{"id":"https://openalex.org/W3198371949","doi":"https://doi.org/10.1109/tip.2021.3106814","title":"Discriminative Cross-Modality Attention Network for Temporal Inconsistent Audio-Visual Event Localization","display_name":"Discriminative Cross-Modality Attention Network for Temporal Inconsistent Audio-Visual Event Localization","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198371949","doi":"https://doi.org/10.1109/tip.2021.3106814","mag":"3198371949","pmid":"https://pubmed.ncbi.nlm.nih.gov/34478364"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3106814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3106814","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5011876855","display_name":"Hanyu Xuan","orcid":"https://orcid.org/0000-0002-4633-2794"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyu Xuan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]"],"raw_orcid":"https://orcid.org/0000-0002-4633-2794","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672909","display_name":"Lei Luo","orcid":"https://orcid.org/0000-0002-9329-1411"},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Luo","raw_affiliation_strings":["JD Finance America Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Finance America Corporation, USA","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389499","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0001-5727-9450"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China. (e-mail: yyan@njust.edu.cn)","[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China. (e-mail: yyan@njust.edu.cn)","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"[School of Computer Sci. & Eng., Nanjing University of Sci. & Tech., Nanjing, China]","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7966,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.85723222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"7878","last_page":"7888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9973000288009644,"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":0.9882000088691711,"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/discriminative-model","display_name":"Discriminative model","score":0.8393311500549316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034591436386108},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.663926899433136},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6370572447776794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6309382915496826},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5799048542976379},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.55318284034729},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4712177813053131},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4255676865577698},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41917747259140015},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41136786341667175},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41107508540153503},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3426312804222107},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3395925760269165},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.125645250082016}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8393311500549316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034591436386108},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.663926899433136},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6370572447776794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309382915496826},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5799048542976379},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.55318284034729},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4712177813053131},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4255676865577698},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41917747259140015},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41136786341667175},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41107508540153503},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3426312804222107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3395925760269165},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.125645250082016},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3106814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3106814","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:34478364","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34478364","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[{"id":"https://openalex.org/G4218343646","display_name":null,"funder_award_id":"61806094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G635378778","display_name":null,"funder_award_id":"U1713208","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W15375276","https://openalex.org/W1531883353","https://openalex.org/W1777628566","https://openalex.org/W1883346539","https://openalex.org/W1949478088","https://openalex.org/W1968375094","https://openalex.org/W2010055427","https://openalex.org/W2053667957","https://openalex.org/W2071207147","https://openalex.org/W2103104224","https://openalex.org/W2108598243","https://openalex.org/W2123024445","https://openalex.org/W2165673880","https://openalex.org/W2186500555","https://openalex.org/W2194775991","https://openalex.org/W2202025056","https://openalex.org/W2267805933","https://openalex.org/W2295107390","https://openalex.org/W2400826247","https://openalex.org/W2428757121","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2575842049","https://openalex.org/W2578229578","https://openalex.org/W2593116425","https://openalex.org/W2597655663","https://openalex.org/W2619383789","https://openalex.org/W2619697695","https://openalex.org/W2742947407","https://openalex.org/W2783457476","https://openalex.org/W2795151422","https://openalex.org/W2798453914","https://openalex.org/W2884001105","https://openalex.org/W2890732922","https://openalex.org/W2890765146","https://openalex.org/W2912512021","https://openalex.org/W2919358988","https://openalex.org/W2920377649","https://openalex.org/W2931433835","https://openalex.org/W2942864103","https://openalex.org/W2946165673","https://openalex.org/W2962756039","https://openalex.org/W2962772482","https://openalex.org/W2962960500","https://openalex.org/W2962968152","https://openalex.org/W2963652649","https://openalex.org/W2963854386","https://openalex.org/W2964045146","https://openalex.org/W2964109005","https://openalex.org/W2964199361","https://openalex.org/W2964345931","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3102207944","https://openalex.org/W4251308012","https://openalex.org/W4293665662","https://openalex.org/W4298112588","https://openalex.org/W6600650022","https://openalex.org/W6639103823","https://openalex.org/W6678470764","https://openalex.org/W6693552211","https://openalex.org/W6725104640","https://openalex.org/W6729831399","https://openalex.org/W6732872814","https://openalex.org/W6735377749","https://openalex.org/W6749633790","https://openalex.org/W6750591037","https://openalex.org/W6751130187","https://openalex.org/W6756871312"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2088690926","https://openalex.org/W1526651343","https://openalex.org/W4387698063"],"abstract_inverted_index":{"It":[0],"is":[1,66,137,174],"theoretically":[2],"insufficient":[3],"to":[4,31,37,51,94,100,109,112,116,124,139,144,176],"construct":[5],"a":[6,19,89,97,132],"complete":[7],"set":[8],"of":[9,22,42,62,191],"semantics":[10],"in":[11,68],"the":[12,25,39,59,69,74,141],"real":[13],"world":[14],"using":[15],"single-modality":[16],"data.":[17],"As":[18],"typical":[20],"application":[21],"multi-modality":[23,85,157],"perception,":[24,86],"audio-visual":[26,70,119,182,192],"event":[27,120,183,193],"localization":[28,200],"task":[29],"aims":[30],"match":[32],"audio":[33,147,168],"and":[34,114,148,155,169,201],"visual":[35,149,170],"components":[36],"identify":[38],"simultaneous":[40],"events":[41],"interest.":[43],"Although":[44],"some":[45],"recent":[46],"methods":[47],"have":[48],"been":[49],"proposed":[50,138],"deal":[52],"with":[53,163],"this":[54,160],"task,":[55],"they":[56],"cannot":[57],"handle":[58],"practical":[60],"situation":[61],"temporal":[63,165,196],"inconsistency":[64,166],"that":[65],"widespread":[67],"scene.":[71],"Inspired":[72],"by":[73],"human":[75,101],"system":[76],"which":[77,151],"automatically":[78],"filters":[79],"out":[80],"event-unrelated":[81],"information":[82,180],"when":[83],"performing":[84],"we":[87,186],"propose":[88],"discriminative":[90,154],"cross-modality":[91,202],"attention":[92],"network":[93,104,127,143,173,214],"simulate":[95],"such":[96],"process.":[98],"Similar":[99],"mechanism,":[102],"our":[103,126,172,213],"can":[105,152],"adaptively":[106,177],"select":[107,178],"\"where\"":[108],"attend,":[110],"\"when\"":[111],"attend":[113,117],"\"which\"":[115],"for":[118,181],"localization.":[121,184,203],"In":[122,159],"addition,":[123],"prevent":[125],"from":[128],"getting":[129],"trivial":[130],"solutions,":[131],"novel":[133],"eigenvalue-based":[134],"objective":[135],"function":[136],"train":[140],"whole":[142],"better":[145,210],"fuse":[146],"signals,":[150],"obtain":[153],"nonlinear":[156],"representation.":[158],"way,":[161],"even":[162],"large":[164],"between":[167],"sequence,":[171],"able":[175],"event-valuable":[179],"Furthermore,":[185],"systemically":[187],"investigate":[188],"three":[189],"subtasks":[190],"localization,":[194,197],"i.e.,":[195],"weakly-supervised":[198],"spatial":[199],"The":[204],"visualization":[205],"results":[206],"also":[207],"help":[208],"us":[209],"understand":[211],"how":[212],"works.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
