{"id":"https://openalex.org/W4402703978","doi":"https://doi.org/10.1016/j.patcog.2026.113916","title":"Global\u2013local distillation network-based audio\u2013visual speaker tracking with incomplete modalities","display_name":"Global\u2013local distillation network-based audio\u2013visual speaker tracking with incomplete modalities","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W4402703978","doi":"https://doi.org/10.1016/j.patcog.2026.113916"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113916","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113916","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.14585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071411382","display_name":"Yidi Li","orcid":"https://orcid.org/0000-0002-5236-7010"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Yidi Li","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, 030024, China","Graduate School of Engineering Science, the University of Osaka, Osaka, 565-0871, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5236-7010","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, 030024, China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science, the University of Osaka, Osaka, 565-0871, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066412702","display_name":"Yihan Li","orcid":"https://orcid.org/0009-0000-1999-8964"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Yihan Li","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, 030024, China","Graduate School of Engineering Science, the University of Osaka, Osaka, 565-0871, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, 030024, China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science, the University of Osaka, Osaka, 565-0871, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112869922","display_name":"Zhenhuan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenhuan Xu","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, 030024, China"],"raw_orcid":"https://orcid.org/0000-0001-5720-7051","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan, 030024, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weiwei Wan","orcid":"https://orcid.org/0000-0002-0058-2819"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Weiwei Wan","raw_affiliation_strings":["Graduate School of Engineering Science, the University of Osaka, Osaka, 565-0871, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0058-2819","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, the University of Osaka, Osaka, 565-0871, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I88101031","display_name":"Immersion (United States)","ror":"https://ror.org/02qgx4h83","country_code":"US","type":"company","lineage":["https://openalex.org/I88101031"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen, 518055, China","State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, 518055, China"],"raw_orcid":"https://orcid.org/0000-0002-7498-6541","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I88101031"]},{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112869922"],"corresponding_institution_ids":["https://openalex.org/I9086337"],"apc_list":{"value":2710,"currency":"USD","value_usd":2710},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0064844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"179","issue":null,"first_page":"113916","last_page":"113916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9807000160217285,"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/audio-visual","display_name":"Audio visual","score":0.7620934247970581},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6781177520751953},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5414377450942993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5366325974464417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44250428676605225},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4123249650001526},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17558446526527405},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16769558191299438},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06541842222213745}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7620934247970581},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6781177520751953},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5414377450942993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5366325974464417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44250428676605225},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4123249650001526},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17558446526527405},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16769558191299438},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06541842222213745},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.patcog.2026.113916","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113916","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2408.14585","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.14585","pdf_url":"https://arxiv.org/pdf/2408.14585","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.14585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.14585","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.14585","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.14585","pdf_url":"https://arxiv.org/pdf/2408.14585","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327913","display_name":"ShanXi Science and Technology Department","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2185469136","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2011264131","https://openalex.org/W3137890128","https://openalex.org/W1984634519"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}
