{"id":"https://openalex.org/W4410806299","doi":"https://doi.org/10.1177/1088467x251344931","title":"Temporal spatial semantic fusion network for audio-visual zero-shot learning","display_name":"Temporal spatial semantic fusion network for audio-visual zero-shot learning","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4410806299","doi":"https://doi.org/10.1177/1088467x251344931"},"language":"en","primary_location":{"id":"doi:10.1177/1088467x251344931","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1088467x251344931","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis: An International Journal","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/A5093981474","display_name":"Ming Guo","orcid":"https://orcid.org/0009-0006-7721-691X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Guo","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-7721-691X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087774421","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0002-1963-5319"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044733681","display_name":"Chongjun Wang","orcid":"https://orcid.org/0000-0002-2628-7033"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjun Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5093981474"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11611823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"2","first_page":"373","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9782999753952026,"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/audio-visual","display_name":"Audio visual","score":0.7742559909820557},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6931725740432739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6308534741401672},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5944024920463562},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4769129455089569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4512537717819214},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2055993378162384}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7742559909820557},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6931725740432739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308534741401672},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5944024920463562},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4769129455089569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4512537717819214},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2055993378162384},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1088467x251344931","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1088467x251344931","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis: An International Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2006370340","https://openalex.org/W2020676607","https://openalex.org/W2611632661","https://openalex.org/W2775079417","https://openalex.org/W2799215068","https://openalex.org/W2911959490","https://openalex.org/W2924476266","https://openalex.org/W2963283377","https://openalex.org/W2963545832","https://openalex.org/W2963960318","https://openalex.org/W2971680695","https://openalex.org/W2990113535","https://openalex.org/W2998708909","https://openalex.org/W3004505825","https://openalex.org/W3007283957","https://openalex.org/W3015371781","https://openalex.org/W3025520547","https://openalex.org/W3035042697","https://openalex.org/W3035254087","https://openalex.org/W3037195468","https://openalex.org/W3089682612","https://openalex.org/W3098404559","https://openalex.org/W3119136678","https://openalex.org/W3138516171","https://openalex.org/W3159849182","https://openalex.org/W3160264863","https://openalex.org/W3175335326","https://openalex.org/W3183071693","https://openalex.org/W3206366488","https://openalex.org/W4220737715","https://openalex.org/W4220990661","https://openalex.org/W4285605441","https://openalex.org/W4312653797","https://openalex.org/W4312719027","https://openalex.org/W4312763854","https://openalex.org/W4312852648","https://openalex.org/W4313477296","https://openalex.org/W4372270167","https://openalex.org/W4385789898","https://openalex.org/W4386159996","https://openalex.org/W4386768890","https://openalex.org/W4387385612","https://openalex.org/W4387968071","https://openalex.org/W4387969040","https://openalex.org/W4390873759","https://openalex.org/W4391899188","https://openalex.org/W4393148276","https://openalex.org/W4393160572","https://openalex.org/W4394951217","https://openalex.org/W4395470960","https://openalex.org/W4396214409","https://openalex.org/W4400903918","https://openalex.org/W4401023952","https://openalex.org/W4402195733","https://openalex.org/W6781630272"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2271369634","https://openalex.org/W2366718574","https://openalex.org/W3147472394","https://openalex.org/W2047100085"],"abstract_inverted_index":{"Due":[0],"to":[1,22,106],"the":[2,44,59,116,134,143,184,207],"scarcity":[3],"of":[4,47,186,197],"annotated":[5],"real-world":[6],"data":[7],"for":[8,154],"specific":[9],"categories,":[10],"audio-visual":[11,181],"generalized":[12],"zero-shot":[13],"learning":[14],"(GZSL)":[15],"has":[16],"attracted":[17],"significant":[18,195],"attention.":[19],"GZSL":[20],"aims":[21],"classify":[23],"novel":[24],"classes":[25],"absent":[26],"during":[27],"training":[28],"while":[29],"ensuring":[30],"stable":[31],"performance":[32],"on":[33,122,178,206],"seen":[34],"classes.":[35],"However,":[36],"most":[37],"existing":[38],"methods":[39],"operate":[40],"implicitly,":[41],"often":[42],"neglecting":[43],"effective":[45],"utilization":[46],"temporal,":[48],"spatial,":[49],"and":[50,71,90,111,125,136,151,164,199,203],"semantic":[51,155],"consistency.":[52],"To":[53,157],"address":[54],"these":[55],"challenges,":[56],"we":[57,67,161],"propose":[58],"Temporal":[60],"Spatial":[61],"Semantic":[62],"Fusion":[63],"network":[64],"(TSSF).":[65],"Specifically,":[66],"explore":[68,158],"both":[69,149],"audio":[70,163],"visual":[72,165],"modalities":[73],"using":[74,128],"a":[75,80,85,91,101,129],"multi-branch,":[76],"multi-grained":[77,92,144],"structure":[78],"comprising":[79],"temporal":[81,96,109,135,150],"global":[82,97,113],"extraction":[83,98],"module,":[84,89,146],"spatial":[86,117,123,137,152],"local":[87,118,126],"refinement":[88,119],"fusion":[93,145],"module.":[94],"The":[95],"module":[99,120],"employs":[100],"Transformer-based":[102],"Spiking":[103],"Neural":[104],"Network":[105],"extract":[107],"explicit":[108],"representations":[110],"capture":[112],"dependencies.":[114],"Simultaneously,":[115],"focuses":[121],"information":[124],"details":[127],"window":[130],"attention":[131,153],"mechanism.":[132],"Furthermore,":[133],"features":[138,166],"are":[139],"hierarchically":[140],"fused":[141],"in":[142,201],"which":[147],"incorporates":[148],"enrichment.":[156],"multi-modal":[159,172],"interactions,":[160],"enhance":[162],"through":[167],"cross-modal":[168],"attention,":[169],"followed":[170],"by":[171],"alignment":[173],"with":[174],"text":[175],"embeddings.":[176],"Experiments":[177],"three":[179],"benchmark":[180],"datasets":[182],"validate":[183],"superiority":[185],"our":[187],"method":[188],"over":[189],"state-of-the-art":[190],"approaches.":[191],"Notably,":[192],"TSSF":[193],"achieves":[194],"improvements":[196],"30.34%":[198],"6.96%":[200],"HM":[202],"ZSL":[204],"metrics":[205],"VGG-GZSL":[208],"dataset.":[209]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}