{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:26:21Z","timestamp":1789467981521,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":89,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373137","type":"print"},{"value":"9783032373144","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37314-4_33","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:52:40Z","timestamp":1789462360000},"page":"599-618","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ClusterStyle: Modeling Intra-style Diversity with\u00a0Prototypical Clustering for\u00a0Stylized Motion Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6990-8833","authenticated-orcid":false,"given":"Kerui","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianrong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hehe","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"issue":"4","key":"33_CR1","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/3386569.3392469","volume":"39","author":"K Aberman","year":"2020","unstructured":"Aberman, K., Weng, Y., Lischinski, D., Cohen-Or, D., Chen, B.: Unpaired motion style transfer from video to animation. ACM Transactions on Graphics (TOG) 39(4), 64\u20131 (2020)","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2pose: Natural language grounded pose forecasting. In: 2019 International Conference on 3D Vision (3DV), pp. 719\u2013728. IEEE (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Ahuja, K., Ofek, E., Gonzalez-Franco, M., Holz, C., Wilson, A.D.: Coolmoves: User motion accentuation in virtual reality. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 5, no. (2), pp. 1\u201323 (2021)","DOI":"10.1145\/3463499"},{"issue":"5","key":"33_CR4","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.3390\/s23052597","volume":"23","author":"SMA Akber","year":"2023","unstructured":"Akber, S.M.A., Kazmi, S.N., Mohsin, S.M., Szcz\u0119sna, A.: Deep learning-based motion style transfer tools, techniques and future challenges. Sensors 23(5), 2597 (2023)","journal-title":"Sensors"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 132\u2013149 (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"33_CR6","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Chen, G., Li, X., Yang, Y., Wang, W.: Neural clustering based visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5714\u20135725 (2024)","DOI":"10.1109\/CVPR52733.2024.00546"},{"key":"33_CR8","unstructured":"Chen, K., Wang, J., Zhang, J., Li, M., Lu, Y., Fan, H.: Scaling video understanding via compact latent multi-agent collaboration. arXiv preprint arXiv:2605.00444 (2026)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Chen, K., Wu, Z., Hou, W., Li, K., Fan, H., Yang, Y.: Prompt-aware controllable shadow removal. arXiv preprint arXiv:2501.15043 (2025)","DOI":"10.24963\/ijcai.2025\/89"},{"key":"33_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"33_CR12","unstructured":"Cuturi, M.: Sinkhorn distances: Lightspeed computation of optimal transport. Adv. Neural. Inf. Process. Syst. 26 (2013)"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., Theobalt, C.: Mofusion: A framework for denoising-diffusion-based motion synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9760\u20139770 (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Ding, C., et al.: Decoupling with entropy-based equalization for semi-supervised semantic segmentation. IJCAI (2023)","DOI":"10.24963\/ijcai.2023\/74"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Ding, Y., Li, L., Wang, W., Yang, Y.: Clustering propagation for universal medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3357\u20133369 (2024)","DOI":"10.1109\/CVPR52733.2024.00323"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Feng, T., Quan, R., Wang, X., Wang, W., Yang, Y.: Interpretable3d: An ad-hoc interpretable classifier for 3d point clouds. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 1761\u20131769 (2024)","DOI":"10.1609\/aaai.v38i2.27944"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Feng, T., Wang, W., Wang, X., Yang, Y., Zheng, Q.: Clustering based point cloud representation learning for 3d analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8283\u20138294 (2023)","DOI":"10.1109\/ICCV51070.2023.00761"},{"issue":"5","key":"33_CR18","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1109\/34.765656","volume":"21","author":"H Frigui","year":"2002","unstructured":"Frigui, H., Krishnapuram, R.: A robust competitive clustering algorithm with applications in computer vision. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 450\u2013465 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"33_CR19","doi-asserted-by":"publisher","first-page":"7518","DOI":"10.1109\/TVCG.2024.3352002","volume":"30","author":"X Gao","year":"2024","unstructured":"Gao, X., Yang, Y., Xie, Z., Du, S., Sun, Z., Wu, Y.: Guess: Gradually enriching synthesis for text-driven human motion generation. IEEE Trans. Visual Comput. Graph. 30(12), 7518\u20137530 (2024)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1396\u20131406 (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Goel, P., Wang, K.C., Liu, C.K., Fatahalian, K.: Iterative motion editing with natural language. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u20139 (2024)","DOI":"10.1145\/3641519.3657447"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Guo, C., Mu, Y., Javed, M.G., Wang, S., Cheng, L.: Momask: Generative masked modeling of 3d human motions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1900\u20131910 (2024)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"33_CR24","unstructured":"Guo, C., et al.: Generative human motion stylization in latent space, (2024). arXiv:2401.13505 arXiv preprint"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Cheng, L.: Tm2t: Stochastic and tokenized modeling for the reciprocal generation of 3d human motions and texts. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Guo, Zet al.: Stylemotif: Multi-modal motion stylization using style-content cross fusion. arXiv preprint arXiv:2503.21775 (2025)","DOI":"10.1109\/ICCV51701.2025.01240"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Han, B., Peng, H., Dong, M., Ren, Y., Shen, Y., Xu, C.: Amd: Autoregressive motion diffusion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 2022\u20132030. (2024)","DOI":"10.1609\/aaai.v38i3.27973"},{"key":"33_CR29","doi-asserted-by":"publisher","unstructured":"He, T., Gao, L., Song, J., Li, Y.F.: Towards open-vocabulary scene graph generation with prompt-based finetuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 56\u201373. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_4","DOI":"10.1007\/978-3-031-19815-1_4"},{"key":"33_CR30","doi-asserted-by":"publisher","first-page":"6274","DOI":"10.1109\/TIP.2023.3330304","volume":"32","author":"T He","year":"2023","unstructured":"He, T., Gao, L., Song, J., Li, Y.F.: Toward a unified transformer-based framework for scene graph generation and human-object interaction detection. IEEE Trans. Image Process. 32, 6274\u20136288 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Hu, L., Zhang, Z., Ye, Y., Xu, Y., Xia, S.: Diffusion-based human motion style transfer with semantic guidance. In: Computer Graphics Forum, vol.\u00a043, p. e15169. Wiley Online Library (2024)","DOI":"10.1111\/cgf.15169"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"issue":"3","key":"33_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3516429","volume":"41","author":"DK Jang","year":"2022","unstructured":"Jang, D.K., Park, S., Lee, S.H.: Motion puzzle: Arbitrary motion style transfer by body part. ACM Trans. Graph. (TOG) 41(3), 1\u201316 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"33_CR34","doi-asserted-by":"publisher","first-page":"15497","DOI":"10.52202\/075280-0681","volume":"36","author":"P Jin","year":"2023","unstructured":"Jin, P., Wu, Y., Fan, Y., Sun, Z., Yang, W., Yuan, L.: Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs. Adv. Neural. Inf. Process. Syst. 36, 15497\u201315518 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"33_CR35","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1109\/34.85669","volume":"13","author":"JM Jolion","year":"1991","unstructured":"Jolion, J.M., Meer, P., Bataouche, S.: Robust clustering with applications in computer vision. IEEE Trans. Pattern Anal. Mach. Intell. 13(8), 791\u2013802 (1991)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., Tang, S.: Guided motion diffusion for controllable human motion synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2151\u20132162 (2023)","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Kim, B., et\u00a0al.: Personabooth: Personalized text-to-motion generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22756\u201322765 (2025)","DOI":"10.1109\/CVPR52734.2025.02119"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Kim, B., Kim, J., Chang, H.J., Choi, J.Y.: Most: Motion style transformer between diverse action contents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1705\u20131714 (2024)","DOI":"10.1109\/CVPR52733.2024.00168"},{"key":"33_CR39","unstructured":"Li, W., et al.: Vla-attc: Adaptive test-time compute for vla models with relative action critic model. arXiv preprint arXiv:2605.01194 (2026)"},{"key":"33_CR40","unstructured":"Li, Z., et al.: Mulsmo: Multimodal stylized motion generation by bidirectional control flow. arXiv preprint arXiv:2412.09901 (2024)"},{"key":"33_CR41","doi-asserted-by":"publisher","first-page":"64029","DOI":"10.52202\/075280-2797","volume":"36","author":"J Liang","year":"2023","unstructured":"Liang, J., Cui, Y., Wang, Q., Geng, T., Wang, W., Liu, D.: Clusterfomer: clustering as a universal visual learner. Adv. Neural. Inf. Process. Syst. 36, 64029\u201364042 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR42","unstructured":"Liang, J., Zhou, T., Liu, D., Wang, W.: Clustseg: Clustering for universal segmentation. arXiv preprint arXiv:2305.02187 (2023)"},{"key":"33_CR43","first-page":"1","volume":"62","author":"X Liu","year":"2024","unstructured":"Liu, X., et al.: Pointcluster: Deep clustering of 3-d point clouds with semantic pseudo-labeling. IEEE Trans. Geosci. Remote Sens. 62, 1\u201314 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"33_CR44","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1109\/JAS.2023.123432","volume":"11","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Tian, B., Lv, Y., Li, L., Wang, F.Y.: Point cloud classification using content-based transformer via clustering in feature space. IEEE\/CAA J. Automatica Sinica 11(1), 231\u2013239 (2023)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"33_CR45","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.1109\/TIP.2024.3365249","volume":"33","author":"Y Lu","year":"2024","unstructured":"Lu, Y., Quan, R., Zhu, L., Yang, Y.: Zero-shot video grounding with pseudo query lookup and verification. IEEE Trans. Image Process. 33, 1643\u20131654 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR46","doi-asserted-by":"crossref","unstructured":"Mason, I., Starke, S., Komura, T.: Real-time style modelling of human locomotion via feature-wise transformations and local motion phases. In: Proceedings of the ACM on Computer Graphics and Interactive Techniques, Vol. 5, no. (1), pp. 1\u201318 (2022)","DOI":"10.1145\/3522618"},{"key":"33_CR47","unstructured":"Meng, C., et al.: Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"33_CR48","doi-asserted-by":"publisher","first-page":"7264","DOI":"10.1109\/TIP.2022.3221290","volume":"31","author":"C Niu","year":"2022","unstructured":"Niu, C., Shan, H., Wang, G.: Spice: Semantic pseudo-labeling for image clustering. IEEE Trans. Image Process. 31, 7264\u20137278 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Park, S., Jang, D.K., Lee, S.H.: Diverse motion stylization for multiple style domains via spatial-temporal graph-based generative model. In: Proceedings of the ACM on Computer Graphics and Interactive Techniques, Vol. 4, no. (3), pp. 1\u201317 (2021)","DOI":"10.1145\/3480145"},{"key":"33_CR50","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"33_CR51","doi-asserted-by":"publisher","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: Generating diverse human motions from textual descriptions. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 480\u2013497. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"33_CR52","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TMR: Text-to-motion retrieval using contrastive 3D human motion synthesis. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"33_CR53","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Saleem, M.U., Wang, P., Lee, M., Das, S., Chen, C.: Bamm: Bidirectional autoregressive motion model. In: Computer Vision - ECCV 2024 (2024)","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"33_CR54","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Wang, P., Lee, M., Chen, C.: Mmm: Generative masked motion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"33_CR55","doi-asserted-by":"crossref","unstructured":"Qian, Z., Yang, D., Li, M., Kou, D., Zhang, L.: Mafd: Fine-grained motion style transfer with adaptive signal fusion. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889410"},{"key":"33_CR56","unstructured":"Qu, H., Wei, J., Shu, X., Wang, W.: Learning clustering-based prototypes for compositional zero-shot learning. arXiv preprint arXiv:2502.06501 (2025)"},{"key":"33_CR57","doi-asserted-by":"crossref","unstructured":"Raab, S., et al.: Monkey see, monkey do: Harnessing self-attention in motion diffusion for zero-shot motion transfer. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201313 (2024)","DOI":"10.1145\/3680528.3687579"},{"key":"33_CR58","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"33_CR59","doi-asserted-by":"crossref","unstructured":"Reynolds, D.: Gaussian mixture models. In: Encyclopedia of biometrics, pp. 827\u2013832. Springer, Cham (2015)","DOI":"10.1007\/978-1-4899-7488-4_196"},{"key":"33_CR60","doi-asserted-by":"crossref","unstructured":"Sawdayee, H., Guo, C., Tevet, G., Zhou, B., Wang, J., Bermano, A.H.: Dance like a chicken: Low-rank stylization for human motion diffusion. arXiv preprint arXiv:2503.19557 (2025)","DOI":"10.1111\/cgf.70365"},{"key":"33_CR61","doi-asserted-by":"crossref","unstructured":"Song, W., et al.: Arbitrary motion style transfer with multi-condition motion latent diffusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 821\u2013830 (2024)","DOI":"10.1109\/CVPR52733.2024.00084"},{"key":"33_CR62","doi-asserted-by":"crossref","unstructured":"Tang, X., et al.: Rsmt: Real-time stylized motion transition for characters. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201310 (2023)","DOI":"10.1145\/3588432.3591514"},{"key":"33_CR63","doi-asserted-by":"crossref","unstructured":"Tao, T., Zhan, X., Chen, Z., van\u00a0de Panne, M.: Style-erd: Responsive and coherent online motion style transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6593\u20136603 (2022)","DOI":"10.1109\/CVPR52688.2022.00648"},{"key":"33_CR64","doi-asserted-by":"publisher","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: Exposing human motion generation to clip space. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 358\u2013374. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_21","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"33_CR65","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"33_CR66","doi-asserted-by":"publisher","unstructured":"Wan, W., Dou, Z., Komura, T., Wang, W., Jayaraman, D., Liu, L.: Tlcontrol: Trajectory and language control for human motion synthesis. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision. pp. 37\u201354. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72913-3_3","DOI":"10.1007\/978-3-031-72913-3_3"},{"key":"33_CR67","unstructured":"Wang, W., Han, C., Zhou, T., Liu, D.: Visual recognition with deep nearest centroids. arXiv preprint arXiv:2209.07383 (2022)"},{"key":"33_CR68","doi-asserted-by":"crossref","unstructured":"Wang, Y., Leng, Z., Li, F.W., Wu, S.C., Liang, X.: Fg-t2m: Fine-grained text-driven human motion generation via diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22035\u201322044 (2023)","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"33_CR69","unstructured":"Wei, M., Xie, X., Shi, G.: Acmo: Attribute controllable motion generation. arXiv preprint arXiv:2503.11038 (2025)"},{"key":"33_CR70","doi-asserted-by":"crossref","unstructured":"Wen, Y.H., Yang, Z., Fu, H., Gao, L., Sun, Y., Liu, Y.J.: Autoregressive stylized motion synthesis with generative flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13612\u201313621 (2021)","DOI":"10.1109\/CVPR46437.2021.01340"},{"key":"33_CR71","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: Omnicontrol: Control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580 (2023)"},{"key":"33_CR72","doi-asserted-by":"crossref","unstructured":"Xie, Z., Wu, Y., Gao, X., Sun, Z., Yang, W., Liang, X.: Towards detailed text-to-motion synthesis via basic-to-advanced hierarchical diffusion model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 6252\u20136260 (2024)","DOI":"10.1609\/aaai.v38i6.28443"},{"key":"33_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-030-58621-8_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Xu","year":"2020","unstructured":"Xu, J., Xu, H., Ni, B., Yang, X., Wang, X., Darrell, T.: Hierarchical Style-Based Networks for Motion Synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 178\u2013194. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_11"},{"key":"33_CR74","doi-asserted-by":"crossref","unstructured":"Yan, X., Misra, I., Gupta, A., Ghadiyaram, D., Mahajan, D.: Clusterfit: Improving generalization of visual representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6509\u20136518 (2020)","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"33_CR75","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"33_CR76","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., Kautz, J.: Physdiff: Physics-guided human motion diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16010\u201316021 (2023)","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"33_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, J., Fan, H., Yang, Y.: Energymogen: Compositional human motion generation with energy-based diffusion model in latent space. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17592\u201317602 (2025)","DOI":"10.1109\/CVPR52734.2025.01639"},{"key":"33_CR78","unstructured":"Zhang, J., Fan, H., Yang, Y.: Towards decompositional human motion generation with energy-based diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 30650\u201330660 (2026)"},{"key":"33_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, T., Ding, C., Zhao, H., Guo, G.: Region-level contrastive and consistency learning for semi-supervised semantic segmentation. IJCAI (2022)","DOI":"10.24963\/ijcai.2022\/226"},{"key":"33_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"33_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"issue":"6","key":"33_CR82","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","unstructured":"Zhang, M., et al.: Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Remodiffuse: Retrieval-augmented motion diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 364\u2013373 (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"33_CR84","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Liu, A., Reid, I., Hartley, R., Zhuang, B., Tang, H.: Motion mamba: Efficient and long sequence motion generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 265\u2013282. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_15","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"33_CR85","doi-asserted-by":"crossref","unstructured":"Zhong, C., Hu, L., Zhang, Z., Xia, S.: Attt2m: Text-driven human motion generation with multi-perspective attention mechanism. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 509\u2013519 (2023)","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"33_CR86","doi-asserted-by":"publisher","unstructured":"Zhong, L., Xie, Y., Jampani, V., Sun, D., Jiang, H.: Smoodi: Stylized motion diffusion model. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 405\u2013421. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_23","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"33_CR87","unstructured":"Zhong, L., Yang, Y., Li, C.: Smoogpt: Stylized motion generation using large language models. arXiv preprint arXiv:2509.04058 (2025)"},{"key":"33_CR88","doi-asserted-by":"crossref","unstructured":"Zhou, T., Wang, W., Konukoglu, E., Van Gool, L.: Rethinking semantic segmentation: A prototype view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2582\u20132593 (2022)","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"33_CR89","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wang, B.: Ude: A unified driving engine for human motion generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5632\u20135641 (2023)","DOI":"10.1109\/CVPR52729.2023.00545"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37314-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:53:27Z","timestamp":1789462407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37314-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373137","9783032373144"],"references-count":89,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37314-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"16 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}