{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:23:32Z","timestamp":1783182212253,"version":"3.54.6"},"reference-count":0,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,10]]},"DOI":"10.1109\/cvpr52734.2025.02691","type":"proceedings-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:26:42Z","timestamp":1755106002000},"page":"28901-28911","source":"Crossref","is-referenced-by-count":30,"title":["MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis"],"prefix":"10.1109","author":[{"given":"Ho Kei","family":"Cheng","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masato","family":"Ishii","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akio","family":"Hayakawa","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takashi","family":"Shibuya","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Schwing","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","event":{"name":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Nashville, TN, USA","start":{"date-parts":[[2025,6,10]]},"end":{"date-parts":[[2025,6,17]]}},"container-title":["2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx8\/11091818\/11091608\/11092848.pdf?arnumber=11092848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:27:05Z","timestamp":1755106025000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/11092848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/cvpr52734.2025.02691","relation":{},"subject":[],"published":{"date-parts":[[2025,6,10]]}}}