{"id":"https://openalex.org/W3209112689","doi":"https://doi.org/10.21437/odyssey.2022-33","title":"A Study of Multimodal Person Verification Using Audio-Visual-Thermal Data","display_name":"A Study of Multimodal Person Verification Using Audio-Visual-Thermal Data","publication_year":2022,"publication_date":"2022-06-17","ids":{"openalex":"https://openalex.org/W3209112689","doi":"https://doi.org/10.21437/odyssey.2022-33","mag":"3209112689"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2022-33","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-33","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2022)","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/A5005829685","display_name":"Madina Abdrakhmanova","orcid":null},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Madina Abdrakhmanova","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007390407","display_name":"Saniya Abushakimova","orcid":null},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Saniya Abushakimova","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044782949","display_name":"H\u00fcseyin Atakan Varol","orcid":"https://orcid.org/0000-0002-4042-425X"},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Huseyin Atakan Varol","raw_affiliation_strings":["Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Smart Systems and Artificial Intelligence, Nazarbayev University, Nur-Sultan City, Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60559429"],"apc_list":null,"apc_paid":null,"fwci":1.1074,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77334617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9984999895095825,"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":0.7408393621444702},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5468447208404541},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42540496587753296},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35092693567276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3353627920150757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3325779438018799},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.29930737614631653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408393621444702},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5468447208404541},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42540496587753296},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35092693567276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3353627920150757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3325779438018799},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29930737614631653}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2022-33","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-33","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2022)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1592551781","https://openalex.org/W1686810756","https://openalex.org/W1936725236","https://openalex.org/W2028209924","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2050970306","https://openalex.org/W2133564696","https://openalex.org/W2140609507","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2154383330","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2316482457","https://openalex.org/W2325939864","https://openalex.org/W2596603442","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2799429369","https://openalex.org/W2806318065","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2902299888","https://openalex.org/W2908400479","https://openalex.org/W2910603373","https://openalex.org/W2943235166","https://openalex.org/W2963371159","https://openalex.org/W2964308564","https://openalex.org/W2981087920","https://openalex.org/W2990079977","https://openalex.org/W3013020904","https://openalex.org/W3025804484","https://openalex.org/W3026006730","https://openalex.org/W3099206234","https://openalex.org/W3126757411","https://openalex.org/W3161402421","https://openalex.org/W4288091954","https://openalex.org/W4316036513"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"In":[0],"this":[1,34],"paper,":[2],"we":[3,36,52,180],"study":[4],"an":[5],"approach":[6],"to":[7,27],"multimodal":[8,177],"person":[9,32,178],"verification":[10,58,103],"using":[11,60],"audio,":[12],"visual,":[13],"and":[14,20,56,65,71,85,117,123,134,148,154,165,173,186],"thermal":[15,49],"modalities.The":[16],"combination":[17],"of":[18,40,45,100,170],"audio":[19],"visual":[21],"modalities":[22,46],"has":[23],"already":[24],"been":[25],"shown":[26],"be":[28],"effective":[29],"for":[30],"robust":[31],"verification.From":[33],"perspective,":[35],"investigate":[37],"the":[38,43,86,93,97,101,106,110,114,132,137,141,145,163,171],"impact":[39],"further":[41],"increasing":[42],"number":[44],"by":[47,120,151],"adding":[48],"images.In":[50],"particular,":[51],"implemented":[53],"unimodal,":[54],"bimodal,":[55],"trimodal":[57,102,111,142],"systems":[59,119,150],"state-of-the-art":[61],"deep":[62],"learning":[63],"architectures":[64],"compared":[66,75],"their":[67],"performance":[68,99],"under":[69,130,161],"clean":[70,133,164],"noisy":[72,135,166],"conditions.We":[73],"also":[74],"two":[76],"popular":[77],"fusion":[78],"approaches":[79],"based":[80],"on":[81,92,105],"simple":[82],"score":[83],"averaging":[84],"soft":[87],"attention":[88],"mechanism.The":[89],"experiment":[90,172],"conducted":[91],"SpeakingFaces":[94],"dataset":[95,188],"demonstrates":[96],"superior":[98],"system.Specifically,":[104],"easy":[107],"test":[108,139],"set,":[109,140],"system":[112,143],"outperforms":[113,144],"best":[115,146],"unimodal":[116,147],"bimodal":[118,149],"over":[121,152],"50%":[122],"18%":[124],"relative":[125,156],"equal":[126,157],"error":[127,158],"rates,":[128,159],"respectively,":[129,160],"both":[131,162],"conditions.On":[136],"hard":[138],"40%":[153],"13%":[155],"conditions.To":[167],"enable":[168],"reproducibility":[169],"facilitate":[174],"research":[175],"into":[176],"verification,":[179],"made":[181],"our":[182,192],"code,":[183],"pretrained":[184],"models,":[185],"preprocessed":[187],"freely":[189],"available":[190],"in":[191],"GitHub":[193],"repository":[194],"1":[195],".":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
