{"id":"https://openalex.org/W3195861134","doi":"https://doi.org/10.1145/3469213.3470254","title":"Audio-Visual Salieny Network with Audio Attention Module","display_name":"Audio-Visual Salieny Network with Audio Attention Module","publication_year":2021,"publication_date":"2021-05-28","ids":{"openalex":"https://openalex.org/W3195861134","doi":"https://doi.org/10.1145/3469213.3470254","mag":"3195861134"},"language":"en","primary_location":{"id":"doi:10.1145/3469213.3470254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469213.3470254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 2nd International Conference on Artificial Intelligence and Information Systems","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/A5052699472","display_name":"Shuaiyang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuaiyang Cheng","raw_affiliation_strings":["Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622644","display_name":"Xing Gao","orcid":"https://orcid.org/0000-0002-0401-5125"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Gao","raw_affiliation_strings":["Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103113014","display_name":"Liang Song","orcid":"https://orcid.org/0000-0003-4251-3798"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Song","raw_affiliation_strings":["Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014076600","display_name":"Jianbing Xiahou","orcid":"https://orcid.org/0000-0002-9715-4502"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbing Xiahou","raw_affiliation_strings":["Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052699472"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43989182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9876000285148621,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8405446410179138},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.8358150720596313},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5979795455932617},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5711191892623901},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5376549959182739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5361964702606201},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4927971661090851},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47063586115837097},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47026070952415466},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44645795226097107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4330425560474396},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4316176474094391},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26793068647384644},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21572661399841309},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11748448014259338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405446410179138},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8358150720596313},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5979795455932617},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5711191892623901},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5376549959182739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5361964702606201},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4927971661090851},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47063586115837097},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47026070952415466},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44645795226097107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4330425560474396},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4316176474094391},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26793068647384644},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21572661399841309},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11748448014259338},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469213.3470254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469213.3470254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 2nd International Conference on Artificial Intelligence and Information Systems","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":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1152443276","https://openalex.org/W1920297912","https://openalex.org/W2119577735","https://openalex.org/W2155479901","https://openalex.org/W2336525740","https://openalex.org/W2498738402","https://openalex.org/W2529272619","https://openalex.org/W2533370895","https://openalex.org/W2544224704","https://openalex.org/W2581141993","https://openalex.org/W2619947201","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2946259291","https://openalex.org/W2946520073","https://openalex.org/W2963503775","https://openalex.org/W2963560594","https://openalex.org/W3034287518","https://openalex.org/W3034658206","https://openalex.org/W3035753399","https://openalex.org/W3111024204","https://openalex.org/W4234552385","https://openalex.org/W4293665662","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6739901393","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W3004170508","https://openalex.org/W1611900921","https://openalex.org/W2405044261","https://openalex.org/W1603949574","https://openalex.org/W2379113420","https://openalex.org/W3173628312","https://openalex.org/W3007022793","https://openalex.org/W2604447241","https://openalex.org/W4360979418","https://openalex.org/W2897411159"],"abstract_inverted_index":{"Recently,":[0],"inspired":[1],"by":[2],"the":[3,15,17,46,58,67,72,110,114,121,127],"fact":[4],"that":[5,101],"people":[6],"rely":[7],"on":[8,76,109,120],"visual":[9],"and":[10,32,35,87],"audio":[11,47,68,84,103,134],"modalities":[12],"to":[13,90],"observe":[14],"world,":[16],"audio-visual":[18,52,94],"multi-modal":[19,53],"method":[20],"for":[21,132],"computer":[22],"vision":[23],"tasks":[24],"in":[25],"deep":[26],"learning":[27],"networks":[28,54],"has":[29,40,106],"attracted":[30],"more":[31,33],"attention,":[34],"a":[36,81,91],"lot":[37],"of":[38,50,60,113,123,129],"work":[39],"been":[41],"achieved":[42],"good":[43],"progress.":[44],"However,":[45],"feature":[48,135],"extraction":[49],"most":[51],"only":[55],"simply":[56],"extracts":[57],"features":[59],"input":[61],"audio,":[62],"but":[63,117],"rarely":[64],"considers":[65],"whether":[66],"noise":[69],"will":[70],"influence":[71],"prediction":[73,96,111],"results.":[74],"Based":[75],"this":[77,130],"fact,":[78],"we":[79],"propose":[80],"detachable":[82],"CNN":[83],"attention":[85,104],"module":[86,105,131],"apply":[88],"it":[89],"current":[92],"classic":[93],"saliency":[95],"network.":[97],"Experimental":[98],"results":[99],"demonstrate":[100],"our":[102],"little":[107],"impact":[108],"speed":[112],"existing":[115],"network":[116],"significant":[118],"improvement":[119],"accuracy":[122],"prediction,":[124],"which":[125],"proves":[126],"effectiveness":[128],"enhancing":[133],"extraction.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
