{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:17:58Z","timestamp":1773137878977,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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","award":["62376201"],"award-info":[{"award-number":["62376201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62501189"],"award-info":[{"award-number":["62501189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3596747","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:46:18Z","timestamp":1754588778000},"page":"2744-2756","source":"Crossref","is-referenced-by-count":0,"title":["TH-Mamba: Spatial-Temporal Correlation Learning for Mamba-Based Talking Head Generation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0748-3669","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology and Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1070-9223","authenticated-orcid":false,"given":"Zhixi","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4055-7503","authenticated-orcid":false,"given":"Kui","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6011-0496","authenticated-orcid":false,"given":"Xiaocheng","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-2318","authenticated-orcid":false,"given":"Chia-Wen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375330"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3465848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083257"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00227"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3394850"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3311039"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3414412"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_23"},{"key":"ref20","article-title":"MuseTalk: Real-time high-fidelity video dubbing via spatio-temporal sampling","author":"Zhang","year":"2024","journal-title":"arXiv:2410.10122"},{"key":"ref21","article-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency","author":"Jiang","year":"2024","journal-title":"arXiv:2409.02634"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref31","article-title":"GeneFace: Generalized and high-fidelity audio-driven 3D talking face synthesis","author":"Ye","year":"2023","journal-title":"arXiv:2301.13430"},{"key":"ref32","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref33","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gu"},{"key":"ref34","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022","journal-title":"arXiv:2208.04933"},{"key":"ref35","first-page":"1474","article-title":"HiPPO: Recurrent memory with optimal polynomial projections","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2607"},{"key":"ref37","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gupta"},{"key":"ref38","article-title":"Liquid structural state-space models","author":"Hasani","year":"2022","journal-title":"arXiv:2209.12951"},{"key":"ref39","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref40","article-title":"State space model for new-generation network alternative to transformers: A survey","author":"Wang","year":"2024","journal-title":"arXiv:2404.09516"},{"key":"ref41","article-title":"Visual mamba: A survey and new outlooks","author":"Xu","year":"2024","journal-title":"arXiv:2404.18861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/app14135683"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3610435"},{"key":"ref44","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv:2401.04722"},{"key":"ref45","article-title":"MambaByte: Token-free selective state space model","author":"Wang","year":"2024","journal-title":"arXiv:2401.13660"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00065"},{"key":"ref47","article-title":"Hungry hungry hippos: Towards language modeling with state space models","author":"Fu","year":"2022","journal-title":"arXiv:2212.14052"},{"key":"ref48","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022","journal-title":"arXiv:2206.13947"},{"key":"ref49","first-page":"2846","article-title":"S4ND: Modeling images and videos as multidimensional signals with state spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Nguyen"},{"key":"ref50","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref52","article-title":"Video mamba suite: State space model as a versatile alternative for video understanding","author":"Chen","year":"2024","journal-title":"arXiv:2403.09626"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"ref54","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548330"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref63","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357808"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00607"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688218"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446049"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687525"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613753"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11119721.pdf?arnumber=11119721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:50Z","timestamp":1773086450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11119721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":70,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3596747","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}