{"id":"https://openalex.org/W4400527613","doi":"https://doi.org/10.1109/fg59268.2024.10581998","title":"Dynamic Cross Attention for Audio-Visual Person Verification","display_name":"Dynamic Cross Attention for Audio-Visual Person Verification","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400527613","doi":"https://doi.org/10.1109/fg59268.2024.10581998"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10581998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581998","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":0.8343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69239419,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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":0.7108584642410278},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7077030539512634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44800904393196106},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4213881194591522},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3304283618927002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7108584642410278},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7077030539512634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44800904393196106},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4213881194591522},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3304283618927002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg59268.2024.10581998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10581998","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2023238506","https://openalex.org/W2145287260","https://openalex.org/W2194775991","https://openalex.org/W2520774990","https://openalex.org/W2726515241","https://openalex.org/W2794506738","https://openalex.org/W2797558164","https://openalex.org/W2902299888","https://openalex.org/W2912083425","https://openalex.org/W2948210185","https://openalex.org/W2962898354","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3025804484","https://openalex.org/W3026006730","https://openalex.org/W3096936581","https://openalex.org/W3111481301","https://openalex.org/W3126259644","https://openalex.org/W3126757411","https://openalex.org/W3163527109","https://openalex.org/W3171302872","https://openalex.org/W3204047821","https://openalex.org/W3211666705","https://openalex.org/W4213188130","https://openalex.org/W4224221948","https://openalex.org/W4226244164","https://openalex.org/W4295789112","https://openalex.org/W4308097564","https://openalex.org/W4313591463","https://openalex.org/W4372259790","https://openalex.org/W4372265901","https://openalex.org/W4375868968","https://openalex.org/W4376226279","https://openalex.org/W4388878581","https://openalex.org/W4402980239","https://openalex.org/W6744265424","https://openalex.org/W6787439801","https://openalex.org/W6790875704","https://openalex.org/W6863095453"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519"],"abstract_inverted_index":{"Although":[0],"person":[1],"or":[2,88,98],"identity":[3],"verification":[4],"has":[5,19],"been":[6],"predominantly":[7],"explored":[8],"using":[9],"individual":[10],"modalities":[11,31],"such":[12],"as":[13],"face":[14],"and":[15,29,105,124],"voice,":[16],"audio-visual":[17,47,68],"fusion":[18],"recently":[20],"shown":[21],"immense":[22],"potential":[23],"to":[24,35,116,146],"outperform":[25],"unimodal":[26],"approaches.":[27],"Audio":[28],"visual":[30,106],"are":[32,140],"often":[33],"expected":[34],"pose":[36],"strong":[37,97,132],"complementary":[38,63,100,133],"relationships,":[39,64,101,134],"which":[40],"plays":[41],"a":[42,76,110],"crucial":[43],"role":[44],"for":[45],"effective":[46],"fusion.":[48],"However,":[49],"they":[50,58,130],"may":[51,59],"not":[52],"always":[53],"strongly":[54],"complement":[55],"each":[56],"other,":[57],"also":[60],"exhibit":[61,131],"weak":[62,99],"resulting":[65],"in":[66],"poor":[67],"feature":[69],"representations.":[70],"In":[71,108],"this":[72],"paper,":[73],"we":[74],"propose":[75],"Dynamic":[77],"Cross":[78],"Attention":[79],"(DCA)":[80],"model":[81,159],"that":[82,156],"can":[83],"dynamically":[84],"select":[85],"the":[86,92,96,118,121,143,148,151,157,162,171],"cross-attended":[87,126],"unattended":[89,136],"features":[90,127],"on":[91,95,142,164],"fly":[93],"based":[94],"respectively,":[102],"across":[103],"audio":[104],"modalities.":[107],"particular,":[109],"conditional":[111],"gating":[112],"layer":[113],"is":[114,175],"designed":[115],"evaluate":[117],"contribution":[119],"of":[120,150,167],"cross-attention":[122,168],"mechanism":[123],"choose":[125],"only":[128],"when":[129],"otherwise":[135],"features.":[137],"Extensive":[138],"experiments":[139],"conducted":[141],"Voxceleb1":[144],"dataset":[145],"demonstrate":[147],"robustness":[149],"proposed":[152,158],"model.":[153],"Results":[154],"indicate":[155],"consistently":[160],"improves":[161],"performance":[163],"multiple":[165],"variants":[166],"while":[169],"outperforming":[170],"state-of-the-art":[172],"methods.":[173],"Code":[174],"available":[176],"at":[177],"https://github.com/praveena2j/DCAforPersonVerification":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}