{"id":"https://openalex.org/W4403791727","doi":"https://doi.org/10.1145/3664647.3681027","title":"TiVA: Time-Aligned Video-to-Audio Generation","display_name":"TiVA: Time-Aligned Video-to-Audio Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791727","doi":"https://doi.org/10.1145/3664647.3681027"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681027","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101560179","display_name":"Xihua Wang","orcid":"https://orcid.org/0009-0002-9454-5775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xihua Wang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009349216","display_name":"Yuyue Wang","orcid":"https://orcid.org/0009-0005-6987-1028"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyue Wang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010596810","display_name":"Yihan Wu","orcid":"https://orcid.org/0009-0001-0312-782X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihan Wu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505570","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0001-6036-9035"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522530","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-5631-0639"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061402916","display_name":"Zehua Chen","orcid":"https://orcid.org/0009-0000-2294-7447"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035141289","display_name":"Hongteng Xu","orcid":"https://orcid.org/0000-0003-4192-5360"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongteng Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078873399","display_name":"G. Sui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guodong Sui","raw_affiliation_strings":["Beijing Zhidemai Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Zhidemai Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101560179"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":1.4017,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82386333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"573","last_page":"582"},"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":0.9976999759674072,"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/T11349","display_name":"Music Technology and Sound Studies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891520023345947},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.45160260796546936},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.4144613742828369},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3454066514968872},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27970072627067566},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2544693946838379},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15854349732398987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891520023345947},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.45160260796546936},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.4144613742828369},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3454066514968872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27970072627067566},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2544693946838379},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15854349732398987}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681027","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2140304104","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2560674852","https://openalex.org/W2593116425","https://openalex.org/W2889365981","https://openalex.org/W3015371781","https://openalex.org/W3094550259","https://openalex.org/W4307079201","https://openalex.org/W4312933868","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4372348103","https://openalex.org/W4377010126","https://openalex.org/W4378942405","https://openalex.org/W4383045354","https://openalex.org/W4385328213","https://openalex.org/W4385775276","https://openalex.org/W4386071707","https://openalex.org/W4386071828","https://openalex.org/W4386907933","https://openalex.org/W4387946970","https://openalex.org/W4390784427","https://openalex.org/W4390873054"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
