{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:01:39Z","timestamp":1764399699519,"version":"3.46.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002467","name":"DKU","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002467","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249337","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1981-1985","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Video to Audio Mapper with Visual Scene Detection"],"prefix":"10.1109","author":[{"given":"Mingjing","family":"Yi","sequence":"first","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxi","family":"Wang","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"journal-title":"Audioldm: Text-toaudio generation with latent diffusion models","year":"2023","author":"Liu","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_43"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref7","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume":"33","author":"Su","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref10","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Luo","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning, PMLR","author":"Radford","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447063"},{"journal-title":"Frieren: Efficient video-to-audio generation with rectified flow matching","year":"2024","author":"Wang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_15"},{"journal-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","year":"2024","author":"Zhang","key":"ref17"},{"key":"ref18","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"volume-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","year":"2019","author":"Kilgour","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249337.pdf?arnumber=11249337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:59:11Z","timestamp":1764399551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249337","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}