{"id":"https://openalex.org/W4400527955","doi":"https://doi.org/10.1109/fg59268.2024.10582018","title":"Audio-Visual Person Verification Based on Recursive Fusion of Joint Cross-Attention","display_name":"Audio-Visual Person Verification Based on Recursive Fusion of Joint Cross-Attention","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400527955","doi":"https://doi.org/10.1109/fg59268.2024.10582018"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10582018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10582018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021177750","display_name":"R. Gnana Praveen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"R. Gnana Praveen","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088749621","display_name":"Jahangir Alam","orcid":"https://orcid.org/0000-0003-4174-9862"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jahangir Alam","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Canada","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":null,"apc_paid":null,"fwci":1.7095,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88551681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.998199999332428,"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":0.9977999925613403,"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":0.996999979019165,"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/joint","display_name":"Joint (building)","score":0.7136606574058533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995433568954468},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6356669068336487},{"id":"https://openalex.org/keywords/joint-attention","display_name":"Joint attention","score":0.6155589818954468},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4798521399497986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4234410524368286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816709518432617},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3608470559120178},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24784287810325623},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1788845956325531},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08559975028038025}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7136606574058533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995433568954468},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6356669068336487},{"id":"https://openalex.org/C137878579","wikidata":"https://www.wikidata.org/wiki/Q9636076","display_name":"Joint attention","level":3,"score":0.6155589818954468},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4798521399497986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4234410524368286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816709518432617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3608470559120178},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24784287810325623},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1788845956325531},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08559975028038025},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg59268.2024.10582018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10582018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6933375589","display_name":null,"funder_award_id":"NFRFR-2021-00338","funder_id":"https://openalex.org/F4320319880","funder_display_name":"Government of Canada"}],"funders":[{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2023238506","https://openalex.org/W2194775991","https://openalex.org/W2726515241","https://openalex.org/W2794506738","https://openalex.org/W2797558164","https://openalex.org/W2902299888","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3025804484","https://openalex.org/W3026006730","https://openalex.org/W3035333188","https://openalex.org/W3096936581","https://openalex.org/W3111481301","https://openalex.org/W3118366136","https://openalex.org/W3126259644","https://openalex.org/W3126757411","https://openalex.org/W3163527109","https://openalex.org/W3211666705","https://openalex.org/W4295789112","https://openalex.org/W4308097564","https://openalex.org/W4313591463","https://openalex.org/W4372259790","https://openalex.org/W4372265901","https://openalex.org/W4372270167","https://openalex.org/W4375868968","https://openalex.org/W4385823141","https://openalex.org/W4388878581","https://openalex.org/W6787439801","https://openalex.org/W6790875704"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W2331316773","https://openalex.org/W4234497699","https://openalex.org/W314221487","https://openalex.org/W2501000359","https://openalex.org/W2137049550","https://openalex.org/W3014989972"],"abstract_inverted_index":{"Person":[0],"or":[1,34],"identity":[2],"verification":[3,54],"has":[4],"been":[5],"recently":[6],"gaining":[7],"a":[8,83,99,103,108,120],"lot":[9],"of":[10,49,67,102,155],"attention":[11],"using":[12],"audio-visual":[13,29,50,110,142,156],"fusion":[14,30,37,51,90,101,182],"as":[15],"faces":[16],"and":[17,72,77,135,189,194],"voices":[18],"share":[19],"close":[20],"associations":[21],"with":[22],"each":[23],"other.":[24],"Conventional":[25],"approaches":[26,41],"based":[27],"on":[28,32,163],"rely":[31],"score-level":[33],"early":[35],"feature-level":[36],"techniques.":[38],"Though":[39],"existing":[40],"showed":[42],"improvement":[43,180],"over":[44,92],"unimodal":[45,93],"systems,":[46],"the":[47,65,89,116,126,133,141,152,164,169,175,187],"potential":[48],"for":[52],"person":[53],"is":[55,113,198],"not":[56],"fully":[57],"exploited.":[58],"In":[59,95],"this":[60],"paper,":[61],"we":[62,97,145],"have":[63,146],"investigated":[64],"prospect":[66],"effectively":[68],"capturing":[69,186],"both":[70],"intra-":[71,134,188],"inter-modal":[73,136,190],"relationships":[74,191],"across":[75,192],"audio":[76,193],"visual":[78,195],"modalities,":[79],"which":[80],"can":[81,130],"play":[82],"crucial":[84],"role":[85],"in":[86,115,119,181],"significantly":[87],"improving":[88],"performance":[91,183],"systems.":[94],"particular,":[96],"introduce":[98],"recursive":[100,121],"joint":[104,109],"cross-attentional":[105],"model,":[106],"where":[107],"feature":[111,127,143,157],"representation":[112],"employed":[114],"cross-attention":[117],"framework":[118],"fashion":[122],"to":[123,150,167],"progressively":[124],"refine":[125],"representations":[128],"that":[129,174],"efficiently":[131],"capture":[132],"relationships.":[137],"To":[138],"further":[139],"enhance":[140],"representations,":[144],"also":[147],"explored":[148],"BLSTMs":[149],"improve":[151],"temporal":[153],"modeling":[154],"representations.":[158],"Extensive":[159],"experiments":[160],"are":[161],"conducted":[162],"Voxceleb1":[165],"dataset":[166],"evaluate":[168],"proposed":[170,176],"model.":[171],"Results":[172],"indicate":[173],"model":[177],"shows":[178],"promising":[179],"by":[184],"adeptly":[185],"modalities.":[196],"Code":[197],"available":[199],"at":[200],"https://github.com/praveena2j/RJCAforSpeakerVerification":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}
