{"id":"https://openalex.org/W4386596890","doi":"https://doi.org/10.1109/icip49359.2023.10222739","title":"Video-Music Retrieval with Fine-Grained Cross-Modal Alignment","display_name":"Video-Music Retrieval with Fine-Grained Cross-Modal Alignment","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386596890","doi":"https://doi.org/10.1109/icip49359.2023.10222739"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222739","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081680514","display_name":"Yuki Era","orcid":"https://orcid.org/0009-0007-6196-8153"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Era","raw_affiliation_strings":["Hokkaido University,School of Engineering,Japan","School of Engineering, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,School of Engineering,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"School of Engineering, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033215072","display_name":"Keisuke Maeda","orcid":"https://orcid.org/0000-0001-8039-3462"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Maeda","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan","Faculty of Information Science and Technology, Hokkaido University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]},{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2005","last_page":"2009"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9854000210762024,"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":0.7650784850120544},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.623424768447876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5439143776893616},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5079482197761536},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4741874635219574},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.45740604400634766},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.4285743534564972},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10290417075157166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650784850120544},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.623424768447876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439143776893616},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5079482197761536},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4741874635219574},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.45740604400634766},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.4285743534564972},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10290417075157166},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222739","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7580542989","display_name":null,"funder_award_id":"JP23K11211","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8595477435","display_name":null,"funder_award_id":"JP23K11141","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8739887802","display_name":null,"funder_award_id":"JP21H03456","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1506450374","https://openalex.org/W1977145863","https://openalex.org/W1979378996","https://openalex.org/W2011577046","https://openalex.org/W2022329870","https://openalex.org/W2052872069","https://openalex.org/W2113305835","https://openalex.org/W2118253129","https://openalex.org/W2119061765","https://openalex.org/W2126700261","https://openalex.org/W2164184461","https://openalex.org/W2191779130","https://openalex.org/W2619383789","https://openalex.org/W2884436226","https://openalex.org/W2903662161","https://openalex.org/W2962960500","https://openalex.org/W2962970472","https://openalex.org/W2963066677","https://openalex.org/W2999723590","https://openalex.org/W3035532688","https://openalex.org/W3128803313","https://openalex.org/W3162322471","https://openalex.org/W3204221554","https://openalex.org/W3205213941","https://openalex.org/W3207290297","https://openalex.org/W4206517842","https://openalex.org/W4312249545","https://openalex.org/W6770639321"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"This":[0,94],"paper":[1],"presents":[2],"a":[3,15],"novel":[4],"video-music":[5,107,119],"retrieval":[6,71,80,123,135],"method":[7,13,67,115,129],"for":[8,105],"videos":[9],"containing":[10],"humans.":[11],"Our":[12],"constructs":[14],"cross-modal":[16,70],"common":[17],"embedding":[18,33,91],"space":[19,34,92],"of":[20,49,63,137],"video":[21,85],"features":[22,29,55,58,86],"based":[23,35],"on":[24,36,73],"human":[25,101,121],"motion":[26,54,102],"and":[27,30,39,44,51,77,87,120,125],"music":[28,52,89,104],"aligns":[31],"the":[32,37,61,69,74,79,88,96,106,110,117,134,138],"beat":[38,43],"genre":[40,45],"information.":[41],"The":[42],"are":[46],"distinctive":[47],"properties":[48],"music,":[50],"relates":[53,100],"better":[56],"than":[57,132],"extracted":[59],"from":[60],"whole":[62],"videos.":[64],"Therefore,":[65],"our":[66,114,128],"realizes":[68],"focusing":[72],"motion-music":[75,122],"relation":[76],"improves":[78],"performance":[81,136],"by":[82],"utilizing":[83],"motion-based":[84],"property-based":[90],"alignment.":[93],"is":[95],"first":[97],"task":[98],"which":[99],"to":[103],"retrieval.":[108],"In":[109],"experiments,":[111],"we":[112],"compare":[113],"with":[116],"state-of-the-art":[118],"methods":[124,140],"verify":[126],"that":[127],"achieves":[130],"more":[131],"twice":[133],"conventional":[139],"in":[141],"Recall@1.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
