{"id":"https://openalex.org/W4312558733","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892495","title":"Look longer to see better: Audio-visual event localization by exploiting long-term correlation","display_name":"Look longer to see better: Audio-visual event localization by exploiting long-term correlation","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312558733","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892495"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892495","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5088989767","display_name":"Longyin Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longyin Guo","raw_affiliation_strings":["National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University,Chengdu,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085914001","display_name":"Qijun Zhao","orcid":"https://orcid.org/0000-0003-4651-7163"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qijun Zhao","raw_affiliation_strings":["National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University,Chengdu,China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005897940","display_name":"Hongmei Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmei Gao","raw_affiliation_strings":["School of Information Science and Technology, Tibet University,Lhasa,China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Tibet University,Lhasa,China","institution_ids":["https://openalex.org/I140786321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088989767"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":0.2452,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42432859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"07"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9955999851226807,"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":0.8246011137962341},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7307319641113281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6063400506973267},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5273840427398682},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.50987708568573},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5091878771781921},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.49739888310432434},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4838915765285492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41693738102912903},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41383129358291626},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40257078409194946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3588944673538208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246011137962341},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7307319641113281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6063400506973267},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5273840427398682},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.50987708568573},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5091878771781921},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49739888310432434},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4838915765285492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41693738102912903},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41383129358291626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40257078409194946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3588944673538208},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892495","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","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":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2161226030","https://openalex.org/W2163605009","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2884739346","https://openalex.org/W2931433835","https://openalex.org/W2963290645","https://openalex.org/W2964109005","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3093287838","https://openalex.org/W3098319575","https://openalex.org/W3110606395","https://openalex.org/W3118366136","https://openalex.org/W3154807520","https://openalex.org/W3163527109","https://openalex.org/W3170936177","https://openalex.org/W3175514052","https://openalex.org/W3198371949","https://openalex.org/W3214311327","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2350267540"],"abstract_inverted_index":{"Visual":[0],"and":[1,72,105,131,133,140,152],"auditory":[2],"modalities":[3,28],"both":[4],"contain":[5],"a":[6],"large":[7],"amount":[8],"of":[9,25,47,50,70,98,129,165],"rich":[10],"information":[11,24,43],"about":[12],"audio-visual":[13,51,61,100],"events.":[14],"While":[15],"the":[16,23,26,45,67,87,95,99,103,116,125,149,157,163],"human":[17],"perception":[18],"system":[19],"can":[20],"effectively":[21,40],"fuse":[22],"dual":[27],"in":[29,53,102,110],"recognizing":[30],"events,":[31],"it":[32],"is":[33,76],"still":[34],"an":[35,60],"open":[36],"issue":[37],"how":[38],"to":[39,65,137],"integrate":[41],"dual-modal":[42],"for":[44,148],"task":[46],"automatic":[48],"localization":[49],"events":[52,101],"videos.":[54],"In":[55],"this":[56,82],"paper,":[57],"we":[58,84],"propose":[59,86,115],"long-term":[62],"correlation":[63,69,127],"network":[64],"capture":[66],"longer":[68],"audio":[71,139],"visual":[73,141],"features,":[74],"which":[75,93,123],"underused":[77],"by":[78],"existing":[79],"methods.":[80],"To":[81],"end,":[83],"first":[85],"time-spatial":[88],"guided":[89],"attention":[90],"(TSGA)":[91],"module,":[92,122],"locates":[94],"spatial":[96],"region":[97],"video":[104,130],"focuses":[106],"on":[107,156],"continuous":[108],"changes":[109],"that":[111],"location.":[112],"We":[113,143],"then":[114],"positive":[117],"time":[118],"residual":[119,135],"fusion":[120,136],"(PTRF)":[121],"encodes":[124],"temporal":[126],"matrix":[128],"audio,":[132],"uses":[134],"combine":[138],"features.":[142],"finally":[144],"evaluate":[145],"our":[146,166],"method":[147,167],"fully":[150],"supervised":[151,154],"weakly":[153],"tasks":[155],"AVE":[158],"dataset.":[159],"The":[160],"results":[161],"prove":[162],"superiority":[164],"over":[168],"its":[169],"counterparts.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}