{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T20:13:41Z","timestamp":1779308021299,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Projects of the Educational Sciences Plan of Beijing Municipality","award":["AMAA25002"],"award-info":[{"award-number":["AMAA25002"]}]},{"name":"Beijing Natural Science Foundation","award":["4252018"],"award-info":[{"award-number":["4252018"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62572032"],"award-info":[{"award-number":["62572032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["QY25393"],"award-info":[{"award-number":["QY25393"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tvcg.2026.3679130","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:06:26Z","timestamp":1774901186000},"page":"3519-3529","source":"Crossref","is-referenced-by-count":0,"title":["Generating Audiovisual Synergy Fluid Animation for Highly Immersive VR Experience"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2239-1121","authenticated-orcid":false,"given":"Na","family":"Jiang","sequence":"first","affiliation":[{"name":"Capital Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3372-8441","authenticated-orcid":false,"given":"Xiangcheng","family":"Zhai","sequence":"additional","affiliation":[{"name":"Capital Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1573-8919","authenticated-orcid":false,"given":"Yuxuan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Capital Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9160-3813","authenticated-orcid":false,"given":"Xiaohui","family":"Tan","sequence":"additional","affiliation":[{"name":"Capital Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5774-6706","authenticated-orcid":false,"given":"Aimin","family":"Hao","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9149-3554","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3372085"},{"key":"ref2","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","volume":"abs\/2304.08477","author":"An","year":"2023","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01762"},{"key":"ref4","first-page":"160","article-title":"Text2gestures: A transformer-based network for generating emotive body gestures for virtual agents * *this work has been supported in part by ARO grants W911NF1910069 and w911nf1910315, and intel","volume-title":"IEEE Virtual Reality and 3D User Interfaces, VR 2021, Lisbon, Portugal, March 27 - April 1, 2021","author":"Bhattacharya","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02161"},{"key":"ref6","volume-title":"Dreamina image generator & video generator: All-in-one AI creative suite","year":"2025"},{"key":"ref7","first-page":"25: 70: 1","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","volume":"abs\/2309.15807","author":"Dai","year":"2023","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/waspaa58266.2023.10248160"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01459"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01457"},{"key":"ref12","article-title":"Mmdisco: Multimodal discriminator-guided cooperative diffusion for joint audio and video generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Hayakawa","year":"2025"},{"key":"ref13","article-title":"Animate-a-story: Storytelling with retrieval-augmented video generation","volume":"abs\/2307.06940","author":"He","year":"2023","journal-title":"CoRR"},{"key":"ref14","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","volume":"abs\/2211.13221","author":"He","year":"2022","journal-title":"CoRR"},{"key":"ref15","article-title":"Imagen video: High definition video generation with diffusion models","volume":"abs\/2210.02303","author":"Ho","year":"2022","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00575"},{"key":"ref17","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA, vol. 202 of Proceedings of Machine Learning Research","author":"Huang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/vr55154.2023.00057"},{"key":"ref20","article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","author":"Kreuk","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/vr58804.2024.00060"},{"key":"ref23","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning, ICML 2023,23\u201329 July 2023, Honolulu, Hawaii, USA, vol. 202 of Proceedings of Machine Learning Research","author":"Liu","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2121"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00365"},{"key":"ref26","first-page":"16784","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA, vol. 162 of Proceedings of Machine Learning Research","author":"Nichol","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00548"},{"key":"ref28","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"abs\/2204.06125","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/vr58804.2024.00048"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00985"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096023"},{"key":"ref33","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135,2023","author":"Singer","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0707"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01366"},{"key":"ref36","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/vr59515.2025.00067"},{"key":"ref38","article-title":"Universe-l: Unified audio-video generation via stitching of experts","volume":"abs\/2509.06155","author":"Wang","year":"2025","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02176"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00683"},{"key":"ref43","article-title":"Qwen2. 5-omni technical report","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/vr58804.2024.00085"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268730"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/vr58804.2024.00090"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2023.3247066"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2026.3679097"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680950"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/vr50410.2021.00110"},{"key":"ref52","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","volume-title":"CoRR","volume":"abs\/2311.04145","author":"Zhang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/vr58804.2024.00034"},{"key":"ref54","article-title":"Foley-crafter: Bring silent videos to life with lifelike and synchronized sounds","volume":"abs\/2407.01494","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref55","article-title":"Magicvideo: Efficient video generation with latent diffusion models","volume":"abs\/2211.11018","author":"Zhou","year":"2022","journal-title":"CoRR"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612707"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11526953\/11458046.pdf?arnumber=11458046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:52:47Z","timestamp":1779306767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11458046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":56,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3679130","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}