{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T14:05:17Z","timestamp":1780322717065,"version":"3.54.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":89,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62566058"],"award-info":[{"award-number":["62566058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Government Guide Local Science and Technology Development Fund of Gansu Province","award":["25ZYJA034"],"award-info":[{"award-number":["25ZYJA034"]}]},{"name":"Science and Technology Program of Lanzhou City","award":["2025-2-42"],"award-info":[{"award-number":["2025-2-42"]}]},{"name":"Education and Teaching Achievement Cultivation Project of Gansu Province","award":["2023GSJXCGPY-60"],"award-info":[{"award-number":["2023GSJXCGPY-60"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s44443-026-00617-6","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T14:33:13Z","timestamp":1772634793000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HimaTalk: robust audio-driven Tibetan talking head generation via bi-directional Mamba and spatiotemporal constraints"],"prefix":"10.1007","volume":"38","author":[{"given":"Tingting","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangzhen","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianghe","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingbin","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shibiao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruilei","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"617_CR1","unstructured":"Afouras T, Chung JS, Zisserman A (2018) Lrs3-ted: a large-scale dataset for visual speech recognition. arXiv:1809.00496"},{"key":"617_CR2","unstructured":"Cao X, Wang G, Shi S, Zhao J, Yao Y, Fei J, Gao M (2024) Joyvasa: portrait and animal image animation with diffusion-based audio-driven facial dynamics and head motion generation. arXiv:2411.09209"},{"key":"617_CR3","doi-asserted-by":"crossref","unstructured":"Chen Z, Cao J, Chen Z, Li Y, Ma C (2025) Echomimic: Lifelike audio-driven portrait animations through editable landmark conditions. In: Proceedings of the AAAI conference on artificial intelligence, vol 39, pp 2403\u20132410","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"617_CR4","doi-asserted-by":"crossref","unstructured":"Chung JS, Zisserman A (2016) Lip reading in the wild. In: Asian conference on computer vision","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"617_CR5","doi-asserted-by":"crossref","unstructured":"Chung JS, Zisserman A (2016) Out of time: automated lip sync in the wild. In: Workshop on multi-view lip-reading, ACCV","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"617_CR6","unstructured":"Cui J, Li H, Yao Y, Zhu H, Shang H, Cheng K, Zhou H, Zhu S, Wang J (2024) Hallo2: long-duration and high-resolution audio-driven portrait image animation"},{"key":"617_CR7","doi-asserted-by":"crossref","unstructured":"Cui J, Li H, Zhan Y, Shang H, Cheng K, Ma Y, Mu S, Zhou H, Wang J, Zhu S (2024) Hallo3: highly dynamic and realistic portrait image animation with video diffusion transformer","DOI":"10.1109\/CVPR52734.2025.01964"},{"key":"617_CR8","doi-asserted-by":"publisher","first-page":"215516","DOI":"10.1109\/ACCESS.2020.3040906","volume":"8","author":"S Fenghour","year":"2020","unstructured":"Fenghour S, Chen D, Guo K, Xiao P (2020) Lip reading sentences using deep learning with only visual cues. IEEE Access 8:215516\u2013215530","journal-title":"IEEE Access"},{"key":"617_CR9","doi-asserted-by":"crossref","unstructured":"Feng H, Ma Y, Di D, Fan L, Su T, Wu X (2025) Ditalker: A unified dit-based framework for high-quality and speaking styles controllable portrait animation. arXiv:2508.06511","DOI":"10.1016\/j.cviu.2026.104819"},{"key":"617_CR10","unstructured":"Gu A, Dao T (2024) Mamba: Linear-time sequence modeling with selective state spaces. In: First conference on language modeling"},{"key":"617_CR11","unstructured":"Gu A, Goel K, R\u00e9 C (2021) Efficiently modeling long sequences with structured state spaces. arXiv:2111.00396"},{"key":"617_CR12","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inf Process Syst 30"},{"key":"617_CR13","doi-asserted-by":"crossref","unstructured":"Hong F-T, Xu Z, Zhou Z, Zhou J, Li X, Lin Q, Lu Q, Xu D (2025) Audio-visual controlled video diffusion with masked selective state spaces modeling for natural talking head generation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV51701.2025.01166"},{"key":"617_CR14","doi-asserted-by":"crossref","unstructured":"Ji X, Hu X, Xu Z, Zhu J, Lin C, He Q, Zhang J, Luo D, Chen Y, Lin Q et al (2025) Sonic: Shifting focus to global audio perception in portrait animation. In: Proceedings of the computer vision and pattern recognition conference, pp 193\u2013203","DOI":"10.1109\/CVPR52734.2025.00027"},{"key":"617_CR15","unstructured":"Jiangga, Zhou J, Ji Z, Wangqing B (2006) Learn to speak Tibetan: 300 sentences. Minzu Publishing House, Beijing. CIP date: Mar 2006. Copyright page: 1st edition, Jul 2004; 2nd printing (Beijing), Mar 2006. Author names romanized into Hanyu Pinyin (not necessarily as printed in the book)"},{"key":"617_CR16","doi-asserted-by":"crossref","unstructured":"Li K, Li X, Wang Y, He Y, Wang Y, Wang L, Qiao Y (2024) Videomamba: State space model for efficient video understanding. In: European conference on computer vision. Springer, pp 237\u2013255","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"617_CR17","unstructured":"Li C, Zhang C, Xu W, Lin J, Xie J, Feng W, Peng B, Chen C, Xing W (2024) Latentsync: Taming audio-conditioned latent diffusion models for lip sync with syncnet supervision. arXiv:2412.09262"},{"key":"617_CR18","unstructured":"Lin B, Yu Y, Ye J, Lv R, Yang Y, Xie R, Yu P, Zhou H (2024) Takin-ada: Emotion controllable audio-driven animation with canonical and landmark loss optimization. arXiv:2410.14283"},{"key":"617_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Zeng Z, Ren T, Li F, Zhang H, Yang J, Jiang Q, Li C, Yang J, Su H et al (2024) Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: European conference on computer vision. Springer, pp 38\u201355","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"617_CR20","doi-asserted-by":"crossref","unstructured":"Ma Y, Wang S, Ding Y, Ma B, Lv T, Fan C, Hu Z, Deng Z, Yu X (2025) Talkclip: Talking head generation with text-guided expressive speaking styles. IEEE Trans Multimed","DOI":"10.1109\/TMM.2025.3581808"},{"key":"617_CR21","unstructured":"Ma J, Wang S, Yang J, Hu J, Liang J, Lin G, Li K, Meng Y et al (2025) Sayanything: Audio-driven lip synchronization with conditional video diffusion. arXiv:2502.11515"},{"key":"617_CR22","doi-asserted-by":"crossref","unstructured":"Meng R, Wang Y, Wu W, Zheng R, Li Y, Ma C (2025) Echomimicv 3: 1.3 b parameters are all you need for unified multi-modal and multi-task human animation. arXiv:2507.03905","DOI":"10.1609\/aaai.v40i10.37746"},{"key":"617_CR23","doi-asserted-by":"crossref","unstructured":"Meng R, Zhang X, Li Y, Ma C (2025) Echomimicv2: Towards striking, simplified, and semi-body human animation. In: Proceedings of the computer vision and pattern recognition conference, pp 5489\u20135498","DOI":"10.1109\/CVPR52734.2025.00516"},{"key":"617_CR24","doi-asserted-by":"publisher","first-page":"101027","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani A, Chung JS, Xie W, Zisserman A (2020) Voxceleb: Large-scale speaker verification in the wild. Comput Speech Lang 60:101027","journal-title":"Comput Speech Lang"},{"key":"617_CR25","doi-asserted-by":"crossref","unstructured":"Raina A, Arora V (2023) Syncnet: Correlating objective for time delay estimation in audio signals. In: ICASSP 2023\u20132023 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10096874"},{"key":"617_CR26","unstructured":"Song J, Meng C, Ermon S (2020) Denoising diffusion implicit models. arXiv:2010.02502"},{"key":"617_CR27","doi-asserted-by":"crossref","unstructured":"Soucek T, Lokoc J (2024) Transnet v2: An effective deep network architecture for fast shot transition detection. In: Proceedings of the 32nd ACM international conference on multimedia, pp 11218\u201311221","DOI":"10.1145\/3664647.3685517"},{"key":"617_CR28","doi-asserted-by":"crossref","unstructured":"Su S, Yan Q, Zhu Y, Zhang C, Ge X, Sun J, Zhang Y (2020) Blindly assess image quality in the wild guided by a self-adaptive hyper network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3667\u20133676","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"617_CR29","unstructured":"Unterthiner T, Van Steenkiste S, Kurach K, Marinier R, Michalski M, Gelly S (2018) Towards accurate generative models of video: A new metric & challenges. arXiv:1812.01717"},{"key":"617_CR30","doi-asserted-by":"crossref","unstructured":"Wang T-C, Mallya A, Liu M-Y (2021) One-shot free-view neural talking-head synthesis for video conferencing. In: CVPR","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"617_CR31","doi-asserted-by":"crossref","unstructured":"Wang H, Weng Y, Du J, Xu H, Wu X, He S, Yin B, Liu C, Gao J, Liu Q (2025) Read: Real-time and efficient asynchronous diffusion for audio-driven talking head generation. arXiv:2508.03457","DOI":"10.1609\/aaai.v40i12.37940"},{"key":"617_CR32","unstructured":"Wang H, Weng Y, Yu X, Du J, Xu H, Wu X, He S, Yin B, Liu C, Liu Q (2025) Rest: Diffusion-based real-time end-to-end streaming talking head generation via id-context caching and asynchronous streaming distillation. arXiv:2512.11229"},{"key":"617_CR33","doi-asserted-by":"crossref","unstructured":"Wang K, Wu Q, Song L, Yang Z, Wu W, Qian C, He R, Qiao Y, Loy CC (2020) Mead: A large-scale audio-visual dataset for emotional talking-face generation. In: ECCV","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"617_CR34","doi-asserted-by":"crossref","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","DOI":"10.1109\/TIP.2003.819861"},{"key":"617_CR35","doi-asserted-by":"crossref","unstructured":"Wu Y, Guo S, Qin Y (2025) Moda: Motion-drift augmentation for inertial human motion analysis. In: Proceedings of the computer vision and pattern recognition conference, pp 27771\u201327781","DOI":"10.1109\/CVPR52734.2025.02586"},{"key":"617_CR36","doi-asserted-by":"crossref","unstructured":"Xie L, Wang X, Zhang H, Dong C, Shan Y (2022) Vfhq: A high-quality dataset and benchmark for video face super-resolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 657\u2013666","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"617_CR37","unstructured":"Xu M, Li H, Su Q, Shang H, Zhang L, Liu C, Wang J, Yao Y, Zhu S (2024) Hallo: Hierarchical audio-driven visual synthesis for portrait image animation. arXiv:2406.08801 [cs.CV]"},{"key":"617_CR38","first-page":"660","volume":"37","author":"S Xu","year":"2024","unstructured":"Xu S, Chen G, Guo Y-X, Yang J, Li C, Zang Z, Zhang Y, Tong X, Guo B (2024) Vasa-1: Lifelike audio-driven talking faces generated in real time. Adv Neural Inf Process Syst 37:660\u2013684","journal-title":"Adv Neural Inf Process Syst"},{"key":"617_CR39","unstructured":"Ye Z, Zhong T, Ren Y, Yang J, Li W, Huang J, Jiang Z, He J, Huang R, Liu J et al (2024) Real3d-portrait: One-shot realistic 3d talking portrait synthesis. arXiv:2401.08503"},{"key":"617_CR40","doi-asserted-by":"crossref","unstructured":"Zhang W, Cun X, Wang X, Zhang Y, Shen X, Guo Y, Shan Y, Wang F (2023) Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8652\u20138661","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"617_CR41","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"},{"key":"617_CR42","doi-asserted-by":"crossref","unstructured":"Zhang Z, Li L, Ding Y, Fan C (2021) Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3661\u20133670","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"617_CR43","unstructured":"Zheng L, Zhang Y, Guo H, Pan J, Tan Z, Lu J, Tang C, An B, Yan S (2024) Memo: Memory-guided diffusion for expressive talking video generation. arXiv:2412.04448"},{"key":"617_CR44","doi-asserted-by":"crossref","unstructured":"Zhuang S, Li K, Chen X, Wang Y, Liu Z, Qiao Y, Wang Y (2024) Vlogger: Make your dream a vlog. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8806\u20138817","DOI":"10.1109\/CVPR52733.2024.00841"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00617-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00617-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00617-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T13:02:26Z","timestamp":1780318946000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00617-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["617"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00617-6","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"assertion":[{"value":"8 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"191"}}