{"id":"https://openalex.org/W4390395706","doi":"https://doi.org/10.1007/s11263-023-01950-3","title":"Joint Learning of Audio\u2013Visual Saliency Prediction and Sound Source Localization on Multi-face Videos","display_name":"Joint Learning of Audio\u2013Visual Saliency Prediction and Sound Source Localization on Multi-face Videos","publication_year":2023,"publication_date":"2023-12-29","ids":{"openalex":"https://openalex.org/W4390395706","doi":"https://doi.org/10.1007/s11263-023-01950-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-023-01950-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-023-01950-3","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","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/A5060267883","display_name":"Minglang Qiao","orcid":"https://orcid.org/0000-0002-9591-2568"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglang Qiao","raw_affiliation_strings":["School of Electronic and Information Engineering, Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068621276","display_name":"Yufan Liu","orcid":"https://orcid.org/0000-0002-8426-9335"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufan Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institution of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences and CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institution of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences and CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079385534","display_name":"Mai Xu","orcid":"https://orcid.org/0000-0002-0277-3301"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mai Xu","raw_affiliation_strings":["School of Electronic and Information Engineering, Beihang University, Beijing, 100191, China"],"raw_orcid":"https://orcid.org/0000-0002-0277-3301","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650157","display_name":"Xin Deng","orcid":"https://orcid.org/0000-0003-1257-694X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Deng","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109346446","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-5888-6735"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institution of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences and CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institution of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences and CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549594","display_name":"Weiming Hu","orcid":"https://orcid.org/0000-0001-9237-8825"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Hu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institution of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences and CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institution of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences and CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068743986","display_name":"Ali Borji","orcid":"https://orcid.org/0000-0001-8198-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Borji","raw_affiliation_strings":["Ali Borji is with Primer.AI Inc., San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ali Borji is with Primer.AI Inc., San Francisco, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079385534"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":1.7691,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86033506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"132","issue":"6","first_page":"2003","last_page":"2025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997000098228455,"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/T12032","display_name":"Multisensory perception and integration","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9941999912261963,"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":0.8351833820343018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6326649785041809},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6071860790252686},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6069207787513733},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.461936354637146},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46154409646987915},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4572945833206177},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.44787365198135376},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.42717245221138},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42053475975990295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41616925597190857},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.41305142641067505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38207727670669556},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2522647976875305},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09330198168754578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351833820343018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6326649785041809},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6071860790252686},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6069207787513733},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.461936354637146},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46154409646987915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4572945833206177},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.44787365198135376},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.42717245221138},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42053475975990295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41616925597190857},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.41305142641067505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38207727670669556},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2522647976875305},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09330198168754578},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-023-01950-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-023-01950-3","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1150375109","display_name":null,"funder_award_id":"62192785","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3168399153","display_name":null,"funder_award_id":"61876013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G336532420","display_name":null,"funder_award_id":"61922009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G388300612","display_name":null,"funder_award_id":"62250001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5548396881","display_name":null,"funder_award_id":"61972071","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6127711580","display_name":null,"funder_award_id":"62231002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6639821268","display_name":null,"funder_award_id":"61902401","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1420992503","https://openalex.org/W1485009520","https://openalex.org/W1510835000","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1959094031","https://openalex.org/W1985202143","https://openalex.org/W2013134489","https://openalex.org/W2056238658","https://openalex.org/W2094432440","https://openalex.org/W2121179941","https://openalex.org/W2128272608","https://openalex.org/W2135957164","https://openalex.org/W2151096523","https://openalex.org/W2155479901","https://openalex.org/W2156232986","https://openalex.org/W2164084182","https://openalex.org/W2168744723","https://openalex.org/W2169561119","https://openalex.org/W2169949291","https://openalex.org/W2212216676","https://openalex.org/W2213100575","https://openalex.org/W2295107390","https://openalex.org/W2330149154","https://openalex.org/W2332175535","https://openalex.org/W2341528187","https://openalex.org/W2395371822","https://openalex.org/W2400730599","https://openalex.org/W2419451029","https://openalex.org/W2422305492","https://openalex.org/W2558906385","https://openalex.org/W2604379605","https://openalex.org/W2612135493","https://openalex.org/W2612690371","https://openalex.org/W2740797387","https://openalex.org/W2756582047","https://openalex.org/W2804567257","https://openalex.org/W2883429621","https://openalex.org/W2913121856","https://openalex.org/W2932399282","https://openalex.org/W2949058392","https://openalex.org/W2951157442","https://openalex.org/W2962865004","https://openalex.org/W2962934715","https://openalex.org/W2962960500","https://openalex.org/W2962965915","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963503775","https://openalex.org/W2963581854","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2969316698","https://openalex.org/W2986131415","https://openalex.org/W2986131686","https://openalex.org/W3011978462","https://openalex.org/W3016098309","https://openalex.org/W3034702511","https://openalex.org/W3081573667","https://openalex.org/W3092603041","https://openalex.org/W3092714093","https://openalex.org/W3097337310","https://openalex.org/W3099561715","https://openalex.org/W3100302033","https://openalex.org/W3101840568","https://openalex.org/W3101998545","https://openalex.org/W3138095408","https://openalex.org/W3149149291","https://openalex.org/W3170088426","https://openalex.org/W3202477427","https://openalex.org/W4212774754","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3011070339","https://openalex.org/W2108013559","https://openalex.org/W2288611238","https://openalex.org/W1485388545","https://openalex.org/W3121690864","https://openalex.org/W2384738070","https://openalex.org/W2349923422","https://openalex.org/W2159006459","https://openalex.org/W2143986816","https://openalex.org/W2056404380"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
