{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:58Z","timestamp":1777567558088,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888189","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis"],"prefix":"10.1109","author":[{"given":"Zhiqi","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Luo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Liao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Foleycrafter: Bring silent videos to life with lifelike and synchronized sounds","author":"Zhang","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref3","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume":"36","author":"Luo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Video-to-audio generation with hidden alignment","author":"Xu","year":"2024"},{"key":"ref5","article-title":"Mini-gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024"},{"key":"ref6","article-title":"Sharegpt4video: Improving video understanding and generation with better captions","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024"},{"key":"ref8","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"ref13","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02537"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref20","article-title":"Semantically consistent video-to-audio generation using multimodal language large model","author":"Chen","year":"2024"},{"key":"ref21","article-title":"X-instructblip: A framework for aligning x-modal instruction-aware representations to llms and emergent cross-modal reasoning","author":"Panagopoulou","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref26","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref27","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref28","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_1"},{"key":"ref34","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888189.pdf?arnumber=10888189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:44Z","timestamp":1774416164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888189","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}