{"id":"https://openalex.org/W4416819545","doi":"https://doi.org/10.1049/cit2.70092","title":"AVCLNet: Multimodal Multispeaker Tracking Network Using Audio\u2010Visual Contrastive Learning","display_name":"AVCLNet: Multimodal Multispeaker Tracking Network Using Audio\u2010Visual Contrastive Learning","publication_year":2025,"publication_date":"2025-11-29","ids":{"openalex":"https://openalex.org/W4416819545","doi":"https://doi.org/10.1049/cit2.70092"},"language":"en","primary_location":{"id":"doi:10.1049/cit2.70092","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70092","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70092","source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037341144","display_name":"Yihan Li","orcid":"https://orcid.org/0009-0009-9924-5529"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I4210111835","display_name":"Osaka Health Science University","ror":"https://ror.org/01tvqd679","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210111835"]},{"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":true,"raw_author_name":"Yihan Li","raw_affiliation_strings":["College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","Graduate School of Engineering Science The University of Osaka  Osaka Japan"],"raw_orcid":"https://orcid.org/0009-0009-9924-5529","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science The University of Osaka  Osaka Japan","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212","https://openalex.org/I4210111835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037341144","display_name":"Yihan Li","orcid":"https://orcid.org/0009-0009-9924-5529"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I4210111835","display_name":"Osaka Health Science University","ror":"https://ror.org/01tvqd679","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210111835"]},{"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 China","Graduate School of Engineering Science The University of Osaka  Osaka Japan"],"raw_orcid":"https://orcid.org/0009-0009-9924-5529","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science The University of Osaka  Osaka Japan","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212","https://openalex.org/I4210111835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071411382","display_name":"Yidi Li","orcid":"https://orcid.org/0000-0002-5236-7010"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I4210111835","display_name":"Osaka Health Science University","ror":"https://ror.org/01tvqd679","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210111835"]},{"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 China","Graduate School of Engineering Science The University of Osaka  Osaka 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 China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science The University of Osaka  Osaka Japan","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212","https://openalex.org/I4210111835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071411382","display_name":"Yidi Li","orcid":"https://orcid.org/0000-0002-5236-7010"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I4210111835","display_name":"Osaka Health Science University","ror":"https://ror.org/01tvqd679","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210111835"]},{"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":true,"raw_author_name":"Yidi Li","raw_affiliation_strings":["College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","Graduate School of Engineering Science The University of Osaka  Osaka 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 China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science The University of Osaka  Osaka Japan","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212","https://openalex.org/I4210111835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049455762","display_name":"Zhenhuan Xu","orcid":"https://orcid.org/0000-0001-5720-7051"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]},{"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"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Zhenhuan Xu","raw_affiliation_strings":["College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","Peking University, Shenzhen Graduate School  Shenzhen China","Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology  Shenzhen 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 China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Peking University, Shenzhen Graduate School  Shenzhen China","institution_ids":["https://openalex.org/I4210128628"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology  Shenzhen China","institution_ids":["https://openalex.org/I88101031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088837669","display_name":"Hao Guo","orcid":"https://orcid.org/0000-0002-5934-7020"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I4210111835","display_name":"Osaka Health Science University","ror":"https://ror.org/01tvqd679","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210111835"]},{"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":"Hao Guo","raw_affiliation_strings":["College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","Graduate School of Engineering Science The University of Osaka  Osaka Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology Taiyuan University of Technology  Taiyuan China","institution_ids":["https://openalex.org/I9086337"]},{"raw_affiliation_string":"Graduate School of Engineering Science The University of Osaka  Osaka Japan","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212","https://openalex.org/I4210111835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]},{"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":"Mengyuan Liu","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology  Shenzhen China","Peking University, Shenzhen Graduate School  Shenzhen China"],"raw_orcid":"https://orcid.org/0000-0002-6332-8316","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology  Shenzhen China","institution_ids":["https://openalex.org/I88101031"]},{"raw_affiliation_string":"Peking University, Shenzhen Graduate School  Shenzhen China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087787651","display_name":"Weiwei Wan","orcid":"https://orcid.org/0000-0002-0058-2819"},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I4210111835","display_name":"Osaka Health Science University","ror":"https://ror.org/01tvqd679","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210111835"]},{"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 Japan"],"raw_orcid":"https://orcid.org/0000-0002-0058-2819","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science The University of Osaka  Osaka Japan","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212","https://openalex.org/I4210111835"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037341144","https://openalex.org/A5049455762","https://openalex.org/A5071411382"],"corresponding_institution_ids":["https://openalex.org/I14314212","https://openalex.org/I4210111835","https://openalex.org/I4210128628","https://openalex.org/I88101031","https://openalex.org/I9086337","https://openalex.org/I98285908"],"apc_list":{"value":2200,"currency":"USD","value_usd":2200},"apc_paid":{"value":2200,"currency":"USD","value_usd":2200},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35650118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"1","first_page":"238","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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":0.9916999936103821,"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/T11309","display_name":"Music and Audio Processing","score":0.0015999999595806003,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/robustness","display_name":"Robustness (evolution)","score":0.7858999967575073},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.46869999170303345},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.41350001096725464},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4059999883174896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.36410000920295715},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.35989999771118164},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3418999910354614}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7858999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741100013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6039000153541565},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1049/cit2.70092","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70092","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70092","source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01056:0007231291","is_oa":true,"landing_page_url":"https://hdl.handle.net/11094/103583","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1049/cit2.70092","is_oa":true,"landing_page_url":"https://doi.org/10.1049/cit2.70092","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.70092","source":{"id":"https://openalex.org/S2898415742","display_name":"CAAI Transactions on Intelligence Technology","issn_l":"2468-2322","issn":["2468-2322","2468-6557"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CAAI Transactions on Intelligence Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2464445471","display_name":null,"funder_award_id":"62403345","funder_id":"https://openalex.org/F4320336806","funder_display_name":"National Natural Science Foundation of China - State Grid Corporation Joint Fund for Smart Grid"},{"id":"https://openalex.org/G6691204964","display_name":null,"funder_award_id":"62403345","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"},{"id":"https://openalex.org/F4320327913","display_name":"ShanXi Science and Technology Department","ror":null},{"id":"https://openalex.org/F4320336806","display_name":"National Natural Science Foundation of China - State Grid Corporation Joint Fund for Smart Grid","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416819545.pdf","grobid_xml":"https://content.openalex.org/works/W4416819545.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1908118577","https://openalex.org/W1974793196","https://openalex.org/W2023100145","https://openalex.org/W2081074144","https://openalex.org/W2088725063","https://openalex.org/W2100152238","https://openalex.org/W2142612029","https://openalex.org/W2167206042","https://openalex.org/W2316138215","https://openalex.org/W2517955251","https://openalex.org/W2917254586","https://openalex.org/W2918984654","https://openalex.org/W2969987364","https://openalex.org/W2989954484","https://openalex.org/W3034751264","https://openalex.org/W3126757411","https://openalex.org/W3135222947","https://openalex.org/W3213737329","https://openalex.org/W4287123540","https://openalex.org/W4292262107","https://openalex.org/W4296069282","https://openalex.org/W4312367758","https://openalex.org/W4385575022","https://openalex.org/W4386498243","https://openalex.org/W4387394243","https://openalex.org/W4390498922","https://openalex.org/W4393181080","https://openalex.org/W4394892234","https://openalex.org/W4401980715"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Audio\u2010visual":[1],"speaker":[2,33,66],"tracking":[3,39,74,78,89],"aims":[4],"to":[5,72,141,152],"determine":[6],"the":[7,13,28,63,123,154,162,175,189],"locations":[8],"of":[9,32,65,156],"multiple":[10],"speakers":[11],"in":[12,36,161,203],"scene":[14],"by":[15,173],"leveraging":[16],"signals":[17],"captured":[18],"from":[19],"multisensor":[20],"platforms.":[21],"Multimodal":[22],"fusion":[23],"methods":[24],"can":[25],"improve":[26,153],"both":[27],"accuracy":[29,75],"and":[30,53,69,76,118,145,177,191],"robustness":[31,202],"tracking.":[34],"However,":[35],"complex":[37],"multispeaker":[38,88,204],"scenarios,":[40],"critical":[41],"challenges":[42],"such":[43],"as":[44],"cross\u2010modal":[45,111,115,143],"feature":[46,112,116],"discrepancy,":[47],"weak":[48,131,157],"sound":[49,132,158],"source":[50,133],"localisation":[51],"ambiguity":[52],"frequent":[54,183],"identity":[55,67,184],"switch":[56,185],"errors":[57],"remain":[58],"unresolved,":[59],"which":[60,109,137],"severely":[61],"hinder":[62],"modelling":[64],"consistency":[68],"consequently":[70],"lead":[71],"degraded":[73],"unstable":[77],"trajectories.":[79],"To":[80],"this":[81,83],"end,":[82],"paper":[84],"proposes":[85],"a":[86,102,129,147,166],"multimodal":[87],"network":[90],"using":[91],"audio\u2010visual":[92,106,124],"contrastive":[93,107],"learning":[94],"(AVCLNet).":[95],"By":[96],"integrating":[97],"heterogeneous":[98],"modal":[99],"representations":[100],"into":[101],"unified":[103],"space":[104],"through":[105],"learning,":[108],"facilitates":[110],"alignment,":[113],"mitigates":[114],"bias":[117],"enhances":[119],"identity\u2010consistent":[120],"representations.":[121],"In":[122],"measurement":[125],"stage,":[126],"we":[127],"design":[128],"vision\u2010guided":[130],"weighted":[134,150],"enhancement":[135],"method,":[136],"leverages":[138],"visual":[139],"cues":[140],"establish":[142],"mappings":[144],"employs":[146],"spatiotemporal":[148],"dynamic":[149],"mechanism":[151],"detectability":[155],"sources.":[159],"Furthermore,":[160],"data":[163],"association":[164],"phase,":[165],"dual":[167],"geometric":[168,180],"constraint":[169],"strategy":[170],"is":[171],"introduced":[172],"combining":[174],"2D":[176],"3D":[178],"spatial":[179],"information,":[181],"reducing":[182],"errors.":[186],"Experiments":[187],"on":[188],"AV16.3":[190],"CAV3D":[192],"datasets":[193],"show":[194],"that":[195],"AVCLNet":[196],"outperforms":[197],"state\u2010of\u2010the\u2010art":[198],"methods,":[199],"demonstrating":[200],"superior":[201],"scenarios.":[205]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-11-29T00:00:00"}
