.K"],"raw_orcid":"https://orcid.org/0000-0002-7655-9228","affiliations":[{"raw_affiliation_string":"School of Creative Technologies, University of Portsmouth, Portsmouth, U.K","institution_ids":["https://openalex.org/I63072094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020422392","display_name":"Yuanan Liu","orcid":"https://orcid.org/0000-0002-8076-1904"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanan Liu","raw_affiliation_strings":["Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China"],"raw_orcid":"https://orcid.org/0000-0002-8076-1904","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, PR, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3055,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93224044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"701","last_page":"713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9934999942779541,"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":0.8402324914932251},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6359707713127136},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6309400796890259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557228684425354},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5298820734024048},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49151715636253357},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4676857590675354},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.448824942111969},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4420415759086609},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43790096044540405},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4267274737358093},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4201313853263855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40695011615753174},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1658557951450348}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402324914932251},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6359707713127136},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6309400796890259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557228684425354},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5298820734024048},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49151715636253357},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4676857590675354},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.448824942111969},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4420415759086609},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43790096044540405},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4267274737358093},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4201313853263855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40695011615753174},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1658557951450348},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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:10.1109/tmm.2023.3270624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3270624","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/G5457963859","display_name":null,"funder_award_id":"62076030","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":50,"referenced_works":["https://openalex.org/W1938425378","https://openalex.org/W2117539524","https://openalex.org/W2187089797","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2931433835","https://openalex.org/W2937949426","https://openalex.org/W2963091558","https://openalex.org/W2963150162","https://openalex.org/W2964109005","https://openalex.org/W2990113535","https://openalex.org/W2996173702","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3093287838","https://openalex.org/W3110606395","https://openalex.org/W3118366136","https://openalex.org/W3168126734","https://openalex.org/W3170717896","https://openalex.org/W3170936177","https://openalex.org/W3174569083","https://openalex.org/W3175514052","https://openalex.org/W3193551800","https://openalex.org/W3198371949","https://openalex.org/W3214311327","https://openalex.org/W3217354365","https://openalex.org/W4211154280","https://openalex.org/W4214912084","https://openalex.org/W4225327041","https://openalex.org/W4225505766","https://openalex.org/W4226206782","https://openalex.org/W4226380330","https://openalex.org/W4280494461","https://openalex.org/W4283792272","https://openalex.org/W4285132306","https://openalex.org/W4285146284","https://openalex.org/W4289752563","https://openalex.org/W4312383773","https://openalex.org/W4312415534","https://openalex.org/W4312583638","https://openalex.org/W4313555695","https://openalex.org/W4319300466","https://openalex.org/W4319992862","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6790875704","https://openalex.org/W6799733436","https://openalex.org/W6838883583"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W4392445444","https://openalex.org/W4396220545","https://openalex.org/W2220831889","https://openalex.org/W4312683641","https://openalex.org/W3027421045","https://openalex.org/W3013312691","https://openalex.org/W2980386803","https://openalex.org/W3215994059","https://openalex.org/W2319823519"],"abstract_inverted_index":{"Audio-visual":[0],"event":[1,20,57,163],"(AVE)":[2],"localization":[3,209],"aims":[4],"to":[5,18,91,96,98,118,175],"localize":[6],"the":[7,47,132,136,177,188,202,212],"temporal":[8,33],"boundaries":[9],"of":[10,49,190,204,215],"events":[11],"that":[12],"contains":[13],"visual":[14,40,102,122,137,156,182],"and":[15,93,104,123,138,151,157,183,192,217,222],"audio":[16,90,124,139,158,184],"contents,":[17],"identify":[19],"categories":[21],"in":[22,42,54,71,142,165,219],"unconstrained":[23],"videos.":[24,166],"Existing":[25],"work":[26],"usually":[27],"utilizes":[28],"successive":[29],"video":[30],"segments":[31,44,150],"for":[32,181],"modeling.":[34,58],"However,":[35],"ambient":[36],"sounds":[37],"or":[38],"irrelevant":[39],"targets":[41],"some":[43],"often":[45],"cause":[46],"problem":[48],"audio-visual":[50,172],"semantics":[51,164,179],"inconsistency,":[52],"resulting":[53],"inaccurate":[55],"global":[56,162,185],"To":[59],"tackle":[60],"this":[61,72],"issue,":[62],"we":[63,75,109,168],"present":[64],"a":[65,77,111,170],"consistent":[66,121],"segment":[67],"selection":[68],"network":[69],"(CSS-Net)":[70],"paper.":[73],"First,":[74],"propose":[76,110,169],"novel":[78,112,171],"bidirectional":[79],"guided":[80],"co-attention":[81],"(BGCA)":[82],"block,":[83],"containing":[84],"two":[85],"distinct":[86],"attention":[87],"paths":[88],"from":[89,94],"vision":[92,95],"audio,":[97],"focus":[99],"on":[100,197],"sound-related":[101],"regions":[103],"event-related":[105],"sound":[106],"segments.":[107,125],"Then,":[108],"context-aware":[113],"similarity":[114],"measure":[115],"(CASM)":[116],"module":[117],"select":[119],"semantic":[120],"A":[126],"cross-correlation":[127],"matrix":[128],"is":[129],"constructed":[130],"using":[131],"correlation":[133],"coefficients":[134],"between":[135],"feature":[140],"pairs":[141],"all":[143],"time":[144],"steps.":[145],"By":[146],"extracting":[147],"highly":[148],"correlated":[149,154],"discarding":[152],"low":[153],"segments,":[155],"features":[159,186],"can":[160],"learn":[161,176],"Finally,":[167],"contrastive":[173],"loss":[174],"similar":[178],"representation":[180],"under":[187],"constraints":[189],"cosine":[191],"L2":[193],"similarities.":[194],"Extensive":[195],"experiments":[196],"public":[198],"AVE":[199],"dataset":[200],"demonstrates":[201],"effectiveness":[203],"our":[205],"proposed":[206],"CSS-Net.":[207],"The":[208],"accuracies":[210],"achieve":[211],"best":[213],"performance":[214],"80.5%":[216],"76.8%":[218],"both":[220],"fully-":[221],"weakly-supervised":[223],"settings":[224],"compared":[225],"with":[226],"other":[227],"state-of-the-art":[228],"methods.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}