{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T16:04:40Z","timestamp":1785341080451,"version":"3.55.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73397-0_11","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:07:20Z","timestamp":1730574440000},"page":"180-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["CoMo: Controllable Motion Generation Through Language Guided Pose Code Editing"],"prefix":"10.1007","author":[{"given":"Yiming","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weilin","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Callison-Burch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Yatskar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingjie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: Teach: temporal action compositions for 3d humans. In: International Conference on 3D Vision (3DV), September 2022","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: SINC: spatial composition of 3D human motions for simultaneous action generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., Huang, Z., Fu, B., Chen, T., Yu, G.: 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":"11_CR4","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., Theobalt, C.: Mofusion: framework for denoising-diffusion-based motion synthesis. In: Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Delmas, G., Weinzaepfel, P., Lucas, T., Moreno-Noguer, F., Rogez, G.: Posescript: 3d human poses from natural language (2022)","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Delmas, G., Weinzaepfel, P., Moreno-Noguer, F., Rogez, G.: Posefix: Correcting 3d human poses with natural language (2023)","DOI":"10.1109\/ICCV51070.2023.01379"},{"key":"11_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Dou, Z., Chen, X., Fan, Q., Komura, T., Wang, W.: Case: 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":"11_CR9","doi-asserted-by":"crossref","unstructured":"Goel, P., Wang, K.C., Liu, C.K., Fatahalian, K.: Iterative motion editing with natural language (2023)","DOI":"10.1145\/3641519.3657447"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152\u20135161, June 2022","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"11_CR11","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":"11_CR12","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":"11_CR13","doi-asserted-by":"publisher","unstructured":"Holden, D., Saito, J., Komura, T.: A Deep Learning Framework for Character Motion Synthesis and Editing. Association for Computing Machinery, New York, NY, USA, 1 edn. (2023). https:\/\/doi.org\/10.1145\/3596711.3596789","DOI":"10.1145\/3596711.3596789"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Diffusion-based generation, optimization, and planning in 3d scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"11_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":"11_CR16","unstructured":"Jin, P., Wu, Y., Fan, Y., Sun, Z., Wei, Y., Yuan, L.: Act as you wish: fine-grained control of motion diffusion model with hierarchical semantic graphs. In: NeurIPS (2023)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Kalakonda, S.S., Maheshwari, S., Sarvadevabhatla, R.K.: Action-gpt: leveraging large-scale language models for improved and generalized action generation (2023)","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Kim, J., Kim, J., Choi, S.: Flame: free-form language-based motion synthesis editing. In: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence. AAAI\u201923\/IAAI\u201923\/EAAI\u201923, AAAI Press (2023). https:\/\/doi.org\/10.1609\/aaai.v37i7.25996, https:\/\/doi.org\/10.1609\/aaai.v37i7.25996","DOI":"10.1609\/aaai.v37i7.25996 10.1609\/aaai.v37i7.25996"},{"key":"11_CR19","unstructured":"Lab, C.M.U.G.: Cmu graphics lab motion capture database (2004)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graphics (Proc. SIGGRAPH Asia) 34(6), 248:1\u2013248:16 (Oct 2015)","DOI":"10.1145\/2816795.2818013"},{"key":"11_CR21","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: International Conference on Computer Vision, pp. 5442\u20135451 (Oct 2019)","DOI":"10.1109\/ICCV.2019.00554"},{"issue":"4","key":"11_CR22","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/TRO.2016.2572685","volume":"32","author":"C Mandery","year":"2016","unstructured":"Mandery, C., Terlemez, O., Do, M., Vahrenkamp, N., Asfour, T.: Unifying representations and large-scale whole-body motion databases for studying human motion. IEEE Trans. Rob. 32(4), 796\u2013809 (2016)","journal-title":"IEEE Trans. Rob."},{"key":"11_CR23","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. CoRR abs\/1711.00937 (2017). http:\/\/arxiv.org\/abs\/1711.00937"},{"key":"11_CR24","unstructured":"OpenAI, R.: Gpt-4 technical report. arXiv pp. 2303\u201308774 (2023)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: Generating diverse human motions from textual descriptions. In: Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 480\u2013497. Springer, Heidelberg (2022)","DOI":"10.1007\/978-3-031-20047-2_28"},{"issue":"4","key":"11_CR26","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":"11_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"11_CR28","unstructured":"Ren, J., Yu, C., Chen, S., Ma, X., Pan, L., Liu, Z.: Diffmimic: efficient motion mimicking with differentiable physics. ICLR (2022)"},{"key":"11_CR29","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior (2023)"},{"key":"11_CR30","unstructured":"Shi, X., Luo, C., Peng, J., Zhang, H., Sun, Y.: Generating fine-grained human motions using chatgpt-refined descriptions (2023)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Siyao, L., et al.: Bailando: 3d dance generation via actor-critic gpt with choreographic memory. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: Exposing human motion generation to clip space. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 358\u2013374. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"11_CR33","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":"11_CR34","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, K.: Edge: Editable dance generation from music. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 448\u2013458 (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"11_CR35","unstructured":"Wan, W., Dou, Z., Komura, T., Wang, W., Jayaraman, D., Liu, L.: Tlcontrol: trajectory and language control for human motion synthesis (2023)"},{"key":"11_CR36","unstructured":"Wan, W., et al.: Diffusionphase: motion diffusion in frequency domain. arXiv preprint arXiv:2312.04036 (2023)"},{"key":"11_CR37","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: Omnicontrol: control any joint at any time for human motion generation (2023)"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Yi, H., et al.: Generating holistic 3d human motion from speech. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 469\u2013480 (June 2023)","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., Kautz, J.: Physdiff: Physics-guided human motion diffusion model. arXiv preprint arXiv:2212.02500 (2022)","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Cun, X., Huang, S., Zhang, Y., Zhao, H., Lu, H., Shen, X.: T2m-gpt: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"11_CR41","unstructured":"Zhang, M., et al.: Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Remodiffuse: Retrieval-augmented motion diffusion model. arXiv preprint arXiv:2304.01116 (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"11_CR43","unstructured":"Zhang, M., Li, H., Cai, Z., Ren, J., Yang, L., Liu, Z.: Finemogen: Fine-grained spatio-temporal motion generation and editing. NeurIPS (2023)"},{"key":"11_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, X., Bhatnagar, B.L., Starke, S., Guzov, V., Pons-Moll, G.: Couch: towards controllable human-chair interactions. In: Computer Vision - ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part V, pp. 518\u2013535. Springer-Verlag, Berlin, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_30","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Motiongpt: finetuned llms are general-purpose motion generators (2023)","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, K., Zhang, Y., Wang, S., Beeler, T., Tang, S.: Synthesizing diverse human motions in 3d indoor scenes. In: International conference on computer vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, W., et al.: Emdm: efficient motion diffusion model for fast, high-quality motion generation. arXiv preprint arXiv:2312.02256 (2023)","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"11_CR48","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 (CVPR), pp. 5632\u20135641 (June 2023)","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, L., Liu, X., Liu, X., Qian, R., Liu, Z., Yu, L.: Taming diffusion models for audio-driven co-speech gesture generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10544\u201310553 (2023)","DOI":"10.1109\/CVPR52729.2023.01016"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73397-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:19:07Z","timestamp":1730575147000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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"}}]}}