{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T23:04:12Z","timestamp":1784847852927,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01166","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12549-12558","source":"Crossref","is-referenced-by-count":3,"title":["Audio-Visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation"],"prefix":"10.1109","author":[{"given":"Fa-Ting","family":"Hong","sequence":"first","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunnan","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglin","family":"Lu","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Xu","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00812"},{"key":"ref7","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Daniel","year":"2021","journal-title":"ICLR"},{"key":"ref8","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref9","article-title":"Hippo: Recurrent memory with optimal polynomial projections","author":"Gu","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"ICLR"},{"key":"ref11","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","author":"Gu","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","article-title":"On the parameterization and initialization of diagonal state space models","author":"Gu","year":"2022","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref14","author":"Guo","year":"2024","journal-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control"},{"key":"ref15","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref16","article-title":"Diagonal state spaces are as effective as structured state spaces","author":"Gupta","year":"2022","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01912"},{"key":"ref18","article-title":"Liquid structural state-space models","author":"Hasani","year":"2022","journal-title":"ICLR"},{"key":"ref19","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02108"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00339"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref25","author":"Jiang","year":"2024","journal-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02104"},{"key":"ref27","article-title":"Mega: Moving average equipped gated attention","author":"Ma","year":"2022","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref29","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2023","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref31","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","article-title":"First order motion model for image animation","author":"Siarohin","year":"2019","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_23"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref37","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref38","author":"Wang","year":"2024","journal-title":"V-express: Conditional dropout for progressive training of portrait video generation"},{"key":"ref39","author":"Wei","year":"2024","journal-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animation"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref42","author":"Xu","year":"2024","journal-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation"},{"key":"ref43","author":"Xu","year":"2024","journal-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00366"},{"key":"ref49","author":"Zheng","year":"2024","journal-title":"Memo: Memory-guided diffusion for expressive talking video generation"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref51","article-title":"Celebvhq: A large-scale video facial attributes dataset","author":"Zhu","year":"2022","journal-title":"ECCV"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443623.pdf?arnumber=11443623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:00Z","timestamp":1777529820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01166","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}