{"id":"https://openalex.org/W4403182060","doi":"https://doi.org/10.1109/is262782.2024.10704086","title":"Enhancing Video Music Recommendation with Transformer-Driven Audio-Visual Embeddings","display_name":"Enhancing Video Music Recommendation with Transformer-Driven Audio-Visual Embeddings","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4403182060","doi":"https://doi.org/10.1109/is262782.2024.10704086"},"language":"en","primary_location":{"id":"doi:10.1109/is262782.2024.10704086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.05008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003172051","display_name":"S. C. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shimiao Liu","raw_affiliation_strings":["Georgia Institute of Technology,Music Informatics Group,Atlanta,USA","Music Informatics Group, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Music Informatics Group,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Music Informatics Group, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048454242","display_name":"Alexander Lerch","orcid":"https://orcid.org/0000-0001-6319-578X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Lerch","raw_affiliation_strings":["Georgia Institute of Technology,Music Informatics Group,Atlanta,USA","Music Informatics Group, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Music Informatics Group,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Music Informatics Group, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003172051"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18930651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9922999739646912,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7303531169891357},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6124837398529053},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49448418617248535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45676282048225403},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4342384934425354},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10473626852035522},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0994688868522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303531169891357},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6124837398529053},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49448418617248535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45676282048225403},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4342384934425354},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10473626852035522},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0994688868522644},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/is262782.2024.10704086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.05008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.05008","pdf_url":"https://arxiv.org/pdf/2503.05008","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.05008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.05008","pdf_url":"https://arxiv.org/pdf/2503.05008","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2020042635","https://openalex.org/W2064675550","https://openalex.org/W2067891598","https://openalex.org/W2095005467","https://openalex.org/W2106053110","https://openalex.org/W2147776527","https://openalex.org/W2194775991","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2765860599","https://openalex.org/W2939574508","https://openalex.org/W2962970472","https://openalex.org/W2963807156","https://openalex.org/W2964282041","https://openalex.org/W3007605881","https://openalex.org/W3105017218","https://openalex.org/W3116298410","https://openalex.org/W3198668032","https://openalex.org/W3207290297","https://openalex.org/W4297808394","https://openalex.org/W4312319752","https://openalex.org/W4323519173","https://openalex.org/W4385245566","https://openalex.org/W4386215334","https://openalex.org/W4387801088","https://openalex.org/W4401155804","https://openalex.org/W6675751002"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"A":[0],"fitting":[1],"soundtrack":[2],"can":[3,68],"help":[4],"a":[5,13,20,45,58,78],"video":[6,34,55],"better":[7,14],"convey":[8],"its":[9],"content":[10],"and":[11,26,54,115,126],"provide":[12],"immersive":[15],"experience.":[16],"This":[17],"paper":[18],"introduces":[19],"novel":[21],"approach":[22],"utilizing":[23],"self-supervised":[24],"learning":[25,28],"contrastive":[27],"to":[29],"automatically":[30],"recommend":[31],"audio":[32,53],"for":[33,40],"content,":[35],"thereby":[36],"eliminating":[37],"the":[38,89,95,121],"need":[39],"manual":[41],"labeling.":[42],"We":[43],"use":[44],"dual-branch":[46],"cross-modal":[47],"embedding":[48],"model":[49,109],"that":[50,107],"maps":[51],"both":[52],"features":[56],"into":[57],"common":[59],"low-dimensional":[60],"space.":[61],"The":[62],"fit":[63],"of":[64,81,91,98,123],"various":[65,82],"audio-video":[66,99,124],"pairs":[67],"then":[69],"be":[70],"mod-eled":[71],"as":[72],"inverse":[73],"distance":[74],"measure.":[75],"In":[76],"addition,":[77],"comparative":[79],"analysis":[80],"temporal":[83,96],"encoding":[84],"methods":[85],"is":[86],"presented,":[87],"emphasizing":[88],"effectiveness":[90],"transformers":[92],"in":[93],"managing":[94],"information":[97],"matching":[100,125],"tasks.":[101],"Through":[102],"multiple":[103],"experiments,":[104],"we":[105],"demonstrate":[106],"our":[108],"TIVM,":[110],"which":[111],"integrates":[112],"transformer":[113],"encoders":[114],"using":[116],"InfoN":[117],"Celoss,":[118],"significantly":[119],"improves":[120],"performance":[122],"surpasses":[127],"traditional":[128],"methods.":[129]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
