{"id":"https://openalex.org/W4407354906","doi":"https://doi.org/10.1007/s10044-025-01414-z","title":"Enhancing semantic audio-visual representation learning with supervised multi-scale attention","display_name":"Enhancing semantic audio-visual representation learning with supervised multi-scale attention","publication_year":2025,"publication_date":"2025-02-11","ids":{"openalex":"https://openalex.org/W4407354906","doi":"https://doi.org/10.1007/s10044-025-01414-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10044-025-01414-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10044-025-01414-z","pdf_url":null,"source":{"id":"https://openalex.org/S45497385","display_name":"Pattern Analysis and Applications","issn_l":"1433-7541","issn":["1433-7541","1433-755X"],"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":"Pattern Analysis and Applications","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/A5100353055","display_name":"Jiwei Zhang","orcid":"https://orcid.org/0000-0003-4494-8648"},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiwei Zhang","raw_affiliation_strings":["Department of Systems Engineering, Wakayama University, 930 Sakaedani, Wakayama, 640-8441, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, Wakayama University, 930 Sakaedani, Wakayama, 640-8441, Japan","institution_ids":["https://openalex.org/I75198481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University, 1-3-2 Kagamiyama, Higashi-Hiroshima City, Hiroshima, 735-8511, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University, 1-3-2 Kagamiyama, Higashi-Hiroshima City, Hiroshima, 735-8511, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033599028","display_name":"Suhua Tang","orcid":"https://orcid.org/0000-0002-5784-8411"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Suhua Tang","raw_affiliation_strings":["Graduate School of Informatics and Engineering, The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, The University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo, 182-8585, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"GuoJun Qi","raw_affiliation_strings":["Westlake University, No. 600 Dunyu Road, Sandun Town, Xihu District, Hangzhou, 310-030, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Westlake University, No. 600 Dunyu Road, Sandun Town, Xihu District, Hangzhou, 310-030, Zhejiang, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100555109","display_name":"Haiyuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I924388194","display_name":"Murata (Japan)","ror":"https://ror.org/04hd8bd67","country_code":"JP","type":"company","lineage":["https://openalex.org/I924388194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haiyuan Wu","raw_affiliation_strings":["Sense Time Japan Co., Ltd., 1-5-1 Chofugaoka, Kyoto, Kyoto, 604-0022, Japan"],"affiliations":[{"raw_affiliation_string":"Sense Time Japan Co., Ltd., 1-5-1 Chofugaoka, Kyoto, Kyoto, 604-0022, Japan","institution_ids":["https://openalex.org/I924388194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073076975","display_name":"Hirotaka Hachiya","orcid":"https://orcid.org/0000-0003-3748-4101"},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirotaka Hachiya","raw_affiliation_strings":["Department of Systems Engineering, Wakayama University, 930 Sakaedani, Wakayama, 640-8441, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering, Wakayama University, 930 Sakaedani, Wakayama, 640-8441, Japan","institution_ids":["https://openalex.org/I75198481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100745222"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":6.2128,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9559572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"28","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9865000247955322,"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":0.7065033912658691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386815667152405},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.53327476978302},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5086270570755005},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5049455761909485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46799060702323914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41180139780044556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3828347623348236},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1495635211467743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065033912658691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386815667152405},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.53327476978302},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5086270570755005},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5049455761909485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46799060702323914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41180139780044556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3828347623348236},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1495635211467743},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10044-025-01414-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10044-025-01414-z","pdf_url":null,"source":{"id":"https://openalex.org/S45497385","display_name":"Pattern Analysis and Applications","issn_l":"1433-7541","issn":["1433-7541","1433-755X"],"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":"Pattern Analysis and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1726806267","https://openalex.org/W1937059634","https://openalex.org/W1955857676","https://openalex.org/W1964073652","https://openalex.org/W1998847750","https://openalex.org/W2071207147","https://openalex.org/W2096733369","https://openalex.org/W2107407880","https://openalex.org/W2130055251","https://openalex.org/W2186500555","https://openalex.org/W2266728343","https://openalex.org/W2295088417","https://openalex.org/W2520774990","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2752345995","https://openalex.org/W2765440071","https://openalex.org/W2908965201","https://openalex.org/W2919115771","https://openalex.org/W2949588459","https://openalex.org/W2954672622","https://openalex.org/W2962968152","https://openalex.org/W2963288100","https://openalex.org/W2963633722","https://openalex.org/W2963807156","https://openalex.org/W2964109005","https://openalex.org/W2964216321","https://openalex.org/W2967957126","https://openalex.org/W3017343282","https://openalex.org/W3041053424","https://openalex.org/W3048939150","https://openalex.org/W3096831136","https://openalex.org/W3099638501","https://openalex.org/W3152602106","https://openalex.org/W4200631412","https://openalex.org/W4249992252","https://openalex.org/W4309762704","https://openalex.org/W4312367758","https://openalex.org/W4384823712","https://openalex.org/W4387967957","https://openalex.org/W4392980395","https://openalex.org/W4408345615","https://openalex.org/W6600654476","https://openalex.org/W6632013632"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
