{"id":"https://openalex.org/W4404239382","doi":"https://doi.org/10.1109/ijcb62174.2024.10744460","title":"Straight Through Gumbel Softmax Estimator based Bimodal Neural Architecture Search for Audio-Visual Deepfake Detection","display_name":"Straight Through Gumbel Softmax Estimator based Bimodal Neural Architecture Search for Audio-Visual Deepfake Detection","publication_year":2024,"publication_date":"2024-09-15","ids":{"openalex":"https://openalex.org/W4404239382","doi":"https://doi.org/10.1109/ijcb62174.2024.10744460"},"language":"en","primary_location":{"id":"doi:10.1109/ijcb62174.2024.10744460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb62174.2024.10744460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-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/A5093104464","display_name":"Aravinda Reddy PN","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aravinda Reddy PN","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073391891","display_name":"Raghavendra Ramachandra","orcid":"https://orcid.org/0000-0003-0484-3956"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Raghavendra Ramachandra","raw_affiliation_strings":["Norwegian University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103596982","display_name":"Krothapalli Sreenivasa Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Krothapalli Sreenivasa Rao","raw_affiliation_strings":["Norwegian University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032809289","display_name":"Pabitra Mitra","orcid":"https://orcid.org/0000-0002-1908-9813"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025662893","display_name":"Vinod Rathod","orcid":"https://orcid.org/0009-0002-4528-2681"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinod Rathod","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093104464"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":1.2464,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81559763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9835000038146973,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9835000038146973,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9632999897003174,"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":0.9199000000953674,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gumbel-distribution","display_name":"Gumbel distribution","score":0.7877483367919922},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6865320205688477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6371538043022156},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.49988460540771484},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.46679267287254333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45961424708366394},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42244717478752136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35978206992149353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.356668084859848},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25795525312423706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24388962984085083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.242534339427948},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07182812690734863}],"concepts":[{"id":"https://openalex.org/C137610916","wikidata":"https://www.wikidata.org/wiki/Q1096862","display_name":"Gumbel distribution","level":3,"score":0.7877483367919922},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6865320205688477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6371538043022156},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49988460540771484},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.46679267287254333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45961424708366394},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42244717478752136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35978206992149353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.356668084859848},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25795525312423706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24388962984085083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.242534339427948},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07182812690734863},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb62174.2024.10744460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb62174.2024.10744460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2341528187","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2904573504","https://openalex.org/W2947168943","https://openalex.org/W2951104886","https://openalex.org/W3033711348","https://openalex.org/W3081492798","https://openalex.org/W3092767330","https://openalex.org/W3093010840","https://openalex.org/W3093077034","https://openalex.org/W3096025930","https://openalex.org/W3101631197","https://openalex.org/W3101998545","https://openalex.org/W3152844947","https://openalex.org/W3154326567","https://openalex.org/W4214691743","https://openalex.org/W4214876496","https://openalex.org/W4287026043","https://openalex.org/W4292791230","https://openalex.org/W4312095999","https://openalex.org/W4372260514","https://openalex.org/W4385245566","https://openalex.org/W4385805162","https://openalex.org/W4386076652","https://openalex.org/W4386928847","https://openalex.org/W6608846882","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6731370813","https://openalex.org/W6752515464","https://openalex.org/W6757599822","https://openalex.org/W6762663619","https://openalex.org/W6784541143","https://openalex.org/W6799942944"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W2565378226","https://openalex.org/W4294294142"],"abstract_inverted_index":{"Deepfakes":[0],"are":[1],"a":[2,71,81,108],"major":[3],"security":[4],"risk":[5],"for":[6,30],"biometric":[7],"authentication.":[8],"This":[9],"technology":[10],"creates":[11],"realistic":[12],"fake":[13],"videos":[14],"that":[15,22,119],"can":[16],"impersonate":[17],"real":[18],"people,":[19],"fooling":[20],"systems":[21],"rely":[23,36],"on":[24,37,138],"facial":[25],"features":[26,96],"and":[27,45,57,92,132,141],"voice":[28],"patterns":[29],"identification.":[31],"Existing":[32],"multimodal":[33,76],"deepfake":[34],"detectors":[35],"conventional":[38],"fusion":[39,77,110],"methods,":[40],"such":[41,129],"as":[42,130],"majority":[43],"rule":[44],"ensemble":[46],"voting,":[47],"which":[48],"often":[49],"struggle":[50],"to":[51,53,74],"adapt":[52],"changing":[54],"data":[55],"characteristics":[56],"complex":[58],"patterns.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"introduce":[64],"the":[65,85,88,105,121,139],"Straight-through":[66],"Gumbel-Softmax":[67],"(STGS)":[68],"framework,":[69],"offering":[70],"comprehensive":[72],"approach":[73],"search":[75,83],"model":[78,153],"architectures.":[79],"Using":[80],"two-level":[82],"approach,":[84],"framework":[86],"optimizes":[87],"network":[89],"architecture,":[90],"parameters,":[91],"performance.":[93],"Initially,":[94],"crucial":[95],"were":[97],"efficiently":[98],"identified":[99],"from":[100,114],"backbone":[101],"networks,":[102],"whereas":[103],"within":[104],"cell":[106],"structure,":[107],"weighted":[109],"operation":[111],"integrated":[112],"information":[113],"various":[115],"sources.":[116],"An":[117],"architecture":[118],"maximizes":[120],"classification":[122],"performance":[123],"is":[124],"derived":[125],"by":[126],"varying":[127],"parameters":[128],"temperature":[131],"sampling":[133],"time.":[134],"The":[135],"experimental":[136],"results":[137],"FakeAVCeleb":[140],"SWAN-DF":[142],"datasets":[143],"demonstrated":[144],"an":[145],"impressive":[146],"AUC":[147],"value":[148],"94.4%":[149],"achieved":[150],"with":[151],"minimal":[152],"parameters.":[154],"https://github.com/Aravinda27/STGS-BMNAS":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}