{"id":"https://openalex.org/W7153091629","doi":"https://doi.org/10.1007/s11042-026-21512-2","title":"Hierarchical graph attention networks with spatio-temporal class tokens for distributed audio-visual event classification","display_name":"Hierarchical graph attention networks with spatio-temporal class tokens for distributed audio-visual event classification","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7153091629","doi":"https://doi.org/10.1007/s11042-026-21512-2"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-026-21512-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21512-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21512-2.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21512-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007962043","display_name":"Vijay John","orcid":"https://orcid.org/0000-0002-9553-0906"},"institutions":[{"id":"https://openalex.org/I2276074","display_name":"Lawrence Technological University","ror":"https://ror.org/04d52ej85","country_code":"US","type":"education","lineage":["https://openalex.org/I2276074"]},{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Vijay John","raw_affiliation_strings":["Guardian Robot Project, RIKEN, Seika, Kyoto, Japan","Lawrence Technological University, Southfield, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-9553-0906","affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Seika, Kyoto, Japan","institution_ids":["https://openalex.org/I46980622"]},{"raw_affiliation_string":"Lawrence Technological University, Southfield, MI, USA","institution_ids":["https://openalex.org/I2276074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[{"id":"https://openalex.org/I46980622","display_name":"Kyoto Seika University","ror":"https://ror.org/05g4f0342","country_code":"JP","type":"education","lineage":["https://openalex.org/I46980622"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["Guardian Robot Project, RIKEN, Seika, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Seika, Kyoto, Japan","institution_ids":["https://openalex.org/I46980622"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007962043"],"corresponding_institution_ids":["https://openalex.org/I2276074","https://openalex.org/I46980622"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4274347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9361000061035156,"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":0.9361000061035156,"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":0.021400000900030136,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.008899999782443047,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.552299976348877},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3246000111103058},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.30309998989105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9358000159263611},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11042-026-21512-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21512-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21512-2.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11042-026-21512-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21512-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21512-2.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4840238145","display_name":null,"funder_award_id":"JP24H00733","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7153091629.pdf","grobid_xml":"https://content.openalex.org/works/W7153091629.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2903659352","https://openalex.org/W2921102529","https://openalex.org/W2996295914","https://openalex.org/W3015594652","https://openalex.org/W3110606395","https://openalex.org/W3160207687","https://openalex.org/W3161798961","https://openalex.org/W3197097128","https://openalex.org/W4221155627","https://openalex.org/W4312596733","https://openalex.org/W4312658081","https://openalex.org/W4312681615","https://openalex.org/W4319300928","https://openalex.org/W4401476348","https://openalex.org/W4404967341","https://openalex.org/W4414169586"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1,118],"paper":[2],"presents":[3],"a":[4,56],"novel":[5],"multi-view":[6,33],"multimodal":[7,34],"graph":[8,57],"learning":[9],"framework":[10,155],"for":[11,32,66,161],"distributed":[12,175],"audio-visual":[13,162],"event":[14,163],"classification":[15],"using":[16],"synchronized":[17],"sequences":[18],"from":[19],"multi-microphone":[20],"and":[21,47,69,71,96,139,148],"multi-camera":[22],"sensors.":[23],"Existing":[24],"approaches":[25],"often":[26],"rely":[27],"on":[28,145],"simple":[29],"aggregation":[30,122],"strategies":[31],"inputs,":[35],"which":[36],"fail":[37],"to":[38,89,94,100],"adequately":[39],"capture":[40,135],"the":[41,146,153],"complex":[42,171],"spatio-temporal":[43,76,86,92,98,109,132,172],"relationships":[44],"both":[45],"within":[46,81],"across":[48,174],"modalities.":[49],"To":[50],"address":[51],"this":[52,79],"limitation,":[53],"we":[54],"propose":[55],"attention":[58],"network":[59],"architecture":[60,119],"with":[61,111],"individual":[62],"frame-level":[63,75],"sensor":[64,102,124,176],"nodes":[65,87,93,99,133],"each":[67,82,108],"microphone":[68],"camera,":[70],"three":[72],"types":[73],"of":[74,123],"nodes.":[77,103],"In":[78],"framework,":[80],"temporal":[83],"frame,":[84],"audio":[85],"connect":[88],"microphones,":[90],"video":[91],"cameras,":[95],"audio-video":[97],"all":[101],"Temporal":[104],"edges":[105],"further":[106],"interconnect":[107],"node":[110,114,125],"its":[112,166],"corresponding":[113],"in":[115,169],"preceding":[116],"frames.":[117],"enables":[120],"dynamic":[121],"features":[126],"through":[127],"attention-weighted":[128],"mechanisms,":[129],"generating":[130],"updated":[131],"that":[134,152],"intra-modal,":[136],"inter-modal,":[137],"intra-frame,":[138],"inter-frame":[140],"relational":[141],"dependencies.":[142],"Experimental":[143],"results":[144],"MM-Office":[147],"MM-OR":[149],"datasets":[150],"demonstrate":[151],"proposed":[154],"significantly":[156],"outperforms":[157],"existing":[158],"baseline":[159],"methods":[160],"classification,":[164],"highlighting":[165],"superior":[167],"capability":[168],"modeling":[170],"dependencies":[173],"networks.":[177]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-04-11T00:00:00"}