{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:17:48Z","timestamp":1783315068295,"version":"3.54.6"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003482","name":"Department of Education of Hebei Province","doi-asserted-by":"publisher","award":["ZD2022102"],"award-info":[{"award-number":["ZD2022102"]}],"id":[{"id":"10.13039\/501100003482","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02275-0","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:03:59Z","timestamp":1773151439000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GRKAT-HCD: talking face generation via group-rational Kolmogorov-Arnold transformer and hierarchical collaborative deformation"],"prefix":"10.1007","volume":"32","author":[{"given":"Yazhi","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"2275_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109865","volume":"144","author":"R Wu","year":"2023","unstructured":"Wu, R., Yu, Y., Zhan, F., Zhang, J., Zhang, X., Lu, S.: Audio-driven talking face generation with diverse yet realistic facial animations. Pattern Recogn. 144, 109865 (2023)","journal-title":"Pattern Recogn."},{"issue":"6","key":"2275_CR2","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., Li, D.: Makelttalk: speaker-aware talking-head animation. ACM Trans. On Graphics (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. On Graphics (TOG)"},{"key":"2275_CR3","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: Faceformer: speech-driven 3d facial animation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18770\u201318780 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"issue":"4","key":"2275_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658221","volume":"43","author":"Z Sun","year":"2024","unstructured":"Sun, Z., Lv, T., Ye, S., Lin, M., Sheng, J., Wen, Y.-H., Yu, M., Liu, Y.-J.: Diffposetalk: speech-driven stylistic 3d facial animation and head pose generation via diffusion models. ACM Trans. on Graphics (TOG) 43(4), 1\u20139 (2024)","journal-title":"ACM Trans. on Graphics (TOG)"},{"issue":"4","key":"2275_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073699","volume":"36","author":"S Taylor","year":"2017","unstructured":"Taylor, S., Kim, T., Yue, Y., Mahler, M., Krahe, J., Rodriguez, A.G., Hodgins, J., Matthews, I.: A deep learning approach for generalized speech animation. ACM Trans. On Graphics (TOG) 36(4), 1\u201311 (2017)","journal-title":"ACM Trans. On Graphics (TOG)"},{"issue":"11","key":"2275_CR6","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"2275_CR7","doi-asserted-by":"crossref","unstructured":"Guan, J., Zhang, Z., Zhou, H., Hu, T., Wang, K., He, D., Feng, H., Liu, J., Ding, E., Liu, Z., et al.: Stylesync: high-fidelity generalized and personalized lip sync in style-based generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1505\u20131515 (2023)","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"2275_CR8","doi-asserted-by":"crossref","unstructured":"Richard, A., Lea, C., Ma, S., Gall, J., Torre, F., Sheikh, Y.: Audio-and gaze-driven facial animation of codec avatars. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 41\u201350 (2021)","DOI":"10.1109\/WACV48630.2021.00009"},{"key":"2275_CR9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141, Polosukhin, I.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, (2017)"},{"key":"2275_CR10","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. ICLR (2021)"},{"key":"2275_CR11","doi-asserted-by":"crossref","unstructured":"Das, D., Biswas, S., Sinha, S., Bhowmick, B.: Speech-driven facial animation using cascaded gans for learning of motion and texture. In: European Conference on Computer Vision, pp. 408\u2013424. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"2275_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102260","volume":"74","author":"X Li","year":"2022","unstructured":"Li, X., Zhang, J., Liu, Y.: Speech driven facial animation generation based on gan. Displays 74, 102260 (2022)","journal-title":"Displays"},{"key":"2275_CR13","unstructured":"Yang X, Wang X (2025) Kolmogorov\u2013arnold transformer. In: The Thirteenth International Conference on Learning Representations"},{"key":"2275_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2275_CR15","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: International Conference on Learning Representations (2020)"},{"key":"2275_CR16","doi-asserted-by":"crossref","unstructured":"Han, X., Jiang, F., Wen, S., Tian, T.: Kolmogorov-arnold network-based enhanced fusion transformer for hyperspectral image classification. Inf. Sci. 122323 (2025)","DOI":"10.1016\/j.ins.2025.122323"},{"key":"2275_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhang, H.: Thin-plate spline motion model for image animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3657\u20133666 (2022)","DOI":"10.1109\/CVPR52688.2022.00364"},{"issue":"4","key":"2275_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing obama: learning lip sync from audio. ACM Trans. on Graphics (ToG) 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. on Graphics (ToG)"},{"issue":"5","key":"2275_CR19","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1007\/s11263-019-01251-8","volume":"128","author":"K Vougioukas","year":"2020","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: Realistic speech-driven facial animation with gans. Int. J. Comput. Vision 128(5), 1398\u20131413 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"2275_CR20","doi-asserted-by":"crossref","unstructured":"Chen, L., Cui, G., Liu, C., Li, Z., Kou, Z., Xu, Y., Xu, C.: Talking-head generation with rhythmic head motion. In: European Conference on Computer Vision, pp. 35\u201351. Springer (2020)","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"2275_CR21","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.: A lip sync expert is all you need for speech to lip generation in the wild. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 484\u2013492 (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"2275_CR22","doi-asserted-by":"crossref","unstructured":"Park, S.J., Kim, M., Hong, J., Choi, J., Ro, Y.M.: Synctalkface: talking face generation with precise lip-syncing via audio-lip memory. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2062\u20132070 (2022)","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"2275_CR23","doi-asserted-by":"crossref","unstructured":"Shen, S., Zhao, W., Meng, Z., Li, W., Zhu, Z., Zhou, J., Lu, J.: Difftalk: crafting diffusion models for generalized audio-driven portraits animation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"2275_CR24","doi-asserted-by":"crossref","unstructured":"Wu, M., Zhao, S., Wu, T., Xu, Y., Xu, T., Chen, E.: Avf-lip: high-fidelity talking face generation via audio-visual fusion. In: 2024 7th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), pp. 491\u2013499 (2024). IEEE","DOI":"10.1109\/PRAI62207.2024.10827447"},{"key":"2275_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, W., Cun, X., Wang, X., Zhang, Y., Shen, X., Guo, Y., Shan, Y., Wang, F.: 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 (2023)","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"2275_CR26","unstructured":"Ye, Z., Zhong, T., Ren, Y., Yang, J., Li, W., Huang, J., Jiang, Z., He, J., Huang, R., Liu, J., Zhang, C., Yin, X., Ma, Z., Zhao, Z.: Real3d-portrait: one-shot realistic 3d talking portrait synthesis. (2024)"},{"key":"2275_CR27","unstructured":"Kim, G., Seo, K., Cha, S., Noh, J.: Nerffacespeech: one-shot audio-driven 3d talking head synthesis via generative prior. arXiv preprint arXiv:2405.05749 (2024)"},{"key":"2275_CR28","doi-asserted-by":"crossref","unstructured":"Ying, T., Yazhi, L., Xiong, L., Wei, L.: Adaptive diffusion landmark dynamic rendering for realistic talking face video generation. Vis. Comput. 1\u201311 (2025)","DOI":"10.1007\/s00371-025-03907-8"},{"key":"2275_CR29","doi-asserted-by":"crossref","unstructured":"Xie, T., Liao, L., Bi, C., Tang, B., Yin, X., Yang, J., Wang, M., Yao, J., Zhang, Y., Ma, Z.: Towards realistic visual dubbing with heterogeneous sources. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1739\u20131747 (2021)","DOI":"10.1145\/3474085.3475318"},{"key":"2275_CR30","doi-asserted-by":"crossref","unstructured":"Yi, R., Ye, Z., Fan, R., Shu, Y., Liu, Y.-J., Lai, Y.-K., Rosin, P.L.: Animating portrait line drawings from a single face photo and a speech signal. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u20138 (2022)","DOI":"10.1145\/3528233.3530720"},{"key":"2275_CR31","unstructured":"Liang, J., Lu, F.: Emotional conversation: Empowering talking faces with cohesive expression, gaze and pose generation. arXiv preprint arXiv:2406.07895 (2024)"},{"key":"2275_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, R., Li, B., Liu, B.: High-fidelity talking face synthesis guided by landmark. In: 2024 6th International Conference on Frontier Technologies of Information and Computer (ICFTIC), pp. 150\u2013154 (2024). IEEE","DOI":"10.1109\/ICFTIC64248.2024.10913301"},{"key":"2275_CR33","doi-asserted-by":"crossref","unstructured":"Biswas, S., Sinha, S., Das, D., Bhowmick, B.: Realistic talking face animation with speech-induced head motion. In: Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing, pp. 1\u20139 (2021)","DOI":"10.1145\/3490035.3490305"},{"key":"2275_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljacic, M., Hou, T.Y., Tegmark, M.: KAN: kolmogorov\u2013arnold networks. In: The Thirteenth International Conference on Learning Representations (2025)","DOI":"10.1103\/4t7t-v19l"},{"key":"2275_CR35","first-page":"14243","volume":"33","author":"N Boull\u00e9","year":"2020","unstructured":"Boull\u00e9, N., Nakatsukasa, Y., Townsend, A.: Rational neural networks. Adv. Neural. Inf. Process. Syst. 33, 14243\u201314253 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2275_CR36","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.-Y., Wang, T.-C., Zhu, J.-Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"issue":"12","key":"2275_CR37","doi-asserted-by":"publisher","first-page":"8717","DOI":"10.1109\/TPAMI.2018.2889052","volume":"44","author":"T Afouras","year":"2018","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8717\u20138727 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2275_CR38","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: Lrs3-ted: a large-scale dataset for visual speech recognition. arXiv preprint arXiv:1809.00496 (2018)"},{"key":"2275_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, Y., Wu, W., Loy, C.C., Wang, X., Liu, Z.: Pose-controllable talking face generation by implicitly modularized audio-visual representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4176\u20134186 (2021)","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"2275_CR40","doi-asserted-by":"crossref","unstructured":"Ji, X., Zhou, H., Wang, K., Wu, Q., Wu, W., Xu, F., Cao, X.: Eamm: one-shot emotional talking face via audio-based emotion-aware motion model. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530745"},{"key":"2275_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hu, Z., Deng, W., Fan, C., Lv, T., Ding, Y.: Dinet: deformation inpainting network for realistic face visually dubbing on high resolution video. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 3543\u20133551 (2023)","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"2275_CR42","doi-asserted-by":"crossref","unstructured":"Hong, F.-T., Xu, D.: Implicit identity representation conditioned memory compensation network for talking head video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23062\u201323072 (2023)","DOI":"10.1109\/ICCV51070.2023.02108"},{"key":"2275_CR43","doi-asserted-by":"crossref","unstructured":"Wang, J., Qian, X., Zhang, M., Tan, R.T., Li, H.: Seeing what you said: talking face generation guided by a lip reading expert. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14653\u201314662 (2023)","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"2275_CR44","doi-asserted-by":"crossref","unstructured":"Rochow, A., Schwarz, M., Behnke, S.: Fsrt: facial scene representation transformer for face reenactment from factorized appearance head-pose and facial expression features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7716\u20137726 (2024)","DOI":"10.1109\/CVPR52733.2024.00737"},{"key":"2275_CR45","unstructured":"Cheng, H., Lin, L., Liu, C., Xia, P., Hu, P., Ma, J., Du, J., Pan, J.: Dawn: dynamic frame avatar with non-autoregressive diffusion framework for talking head video generation. In: International Conference on Representation Learning, vol. 2025, pp. 99250\u201399268 (2025)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02275-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02275-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02275-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:03:54Z","timestamp":1783314234000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02275-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2275"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02275-0","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"16 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"199"}}