{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:29Z","timestamp":1788934049184,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372314","type":"print"},{"value":"9783032372321","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\/978-3-032-37232-1_28","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:53:23Z","timestamp":1788933203000},"page":"509-527","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ARMS: Anchor\u2013Relational Motion Streaming for\u00a0Seamless Solo-Social Motion Transitions"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9130-2519","authenticated-orcid":false,"given":"Huakun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6965-9581","authenticated-orcid":false,"given":"Qing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2205-6115","authenticated-orcid":false,"given":"Kent","family":"Fujiwara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6119-1184","authenticated-orcid":false,"given":"Hideaki","family":"Uchiyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2260-1707","authenticated-orcid":false,"given":"Kiyoshi","family":"Kiyokawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"issue":"209","key":"28_CR1","first-page":"1","volume":"26","author":"M Albergo","year":"2025","unstructured":"Albergo, M., Boffi, N.M., Vanden-Eijnden, E.: Stochastic interpolants: a unifying framework for flows and diffusions. J. Mach. Learn. Res. 26(209), 1\u201380 (2025)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR2","unstructured":"Albergo, M.S., Vanden-Eijnden, E.: Building normalizing flows with stochastic interpolants. In: The Eleventh International Conference on Learning Representations (2023)"},{"issue":"4","key":"28_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592458","volume":"42","author":"S Alexanderson","year":"2023","unstructured":"Alexanderson, S., Nagy, R., Beskow, J., Henter, G.E.: Listen, denoise, action! audio-driven motion synthesis with diffusion models. ACM Trans. Graph. (TOG) 42(4), 1\u201320 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., Palmero, C.: Seamless human motion composition with blended positional encodings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 457\u2013469 (2024)","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Z., et al.: Digital life project: autonomous 3d characters with social intelligence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 582\u2013592 (2024)","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"28_CR6","unstructured":"Cen, Z., et al.: Ready-to-react: online reaction policy for two-character interaction generation. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Diffusion forcing: next-token prediction meets full-sequence diffusion. Adv. Neural Inf. Process. Syst. 37, 24081\u201324125 (2024)","DOI":"10.52202\/079017-0759"},{"key":"28_CR8","unstructured":"Chen, J., Hu, P., Chang, X., Shi, Z., Kampffmeyer, M., Liang, X.: Sitcom-crafter: a plot-driven human motion generation system in 3d scenes. In: The Thirteenth International Conference on Learning Representations (2025)"},{"issue":"4","key":"28_CR9","first-page":"1","volume":"40","author":"K Chen","year":"2021","unstructured":"Chen, K., et al.: Choreomaster: choreography-oriented music-driven dance synthesis. ACM Trans. Graph. (TOG) 40(4), 1\u201313 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Chen, R., Shi, M., Huang, S., Tan, P., Komura, T., Chen, X.: Taming diffusion probabilistic models for character control. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201310 (2024)","DOI":"10.1145\/3641519.3657440"},{"key":"28_CR11","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":"28_CR12","doi-asserted-by":"crossref","unstructured":"Ghosh, A., et al.: Duetgen: music driven two-person dance generation via hierarchical masked modeling. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3721238.3730741"},{"key":"28_CR13","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":"28_CR14","doi-asserted-by":"publisher","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: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13695, pp. 580\u2013597. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_34","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Action2motion: conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"28_CR16","unstructured":"Javed, M.G., Li, X.: Intermask: 3d human interaction generation via collaborative masked modeling. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: Motiongpt: human motion as a foreign language. Adv. Neural Inf. Process. Syst. 36, 20067\u201320079 (2023)","DOI":"10.52202\/075280-0880"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with aist. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13401\u201313412 (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"issue":"9","key":"28_CR19","doi-asserted-by":"publisher","first-page":"3463","DOI":"10.1007\/s11263-024-02042-6","volume":"132","author":"H Liang","year":"2024","unstructured":"Liang, H., Zhang, W., Li, W., Yu, J., Xu, L.: Intergen: diffusion-based multi-human motion generation under complex interactions. Int. J. Comput. Vis. 132(9), 3463\u20133483 (2024)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Lim, D., Bae, J., Hwang, I., Lee, S., Lee, H., Kim, Y.M.: Event-driven storytelling with multiple lifelike humans in a 3D scene. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11654\u201311664 (2025)","DOI":"10.1109\/ICCV51701.2025.01084"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Het al.: EMAGE: towards unified holistic co-speech gesture generation via expressive masked audio gesture modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1144\u20131154 (2024)","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"28_CR22","unstructured":"Liu, M., et al.: Hint: hierarchical interaction modeling for autoregressive multi-human motion generation (2026). arXiv preprint arXiv:2601.20383"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: Amass: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"28_CR24","unstructured":"Meng, Z., Han, Z., Peng, X., Xie, Y., Jiang, H.: Absolute coordinates make motion generation easy (2025). arXiv preprint arXiv:2505.19377"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Mullen, J.F., Kothandaraman, D., Bera, A., Manocha, D.: Placing human animations into 3D scenes by learning interaction-and geometry-driven keyframes. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 300\u2013310 (2023)","DOI":"10.1109\/WACV56688.2023.00038"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Ota, S., Yu, Q., Fujiwara, K., Ikehata, S., Sato, I.: Pino: person-interaction noise optimization for long-duration and customizable motion generation of arbitrary-sized groups. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10676\u201310685 (2025)","DOI":"10.1109\/ICCV51701.2025.00994"},{"key":"28_CR27","unstructured":"Ouyang, R., et al.: Motion-r1: chain-of-thought reasoning and reinforcement learning for human motion generation. arXiv e-prints, pp. arXiv\u20132506 (2025)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer vae. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"28_CR31","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.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13682, 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":"28_CR32","doi-asserted-by":"crossref","unstructured":"Petrovich, M., et al.: Multi-track timeline control for text-driven 3d human motion generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1911\u20131921 (2024)","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Ruiz-Ponce, P., Barquero, G., Palmero, C., Escalera, S., Garc\u00eda-Rodr\u00edguez, J.: in2IN: leveraging individual information to generate human interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1941\u20131951 (2024)","DOI":"10.1109\/CVPRW63382.2024.00200"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Ruiz-Ponce, P., Barquero, G., Palmero, C., Escalera, S., Garc\u00eda-Rodr\u00edguez, J.: Mixermdm: learnable composition of human motion diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12380\u201312390 (2025)","DOI":"10.1109\/CVPR52734.2025.01155"},{"key":"28_CR35","unstructured":"Ruiz-Ponce, P., Escalera, S., Garc\u00eda-Rodr\u00edguez, J., Deng, J., Potamias, R.A.: Interact2ar: full-body human-human interaction generation via autoregressive diffusion models, (2025). arXiv preprint arXiv:2512.19692"},{"key":"28_CR36","unstructured":"Sahili, A.R., Neji, N., Tabia, H.: Text-driven motion generation: overview, challenges and directions (2025). arXiv preprint arXiv:2505.09379"},{"key":"28_CR37","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter (2019). arXiv preprint arXiv:1910.01108"},{"key":"28_CR38","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. In: The Twelfth International Conference on Learning Representations (2024)"},{"issue":"4","key":"28_CR39","first-page":"1","volume":"43","author":"Y Shi","year":"2024","unstructured":"Shi, Y., Wang, J., Jiang, X., Lin, B., Dai, B., Peng, X.B.: Interactive character control with auto-regressive motion diffusion models. ACM Trans. Graph. (TOG) 43(4), 1\u201314 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"28_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"issue":"3","key":"28_CR41","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11263-025-02582-5","volume":"134","author":"K Sui","year":"2026","unstructured":"Sui, K., Ghosh, A., Hwang, I., Zhou, B., Wang, J., Guo, C.: A survey on human interaction motion generation. Int. J. Comput. Vis. 134(3), 113 (2026)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Tanaka, M., Fujiwara, K.: Role-aware interaction generation from textual description. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15999\u201316009 (2023)","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"28_CR43","unstructured":"Tevet, G., et al.: Closd: closing the loop between simulation and diffusion for multi-task character control. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"28_CR44","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model (2022). arXiv preprint arXiv:2209.14916"},{"key":"28_CR45","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)"},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Timotion: temporal and interactive framework for efficient human-human motion generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 7169\u20137178 (2025)","DOI":"10.1109\/CVPR52734.2025.00672"},{"key":"28_CR47","unstructured":"Wu, Q., et al.: Text2interact: high-fidelity and diverse text-to-two-person interaction generation (2025). arXiv preprint arXiv:2510.06504"},{"key":"28_CR48","doi-asserted-by":"crossref","unstructured":"Xiao, L., et al.: Motionstreamer: streaming motion generation via diffusion-based autoregressive model in causal latent space. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10086\u201310096 (2025)","DOI":"10.1109\/ICCV51701.2025.00940"},{"key":"28_CR49","doi-asserted-by":"crossref","unstructured":"Xu, L., et\u00a0al.: Inter-x: towards versatile human-human interaction analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22260\u201322271 (2024)","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Yu, H., et al.: Socialgen: modeling multi-human social interaction with language models. In: Thirteenth International Conference on 3D Vision (2025)","DOI":"10.1109\/3DV69130.2026.00175"},{"key":"28_CR51","unstructured":"Yu, Q., Watanabe, A., Fujiwara, K.: Causal motion diffusion models for autoregressive motion generation (2026). arXiv preprint arXiv:2602.22594"},{"key":"28_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Primal: physically reactive and interactive motor model for avatar learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12725\u201312736 (2025)","DOI":"10.1109\/ICCV51701.2025.01182"},{"key":"28_CR53","unstructured":"Zhao, K., Li, G., Tang, S.: Dartcontrol: a diffusion-based autoregressive motion model for real-time text-driven motion control. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"28_CR54","doi-asserted-by":"crossref","unstructured":"Zhao, K., Zhang, Y., Wang, S., Beeler, T., Tang, S.: Synthesizing diverse human motions in 3d indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14738\u201314749 (2023)","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"28_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"28_CR56","unstructured":"Zhu, B., et al.: Motiongpt3: human motion as a second modality. arXiv preprint arXiv: 2506.24086 (2025)"},{"key":"28_CR57","doi-asserted-by":"crossref","unstructured":"Zhuo, W., Ma, F., Fan, H.: Infinidreamer: arbitrarily long human motion generation via segment score distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14688\u201314698 (2025)","DOI":"10.1109\/ICCV51701.2025.01363"}],"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\/978-3-032-37232-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:53:35Z","timestamp":1788933215000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37232-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372314","9783032372321"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37232-1_28","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":"10 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"}}]}}