{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T16:18:01Z","timestamp":1771604281966,"version":"3.50.1"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"1","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"}],"funder":[{"name":"MOE AcRF Tier 2","award":["MOET2EP20221- 0012"],"award-info":[{"award-number":["MOET2EP20221- 0012"]}]},{"name":"MOE AcRF Tier 2","award":["MOE-T2EP20223-0002"],"award-info":[{"award-number":["MOE-T2EP20223-0002"]}]},{"name":"RIE2020 Industry Alignment Fund \u2013 Industry Collaboration Projects (IAF-ICP) Funding Initiative"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11263-025-02677-z","type":"journal-article","created":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T02:40:19Z","timestamp":1767494419000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CrowdMoGen: Event-Driven Collective Human Motion Generation"],"prefix":"10.1007","volume":"134","author":[{"given":"Yukang","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinying","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozhe","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"2677_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S. Anadkat, S. and others. (2023) Gpt-4 technical report. arXiv preprint arXiv:2303.08774."},{"key":"2677_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, H., Mascaro, D., & Esteve an\u00a0Lee, V. (2023). Can we use diffusion probabilistic models for 3d motion prediction? In 2023 IEEE International Conference on Robotics and Automation (ICRA).","DOI":"10.1109\/ICRA48891.2023.10160722"},{"key":"2677_CR3","doi-asserted-by":"crossref","unstructured":"Ahn, H., Mascaro, E. V., & Lee, D. (2023). Can we use diffusion probabilistic models for 3d motion prediction? arXiv preprint arXiv:2302.14503.","DOI":"10.1109\/ICRA48891.2023.10160722"},{"key":"2677_CR4","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M. J., & Varol, G. (2022). Teach: Temporal action composition for 3d humans. In 2022 International Conference on 3D Vision (3DV), (pp. 414\u2013423). IEEE.","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"2677_CR5","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., & Palmero, C. (2023). Belfusion: Latent diffusion for behavior-driven human motion prediction. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 2317\u20132327).","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"2677_CR6","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Kender, J., & Liu, Z. (2018). Hp-gan: Probabilistic 3d human motion prediction via gan. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, (pp. 1418\u20131427).","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"2677_CR7","doi-asserted-by":"crossref","unstructured":"Bhatnagar, B. L., Xie, X., Petrov, I. A., Sminchisescu, C., Theobalt, C., & Pons-Moll, G. (2022). Behave: Dataset and method for tracking human object interactions. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 15935\u201315946).","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"2677_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Z., Jiang, J., Qing, Z., Guo, X., Zhang, M., Lin, Z., Mei, H., Wei, C., Wang, R., Yin, W. and others. (2023). Digital life project: Autonomous 3d characters with social intelligence. arXiv preprint arXiv:2312.04547.","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"2677_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.-H., Zhang, J., Li, Y., Pang, Y., Xia, X., & Liu, T. (2023a). Humanmac: Masked motion completion for human motion prediction.","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"2677_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., & Yu, G. (2023b). 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).","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"2677_CR11","doi-asserted-by":"crossref","unstructured":"Dai, W., Chen, L.-H., Wang, J., Liu, J., Dai, B., & Tang, Y. (2024). Motionlcm: Real-time controllable motion generation via latent consistency model. In European Conference on Computer Vision, (pp. 390\u2013408). Springer.","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"2677_CR12","doi-asserted-by":"crossref","unstructured":"Diller, C., & Dai, A. (2023). Cg-hoi: Contact-guided 3d human-object interaction generation. arXiv preprint arXiv:2311.16097.","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"2677_CR13","doi-asserted-by":"crossref","unstructured":"Diller, C., Funkhouser, T., & Dai, A. (2022). Forecasting characteristic 3d poses of human actions.","DOI":"10.1109\/CVPR52688.2022.01545"},{"key":"2677_CR14","doi-asserted-by":"crossref","unstructured":"Gopalakrishnan, A., Mali, A., Kifer, D., Giles, L., & Ororbia, A. G. (2019). A neural temporal model for human motion prediction. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 12116\u201312125).","DOI":"10.1109\/CVPR.2019.01239"},{"key":"2677_CR15","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Zou, S., Sun, Q., Deng, A., Gong, M., Cheng, L. (2020). Action2motion: Conditioned generation of 3d human motions. In Proceedings of the 28th ACM International Conference on Multimedia, (pp. 2021\u20132029).","DOI":"10.1145\/3394171.3413635"},{"key":"2677_CR16","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., & Cheng, L. (2022). 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).","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"2677_CR17","doi-asserted-by":"crossref","unstructured":"Guo, W., Du, Y., Shen, X., Lepetit, V., Alameda-Pineda, X., & Moreno-Noguer, F. (2023). Back to mlp: A simple baseline for human motion prediction. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, (pp. 4809\u20134819).","DOI":"10.1109\/WACV56688.2023.00479"},{"key":"2677_CR18","doi-asserted-by":"crossref","unstructured":"Hao, Y., Zhang, J., Zhuo, T., Wen, F., & Fan, H. (2024). Hand-centric motion refinement for 3d hand-object interaction via hierarchical spatial-temporal modeling. arXiv preprint arXiv:2401.15987.","DOI":"10.1609\/aaai.v38i3.27979"},{"key":"2677_CR19","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840\u20136851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2677_CR20","doi-asserted-by":"crossref","unstructured":"Hoang, N. M., Gong, K., Guo, C., & Mi, M. B. (2024). Motionmix: Weakly-supervised diffusion for controllable motion generation. arXiv preprint arXiv:2401.11115.","DOI":"10.1609\/aaai.v38i3.27988"},{"key":"2677_CR21","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, Z., Li, P., Jia, B., Liu, T., Zhu, Y., Liang, W., & Zhu, S.-C. (2023). Diffusion-based generation, optimization, and planning in 3d scenes. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 16750\u201316761).","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"2677_CR22","unstructured":"Javed, M. G., Guo, C., Cheng, L., & Li, X. (2024). Intermask: 3d human interaction generation via collaborative masked modeling. arXiv preprint arXiv:2410.10010."},{"key":"2677_CR23","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., & Chen, T. (2024). Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems, 36."},{"key":"2677_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, C., Cornman, A., Park, C., Sapp, B., Zhou, Y., Anguelov, D.and others. (2023a). Motiondiffuser: Controllable multi-agent motion prediction using diffusion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 9644\u20139653).","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"2677_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, N., Liu, T., Cao, Z., Cui, J., Zhang, Z., Chen, Y., Wang, H., Zhu, Y., & Huang, S. (2023b). Full-body articulated human-object interaction. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 9365\u20139376).","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"2677_CR26","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., & Tang, S. (2023). Guided motion diffusion for controllable human motion synthesis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 2151\u20132162).","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"2677_CR27","doi-asserted-by":"publisher","first-page":"8255","DOI":"10.1609\/aaai.v37i7.25996","volume":"37","author":"J Kim","year":"2023","unstructured":"Kim, J., Kim, J., & Choi, S. (2023). Flame: Free-form language-based motion synthesis & editing. In Proceedings of the AAAI Conference on Artificial Intelligence, 37, 8255\u20138263.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2677_CR28","doi-asserted-by":"crossref","unstructured":"Kulal, S., Mao, J., Aiken, A., & Wu, J. (2022). Programmatic concept learning for human motion description and synthesis. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 13843\u201313852).","DOI":"10.1109\/CVPR52688.2022.01347"},{"key":"2677_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., Clegg, A., Mottaghi, R., Wu, J., Puig, X., & Liu, C. K. (2023a). Controllable human-object interaction synthesis. arXiv preprint arXiv:2312.03913.","DOI":"10.1007\/978-3-031-72940-9_4"},{"issue":"6","key":"2677_CR30","first-page":"1","volume":"42","author":"J Li","year":"2023","unstructured":"Li, J., Wu, J., & Liu, C. K. (2023). Object motion guided human motion synthesis. ACM Transactions on Graphics (TOG), 42(6), 1\u201311.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2677_CR31","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D. A., & Kanazawa, A. (2021). Ai choreographer: Music conditioned 3d dance generation with aist++. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 13401\u201313412).","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"2677_CR32","unstructured":"Liang, H., Zhang, W., Li, W., Yu, J., & Xu, L. (2023). Intergen: Diffusion-based multi-human motion generation under complex interactions. arXiv preprint arXiv:2304.05684."},{"issue":"9","key":"2677_CR33","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. (2024). Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision, 132(9), 3463\u20133483.","journal-title":"International Journal of Computer Vision"},{"key":"2677_CR34","doi-asserted-by":"crossref","unstructured":"Lim, D., Jeong, C., & Kim, Y. M. (2023). Mammos: Mapping multiple human motion with scene understanding and natural interactions. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 4278\u20134287).","DOI":"10.1109\/ICCVW60793.2023.00462"},{"key":"2677_CR35","unstructured":"Lin, J., Chang, J., Liu, L., Li, G., Lin, L., Tian, Q., & Chen, C.-W. (2022). Ohmg: Zero-shot open-vocabulary human motion generation. arXiv preprint arXiv:2210.15929."},{"key":"2677_CR36","unstructured":"Lin, P., Xu, S., Yang, H., Liu, Y., Chen, X., Wang, J., Yu, J., & Xu, L. (2023). Handdiffuse: Generative controllers for two-hand interactions via diffusion models. arXiv preprint arXiv:2312.04867."},{"key":"2677_CR37","doi-asserted-by":"crossref","unstructured":"Liu, X., Hou, H., Yang, Y., Li, Y.-L., & Lu, C. (2023). Revisit human-scene interaction via space occupancy. arXiv preprint arXiv:2312.02700.","DOI":"10.1007\/978-3-031-72973-7_1"},{"key":"2677_CR38","unstructured":"Lou, Y., Zhu, L., Wang, Y., Wang, X., & Yang, Y. (2023). Diversemotion: Towards diverse human motion generation via discrete diffusion. arXiv preprint arXiv:2309.01372."},{"key":"2677_CR39","unstructured":"Lu, S., Chen, L.-H., Zeng, A., Lin, J., Zhang, R., Zhang, L., & Shum, H.-Y. (2023). Humantomato: Text-aligned whole-body motion generation. arXiv preprint arXiv:2310.12978."},{"key":"2677_CR40","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N. F., Pons-Moll, G., & Black, M. J. (2019). Amass: Archive of motion capture as surface shapes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 5442\u20135451).","DOI":"10.1109\/ICCV.2019.00554"},{"key":"2677_CR41","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., & Salzmann, M. (2020). History repeats itself: Human motion prediction via motion attention. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16, (pp. 474\u2013489). Springer.","DOI":"10.1007\/978-3-030-58568-6_28"},{"key":"2677_CR42","unstructured":"Okamura, M., Kondo, N., Sakamoto, T. F. M., & Ochiai, Y. (2023). Dance generation by sound symbolic words. arXiv preprint arXiv:2306.03646."},{"key":"2677_CR43","unstructured":"Peng, X., Xie, Y., Wu, Z., Jampani, V., Sun, D., & Jiang, H. (2023) Hoi-diff: Text-driven synthesis of 3d human-object interactions using diffusion models. arXiv preprint arXiv:2312.06553."},{"key":"2677_CR44","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M. J., & Varol, G. (2021). Action-conditioned 3d human motion synthesis with transformer vae. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 10985\u201310995).","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"2677_CR45","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M. J., & Varol, G. (2022). Temos: Generating diverse human motions from textual descriptions. In European Conference on Computer Vision, (pp. 480\u2013497). Springer.","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"2677_CR46","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Litany, O., Iqbal, U., Black, M. J., Varol, G., Peng, X. B., & Rempe, D. (2024). Multi-track timeline control for text-driven 3d human motion generation. arXiv preprint arXiv:2401.08559.","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"2677_CR47","doi-asserted-by":"crossref","unstructured":"Pi, H., Peng, S., Yang, M., Zhou, X., & Bao, H. (2023). Hierarchical generation of human-object interactions with diffusion probabilistic models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 15061\u201315073).","DOI":"10.1109\/ICCV51070.2023.01383"},{"issue":"4","key":"2677_CR48","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1089\/big.2016.0028","volume":"4","author":"M Plappert","year":"2016","unstructured":"Plappert, M., Mandery, C., & Asfour, T. (2016). The kit motion-language dataset. Big data, 4(4), 236\u2013252.","journal-title":"Big data"},{"key":"2677_CR49","doi-asserted-by":"crossref","unstructured":"Rempe, D., Luo, Z., Peng, X. B., Yuan, Y., Kitani, K., Kreis, K., Fidler, S., & Litany, O. (2023). Trace and pace: Controllable pedestrian animation via guided trajectory diffusion. In Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"2677_CR50","unstructured":"Ren, J., Zhang, M., Yu, C., Ma, X., Pan, L., & Liu, Z. (2024). Insactor: Instruction-driven physics-based characters. Advances in Neural Information Processing Systems, 36."},{"key":"2677_CR51","unstructured":"Shafir, Y., Tevet, G., Kapon, R., & Bermano, A. H. (2023). Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418."},{"key":"2677_CR52","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., & Li, H. (2021). Efficient attention: Attention with linear complexities. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, (pp. 3531\u20133539)."},{"key":"2677_CR53","unstructured":"Shi, X., Luo, C., Peng, J., Zhang, H., & Sun, Y. (2023). Generating fine-grained human motions using chatgpt-refined descriptions. arXiv preprint arXiv:2312.02772."},{"key":"2677_CR54","doi-asserted-by":"crossref","unstructured":"Shimada, S., Mueller, F., Bednarik, J., Doosti, B., Bickel, B., Tang, D., Golyanik, V., Taylor, J., Theobalt, C., & Beeler, T. (2023). Macs: Mass conditioned 3d hand and object motion synthesis. arXiv preprint arXiv:2312.14929.","DOI":"10.1109\/3DV62453.2024.00082"},{"key":"2677_CR55","doi-asserted-by":"crossref","unstructured":"Siyao, L., Yu, W., Gu, T., Lin, C., Wang, Q., Qian, C., Loy, C.\u00a0C., & Liu, Z. (2022). Bailando: 3d dance generation by actor-critic gpt with choreographic memory. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 11050\u201311059).","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"2677_CR56","first-page":"30169","volume":"34","author":"J Sun","year":"2021","unstructured":"Sun, J., Lin, Z., Han, X., Jian-Fang, H., Jia, X., & Zheng, W.-S. (2021). Action-guided 3d human motion prediction. Advances in Neural Information Processing Systems, 34, 30169\u201330180.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2677_CR57","doi-asserted-by":"crossref","unstructured":"Sun, J., & Chowdhary, G. (2023). Towards globally consistent stochastic human motion prediction via motion diffusion. arXiv preprint arXiv:2305.12554.","DOI":"10.1007\/978-3-031-73036-8_2"},{"key":"2677_CR58","doi-asserted-by":"crossref","unstructured":"Tendulkar, P., Sur\u00eds, D., & Vondrick, C. (2023). Flex: Full-body grasping without full-body grasps. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 21179\u201321189).","DOI":"10.1109\/CVPR52729.2023.02029"},{"key":"2677_CR59","doi-asserted-by":"crossref","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A. H., & Cohen-Or, D. (2022a). Motionclip: Exposing human motion generation to clip space. In European Conference on Computer Vision, pages 358\u2013374. Springer.","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"2677_CR60","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., & Bermano, A.\u00a0H. (2022b). Human motion diffusion model. In The Eleventh International Conference on Learning Representations."},{"key":"2677_CR61","doi-asserted-by":"crossref","unstructured":"Wang, X., Cui, Q., Chen, C., & Liu, M. (2023). Gcnext: Towards the unity of graph convolutions for human motion prediction. arXiv preprint arXiv:2312.11850.","DOI":"10.1609\/aaai.v38i6.28375"},{"key":"2677_CR62","volume-title":"and Bo Dai","author":"Z Wang","year":"2024","unstructured":"Wang, Z., Wang, J., Li, Y., & Lin, D. (2024). and Bo Dai. Intercontrol: Generate human motion interactions by controlling every joint."},{"key":"2677_CR63","unstructured":"Xiao, Z., Wang, T., Wang, J., Cao, J., Zhang, W., Dai, B., Lin, D., & Pang, J. (2023). Unified human-scene interaction via prompted chain-of-contacts. arXiv preprint arXiv:2309.07918."},{"key":"2677_CR64","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., & Jiang, H. (2023). Omnicontrol: Control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580."},{"key":"2677_CR65","doi-asserted-by":"crossref","unstructured":"Xu, L., Lv, X., Yan, Y., Jin, X., Wu, S., Xu, C., Liu, Y., Zhou, Y., Rao, F., Sheng, X. and others. (2024). Inter-x: Towards versatile human-human interaction analysis. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 22260\u201322271).","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"2677_CR66","unstructured":"Yan, H., Hu, Z., Schmitt, S., & Bulling, A. (2023). Gazemodiff: Gaze-guided diffusion model for stochastic human motion prediction. arXiv preprint arXiv:2312.12090."},{"key":"2677_CR67","doi-asserted-by":"crossref","unstructured":"Yao, S., Sun, M., Li, B., Yang, F., Wang, J., & Zhang, R. (2023). Dance with you: The diversity controllable dancer generation via diffusion models. In Proceedings of the 31st ACM International Conference on Multimedia, (pp. 8504\u20138514).","DOI":"10.1145\/3581783.3612046"},{"key":"2677_CR68","unstructured":"Yazdian, P. J., Lagasse, R., Mohammadi, H., Liu, E., Cheng, L., & Lim, A. (2023). Motionscript: Natural language descriptions for expressive 3d human motions. arXiv preprint arXiv:2312.12634"},{"key":"2677_CR69","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., & Kautz, J. (2023). Physdiff: Physics-guided human motion diffusion model. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 16010\u201316021).","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"2677_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Cun, X., Zhang, Y., Zhao, H., Lu, H., & Shan, Y. (2023a). T2m-gpt: Generating human motion from textual descriptions with discrete representations. arXiv preprint arXiv:2301.06052.","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"2677_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023b). Adding conditional control to text-to-image diffusion models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2677_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, M., Guo, X., Pan, L., Cai, Z., Hong, F., Li, H., Yang, L., & Liu, Z. (2023c) Remodiffuse: Retrieval-augmented motion diffusion model. In IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023, (pp. 364\u2013373).","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"2677_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., & Liu, Z. (2024a). Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"2677_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, M., Jin, D., Gu, C., Hong, F., Cai, Z., Huang, J., Zhang, C., Guo, X., Yang, L., He, Y., & Liu, Z. (2024b). Large motion model for unified multi-modal motion generation.","DOI":"10.1007\/978-3-031-72624-8_23"},{"key":"2677_CR75","unstructured":"Zhang, M., Li, H., Cai, Z., Ren, J., Yang, L., & Liu, Z. (2024c). Finemogen: Fine-grained spatio-temporal motion generation and editing. Advances in Neural Information Processing Systems, 36."},{"key":"2677_CR76","unstructured":"Zhao, M., Liu, M., Ren, B., Dai, S., & Sebe, N. (2023). Modiff: Action-conditioned 3d motion generation with denoising diffusion probabilistic models. arXiv preprint arXiv:2301.03949."},{"key":"2677_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, W., Dou, Z., Cao, Z., Liao, Z., Wang, J., Wang, W., Liu, Y., Komura, T., Wang, W., & Liu, L. (2023). Emdm: Efficient motion diffusion model for fast, high-quality motion generation. arXiv preprint arXiv:2312.02256.","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"2677_CR78","unstructured":"Zhu, W., Qin, J., Lou, Y., Ye, H., Ma, X., Ci, H., & Wang, Y. (2023). Social motion prediction with cognitive hierarchies. In A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine, editors, Advances in Neural Information Processing Systems, volume\u00a036, pages 77675\u201377690. Curran Associates, Inc.. URL https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/f4b52b45a677d855dee0ca9ba1ddf638-Paper-Conference.pdf."},{"issue":"2","key":"2677_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3485664","volume":"18","author":"W Zhuang","year":"2022","unstructured":"Zhuang, W., Wang, C., Chai, J., Wang, Y., Shao, M., & Xia, S. (2022). Music2dance: Dancenet for music-driven dance generation. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 18(2), 1\u201321.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02677-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02677-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02677-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:43:22Z","timestamp":1771602202000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02677-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":79,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2677"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02677-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"15 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"29"}}