{"id":"https://openalex.org/W3133481345","doi":"https://doi.org/10.1007/978-3-030-68780-9_26","title":"Cross-modal Deep Learning Applications: Audio-Visual Retrieval","display_name":"Cross-modal Deep Learning Applications: Audio-Visual Retrieval","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3133481345","doi":"https://doi.org/10.1007/978-3-030-68780-9_26","mag":"3133481345"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-68780-9_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-68780-9_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5068772612","display_name":"Cong Jin","orcid":"https://orcid.org/0000-0003-0464-9862"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Jin","raw_affiliation_strings":["School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371729","display_name":"Tian Zhang","orcid":"https://orcid.org/0000-0002-1284-1232"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China","School of Information and Engineering, Zhengzhou University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"School of Information and Engineering, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053790581","display_name":"Shouxun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouxun Liu","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101112071","display_name":"Yun Tie","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Tie","raw_affiliation_strings":["School of Information and Engineering, Zhengzhou University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101400717","display_name":"Xin Lv","orcid":"https://orcid.org/0000-0002-4843-7987"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lv","raw_affiliation_strings":["School of Animation and Digital Arts, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Animation and Digital Arts, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102970818","display_name":"Jianguang Li","orcid":"https://orcid.org/0000-0002-6551-8498"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguang Li","raw_affiliation_strings":["School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019031108","display_name":"Wencai Yan","orcid":"https://orcid.org/0000-0002-4198-2472"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wencai Yan","raw_affiliation_strings":["School of Information and Engineering, Zhengzhou University, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089718306","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0001-8979-8490"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Key Laboratory of Convergent Media and Intelligent Technology, Ministry of Education, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111899405","display_name":"Qian Xu","orcid":"https://orcid.org/0009-0008-1884-489X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Xu","raw_affiliation_strings":["School of Animation and Digital Arts, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Animation and Digital Arts, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062470096","display_name":"Yicong Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicong Guan","raw_affiliation_strings":["School of Animation and Digital Arts, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Animation and Digital Arts, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022412417","display_name":"Zhenggougou Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenggougou Yang","raw_affiliation_strings":["Broadcasting and Anchoring School, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Broadcasting and Anchoring School, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.7566,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90747155,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9896000027656555,"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/computer-science","display_name":"Computer science","score":0.885502815246582},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.669059157371521},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5724331140518188},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5689900517463684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5482115149497986},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5137942433357239},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5132881999015808},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5088258385658264},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.499267578125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4970441162586212},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4184868633747101},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4003976583480835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38175153732299805},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.244503915309906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.885502815246582},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.669059157371521},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5724331140518188},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5689900517463684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5482115149497986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5137942433357239},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5132881999015808},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5088258385658264},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.499267578125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4970441162586212},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4184868633747101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4003976583480835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38175153732299805},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.244503915309906},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-68780-9_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-68780-9_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W306648316","https://openalex.org/W1523385540","https://openalex.org/W1731081199","https://openalex.org/W1861492603","https://openalex.org/W1950117310","https://openalex.org/W2031458230","https://openalex.org/W2056935845","https://openalex.org/W2097117768","https://openalex.org/W2100235303","https://openalex.org/W2112912048","https://openalex.org/W2185175083","https://openalex.org/W2209982072","https://openalex.org/W2547411571","https://openalex.org/W2604397568","https://openalex.org/W2604490051","https://openalex.org/W2606473278","https://openalex.org/W2742097923","https://openalex.org/W2796667576","https://openalex.org/W2895347732","https://openalex.org/W2962968152","https://openalex.org/W2963807156","https://openalex.org/W2963885538","https://openalex.org/W2964271799","https://openalex.org/W2965896114","https://openalex.org/W2982247743","https://openalex.org/W3034498211","https://openalex.org/W6637618735"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2185469136","https://openalex.org/W2364594919","https://openalex.org/W2167092671","https://openalex.org/W2011264131","https://openalex.org/W1861706286","https://openalex.org/W2219338811","https://openalex.org/W2149583853","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
