{"id":"https://openalex.org/W4312886874","doi":"https://doi.org/10.1109/tmm.2022.3222936","title":"Looking and Hearing Into Details: Dual-Enhanced Siamese Adversarial Network for Audio-Visual Matching","display_name":"Looking and Hearing Into Details: Dual-Enhanced Siamese Adversarial Network for Audio-Visual Matching","publication_year":2022,"publication_date":"2022-11-17","ids":{"openalex":"https://openalex.org/W4312886874","doi":"https://doi.org/10.1109/tmm.2022.3222936"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3222936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3222936","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5100784264","display_name":"Jiaxiang Wang","orcid":"https://orcid.org/0000-0003-3059-798X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxiang Wang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017558628","display_name":"Aihua Zheng","orcid":"https://orcid.org/0000-0002-9820-4743"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aihua Zheng","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030720334","display_name":"Jin Tang","orcid":"https://orcid.org/0000-0001-8375-3590"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Tang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107117636","display_name":"Bin Luo","orcid":"https://orcid.org/0000-0002-1414-3307"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Luo","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100784264"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":1.6355,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83796219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"7505","last_page":"7516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T11448","display_name":"Face recognition and analysis","score":0.9980999827384949,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9965000152587891,"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":0.8293789625167847},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7997385263442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6553265452384949},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5552371740341187},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5529838800430298},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5445679426193237},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5176253914833069},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.48557111620903015},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4838930070400238},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48192739486694336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44409433007240295},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4317898452281952},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.359674870967865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09074375033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293789625167847},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7997385263442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553265452384949},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5552371740341187},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5529838800430298},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5445679426193237},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5176253914833069},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.48557111620903015},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4838930070400238},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48192739486694336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44409433007240295},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4317898452281952},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.359674870967865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09074375033378601},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3222936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3222936","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[{"id":"https://openalex.org/G218645354","display_name":null,"funder_award_id":"62102344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3254430106","display_name":null,"funder_award_id":"61976002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2019111214","https://openalex.org/W2066078528","https://openalex.org/W2096733369","https://openalex.org/W2194775991","https://openalex.org/W2227324914","https://openalex.org/W2325939864","https://openalex.org/W2726515241","https://openalex.org/W2804078698","https://openalex.org/W2904949947","https://openalex.org/W2909680570","https://openalex.org/W2945210081","https://openalex.org/W2948037078","https://openalex.org/W2951237705","https://openalex.org/W2963026686","https://openalex.org/W2963351448","https://openalex.org/W2963467339","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964216321","https://openalex.org/W2966146145","https://openalex.org/W2967515867","https://openalex.org/W2967957126","https://openalex.org/W2997300818","https://openalex.org/W2997819898","https://openalex.org/W2998039742","https://openalex.org/W3007589762","https://openalex.org/W3034725201","https://openalex.org/W3035186652","https://openalex.org/W3093411628","https://openalex.org/W3105352633","https://openalex.org/W3118548710","https://openalex.org/W3154807520","https://openalex.org/W3177326298","https://openalex.org/W3182657421","https://openalex.org/W3205193540","https://openalex.org/W3214311327","https://openalex.org/W4255501777","https://openalex.org/W4292958273","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6752378368","https://openalex.org/W6752791795","https://openalex.org/W6783539077","https://openalex.org/W6841484515"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W2965546495","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4389116644","https://openalex.org/W4310988119"],"abstract_inverted_index":{"Audio-visual":[0],"cross-modal":[1,41,73,124],"matching":[2],"aims":[3],"to":[4,39,63,82,105,112,132,156,160],"explore":[5],"the":[6,20,59,102,107,114,120,158,163,175,178],"intrinsic":[7],"correspondence":[8],"between":[9,25],"face":[10],"images":[11,27],"and":[12,28,67,141],"audio":[13],"clips.":[14],"Existing":[15],"methods":[16],"usually":[17],"focus":[18,161],"on":[19,162,170],"salient":[21,66,94,99,140],"features":[22,69,86,100,118,143],"of":[23,116,122,177],"identities":[24],"visual":[26],"voice":[29],"clips,":[30],"while":[31,97],"neglecting":[32],"their":[33],"subtle":[34,68,85,117,142],"differences,":[35],"which":[36,57],"are":[37],"crucial":[38],"distinguishing":[40],"samples.":[42],"To":[43],"deal":[44],"with":[45],"this":[46],"problem,":[47],"we":[48,76,126,149],"propose":[49,150],"a":[50,78,90,128,145],"novel":[51],"Dual-enhanced":[52],"Siamese":[53],"Adversarial":[54],"Network":[55],"(DSANet),":[56],"pursues":[58],"adversarial":[60,130],"dual":[61,79],"enhancement":[62,80],"highlight":[64],"both":[65,138],"for":[70,93,137],"robust":[71],"audio-visual":[72],"matching.":[74],"First,":[75],"designed":[77],"mechanism":[81],"enhance":[83],"potential":[84],"by":[87],"randomly":[88],"selecting":[89],"region":[91,104],"feature":[92,95,164],"suppression,":[96],"enhancing":[98],"in":[101,119,144],"corresponding":[103],"ensure":[106],"global":[108],"discriminative":[109],"ability.":[110],"Second,":[111],"establish":[113],"correlation":[115],"process":[121],"eliminating":[123],"heterogeneity,":[125],"design":[127],"siamese":[129],"structure":[131],"perform":[133],"modal":[134],"heterogeneity":[135],"elimination":[136],"enhanced":[139],"parallel":[146],"manner.":[147],"Moreover,":[148],"an":[151],"adaptive":[152],"masked":[153],"cross-entropy":[154],"loss":[155],"force":[157],"network":[159],"differences":[165],"among":[166],"hard":[167],"classes.":[168],"Experiments":[169],"public":[171],"benchmark":[172],"datasets":[173],"validate":[174],"effectiveness":[176],"proposed":[179],"algorithm.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}