{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:40:07Z","timestamp":1748198407385,"version":"3.41.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031915741"},{"type":"electronic","value":"9783031915758"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91575-8_17","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:57:52Z","timestamp":1748195872000},"page":"274-289","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FlexControl: Flexible and\u00a0Efficient Full-Body Controllable Text-to-Motion Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5877-2126","authenticated-orcid":false,"given":"Qingyuan","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1732-8627","authenticated-orcid":false,"given":"Zehai","family":"Niu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3714-1650","authenticated-orcid":false,"given":"Kun","family":"Dong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-802X","authenticated-orcid":false,"given":"Jian","family":"Xue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9720-3220","authenticated-orcid":false,"given":"Xiaoyu","family":"Qin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5916-8965","authenticated-orcid":false,"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"17_CR1","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":"17_CR2","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":"17_CR3","unstructured":"Chen, X., et al.: Learning variational motion prior for video-based motion capture. arXiv preprint arXiv:2210.15134 (2022)"},{"key":"17_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Dou, Z., Chen, X., Fan, Q., Komura, T., Wang, W.: C $$\\cdot $$ ase: learning conditional adversarial skill embeddings for physics-based characters. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201311 (2023)","DOI":"10.1145\/3610548.3618205"},{"key":"17_CR6","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"},{"issue":"3","key":"17_CR7","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/0141-5425(85)90021-4","volume":"7","author":"S Gracovetsky","year":"1985","unstructured":"Gracovetsky, S.: An hypothesis for the role of the spine in human locomotion: a challenge to current thinking. J. Biomed. Eng. 7(3), 205\u2013216 (1985)","journal-title":"J. Biomed. Eng."},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Guo, C., Mu, Y., Javed, M.G., Wang, S., Cheng, L.: Momask: generative masked modeling of 3d human motions (2023)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"17_CR9","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":"17_CR10","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: European Conference on Computer Vision, pp. 580\u2013597. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"17_CR11","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":"17_CR12","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR13","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"17_CR14","unstructured":"Hodgins, J.: Cmu graphics lab motion capture database (2015)"},{"key":"17_CR15","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"17_CR16","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., Tang, S.: Gmd: Controllable human motion synthesis via guided diffusion models. arXiv preprint arXiv:2305.12577 (2023)"},{"key":"17_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"17_CR18","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":"17_CR19","doi-asserted-by":"crossref","unstructured":"Mandery, C., Terlemez, \u00d6., Do, M., Vahrenkamp, N., Asfour, T.: The kit whole-body human motion database. In: 2015 International Conference on Advanced Robotics (ICAR), pp. 329\u2013336. IEEE (2015)","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"issue":"4","key":"17_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459670","volume":"40","author":"XB Peng","year":"2021","unstructured":"Peng, X.B., Ma, Z., Abbeel, P., Levine, S., Kanazawa, A.: Amp: adversarial motion priors for stylized physics-based character control. ACM Trans. Graph. (ToG) 40(4), 1\u201320 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Wang, P., Lee, M., Chen, C.: Mmm: Generative masked motion model. arXiv preprint arXiv:2312.03596 (2023)","DOI":"10.1109\/CVPR52733.2024.00153"},{"issue":"4","key":"17_CR23","first-page":"236","volume":"4","author":"M Plappert","year":"2016","unstructured":"Plappert, M., Mandery, C., Asfour, T.: The kit motion-language dataset. Big Data 4(4), 236\u2013252 (2016)","journal-title":"The kit motion-language dataset. Big Data"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., Guibas, L.J.: Humor: 3d human motion model for robust pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11488\u201311499 (2021)","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"17_CR25","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418 (2023)"},{"issue":"4","key":"17_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530178","volume":"41","author":"S Starke","year":"2022","unstructured":"Starke, S., Mason, I., Komura, T.: Deepphase: periodic autoencoders for learning motion phase manifolds. ACM Trans. Graph. (TOG) 41(4), 1\u201313 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"6","key":"17_CR27","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1145\/3355089.3356505","volume":"38","author":"S Starke","year":"2019","unstructured":"Starke, S., Zhang, H., Komura, T., Saito, J.: Neural state machine for character-scene interactions. ACM Trans. Graph. 38(6), 178 (2019)","journal-title":"ACM Trans. Graph."},{"key":"17_CR28","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"17_CR29","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Advances in neural information processing systems 30 (2017)"},{"key":"17_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"17_CR31","unstructured":"Wang, C.: T2m-hifigpt: generating high quality human motion from textual descriptions with residual discrete representations, December 2023"},{"key":"17_CR32","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: Omnicontrol: control any joint at any time for human motion generation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"17_CR33","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","volume":"30","author":"N Zeghidour","year":"2021","unstructured":"Zeghidour, N., Luebs, A., Omran, A., Skoglund, J., Tagliasacchi, M.: Soundstream: an end-to-end neural audio codec. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 495\u2013507 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"17_CR34","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":"17_CR35","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"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., Liu, Z.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"17_CR37","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, pp. 509\u2013519 (2023)","DOI":"10.1109\/ICCV51070.2023.00053"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91575-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T17:58:01Z","timestamp":1748195881000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91575-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915741","9783031915758"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91575-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}