{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:09:20Z","timestamp":1778080160529,"version":"3.51.4"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726293","type":"print"},{"value":"9783031726309","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-72630-9_2","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:17:52Z","timestamp":1733289472000},"page":"18-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["M2D2M: Multi-Motion Generation from\u00a0Text with\u00a0Discrete Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6965-6938","authenticated-orcid":false,"given":"Seunggeun","family":"Chi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5454-3404","authenticated-orcid":false,"given":"Hyung-gun","family":"Chi","sequence":"additional","affiliation":[]},{"given":"Hengbo","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Nakul","family":"Agarwal","sequence":"additional","affiliation":[]},{"given":"Faizan","family":"Siddiqui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8639-5135","authenticated-orcid":false,"given":"Karthik","family":"Ramani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1433-551X","authenticated-orcid":false,"given":"Kwonjoon","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2action: generative adversarial synthesis from language to action. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5915\u20135920. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"2_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"},{"issue":"4","key":"2_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":"2_CR4","doi-asserted-by":"crossref","unstructured":"Aliakbarian, S., Saleh, F.S., Salzmann, M., Petersson, L., Gould, S.: A stochastic conditioning scheme for diverse human motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5223\u20135232 (2020)","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Ao, T., Zhang, Z., Liu, L.: Gesturediffuclip: Gesture diffusion model with clip latents. arXiv preprint arXiv:2303.14613 (2023)","DOI":"10.1145\/3592097"},{"key":"2_CR6","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":"2_CR7","first-page":"17981","volume":"34","author":"J Austin","year":"2021","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., Van Den Berg, R.: Structured denoising diffusion models in discrete state-spaces. Adv. Neural. Inf. Process. Syst. 34, 17981\u201317993 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Azadi, S., Shah, A., Hayes, T., Parikh, D., Gupta, S.: Make-an-animation: Large-scale text-conditional 3d human motion generation. arXiv preprint arXiv:2305.09662 (2023)","DOI":"10.1109\/ICCV51070.2023.01381"},{"key":"2_CR9","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U., Rewkowski, N., Banerjee, A., Guhan, P., Bera, A., Manocha, D.: Text2gestures: A transformer-based network for generating emotive body gestures for virtual agents. In: 2021 IEEE Virtual Reality and 3D User Interfaces (VR), pp. 1\u201310. IEEE (2021)","DOI":"10.1109\/VR50410.2021.00037"},{"key":"2_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":"2_CR12","unstructured":"CMU Graphics Lab: Motion capture database. http:\/\/mocap.cs.cmu.edu (2016)"},{"key":"2_CR13","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":"2_CR14","unstructured":"Duan, Y., et al.: Single-shot motion completion with transformer. arXiv preprint arXiv:2103.00776 (2021)"},{"issue":"7","key":"2_CR15","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1523\/JNEUROSCI.05-07-01688.1985","volume":"5","author":"T Flash","year":"1985","unstructured":"Flash, T., Hogan, N.: The coordination of arm movements: an experimentally confirmed mathematical model. J. Neurosci. 5(7), 1688\u20131703 (1985)","journal-title":"J. Neurosci."},{"key":"2_CR16","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":"2_CR17","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Gulde, P., Hermsd\u00f6rfer, J.: Smoothness metrics in complex movement tasks. Front. Neurol. 9, 615 (09 2018). https:\/\/doi.org\/10.3389\/fneur.2018.00615","DOI":"10.3389\/fneur.2018.00615"},{"key":"2_CR19","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":"2_CR20","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1007\/978-3-031-19833-5_34","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV","author":"C Guo","year":"2022","unstructured":"Guo, C., Zuo, X., Wang, S., Cheng, L.: TM2T: stochastic and\u00a0tokenized modeling for\u00a0the\u00a0reciprocal generation of\u00a03d human motions and\u00a0texts. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV, pp. 580\u2013597. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_34"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Harvey, F.G., Pal, C.: Recurrent transition networks for character locomotion. In: SIGGRAPH Asia 2018 Technical Briefs, pp.\u00a01\u20134 (2018)","DOI":"10.1145\/3283254.3283277"},{"issue":"4","key":"2_CR22","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1145\/3386569.3392480","volume":"39","author":"FG Harvey","year":"2020","unstructured":"Harvey, F.G., Yurick, M., Nowrouzezahrai, D., Pal, C.: Robust motion in-betweening. ACM Trans. Graph. (TOG) 39(4), 60\u20131 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR23","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":"2_CR24","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"2_CR25","unstructured":"Hoogeboom, E., Nielsen, D., Jaini, P., Forr\u00e9, P., Welling, M.: Argmax flows and multinomial diffusion: Learning categorical distributions (2021). https:\/\/arxiv.org\/abs\/2102.05379"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., et al.: Adaptutar: an adaptive tutoring system for machine tasks in augmented reality. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1\u201315 (2021)","DOI":"10.1145\/3411764.3445283"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Ipsita, A., Li, H., Duan, R., Cao, Y., Chidambaram, S., Liu, M., Ramani, K.: Vrfromx: from scanned reality to interactive virtual experience with human-in-the-loop. In: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, pp.\u00a01\u20137 (2021)","DOI":"10.1145\/3411763.3451747"},{"key":"2_CR28","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: Motiongpt: Human motion as a foreign language. arXiv preprint arXiv:2306.14795 (2023)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Kaufmann, M., Aksan, E., Song, J., Pece, F., Ziegler, R., Hilliges, O.: Convolutional autoencoders for human motion infilling. In: 2020 International Conference on 3D Vision (3DV), pp. 918\u2013927. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00102"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Komura, T., Habibie, I., Holden, D., Schwarz, J., Yearsley, J.: A recurrent variational autoencoder for human motion synthesis. In: The 28th British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.119"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Kong, H., Gong, K., Lian, D., Mi, M.B., Wang, X.: Priority-centric human motion generation in discrete latent space. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14806\u201314816 (2023)","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Kucherenko, T., Hasegawa, D., Henter, G.E., Kaneko, N., Kjellstr\u00f6m, H.: Analyzing input and output representations for speech-driven gesture generation. In: Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents, pp. 97\u2013104 (2019)","DOI":"10.1145\/3308532.3329472"},{"key":"2_CR33","unstructured":"Lee, H.Y., et al.: Dancing to music. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"2_CR34","unstructured":"Lee, K., Chang, H., Jiang, L., Zhang, H., Tu, Z., Liu, C.: ViTGAN: Training GANs with vision transformers. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=dwg5rXg1WS_"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Lee, T., Moon, G., Lee, K.M.: Multiact: Long-term 3d human motion generation from multiple action labels. In: AAAI Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"2_CR36","unstructured":"Lin, A.S., Wu, L., Corona, R., Tai, K., Huang, Q., Mooney, R.J.: Generating animated videos of human activities from natural language descriptions. Learning 2018(1) (2018)"},{"key":"2_CR37","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":"2_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-030-58568-6_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Mao","year":"2020","unstructured":"Mao, W., Liu, M., Salzmann, M.: History repeats itself: human motion prediction via motion attention. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 474\u2013489. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_28"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M., Li, H.: Learning trajectory dependencies for human motion prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9489\u20139497 (2019)","DOI":"10.1109\/ICCV.2019.00958"},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"Mobini, A., Behzadipour, S., Foumani, M.: Test-retest reliability of kinect\u2019s measurements for the evaluation of upper body recovery of stroke patients. Biomed. Eng. Online 14, 75 (08 2015).https:\/\/doi.org\/10.1186\/s12938-015-0070-0","DOI":"10.1186\/s12938-015-0070-0"},{"key":"2_CR41","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1007\/978-3-031-20047-2_28","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII","author":"M Petrovich","year":"2022","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS: generating diverse human motions from\u00a0textual descriptions. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 480\u2013497. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Plappert, M., Mandery, C., Asfour, T.: The kit motion-language dataset. Big Data 4(4), 236\u2013252 (2016)","DOI":"10.1089\/big.2016.0028"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: Babel: bodies, action and behavior with english labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 722\u2013731 (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"2_CR44","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"2_CR45","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR47","doi-asserted-by":"publisher","unstructured":"Roren, A., et al.: Assessing smoothness of arm movements with jerk: a comparison of laterality, contraction mode and plane of elevation. a pilot study. Front. Bioeng. Biotechnol. 9 (01 2022).https:\/\/doi.org\/10.3389\/fbioe.2021.782740","DOI":"10.3389\/fbioe.2021.782740"},{"key":"2_CR48","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). https:\/\/openreview.net\/forum?id=dTpbEdN9kr"},{"key":"2_CR49","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"2_CR50","first-page":"12438","volume":"33","author":"Y Song","year":"2020","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. Adv. Neural. Inf. Process. Syst. 33, 12438\u201312448 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"2_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530090","volume":"41","author":"X Tang","year":"2022","unstructured":"Tang, X., et al.: Real-time controllable motion transition for characters. ACM Trans. Graph. (TOG) 41(4), 1\u201310 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR52","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-031-20047-2_21","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII","author":"G Tevet","year":"2022","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: MotionCLIP: exposing human motion generation to\u00a0CLIP space. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXII, pp. 358\u2013374. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_21"},{"key":"2_CR53","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":"2_CR54","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: Mocogan: decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"2_CR55","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR56","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Yan, S., Li, Z., Xiong, Y., Yan, H., Lin, D.: Convolutional sequence generation for skeleton-based action synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4394\u20134402 (2019)","DOI":"10.1109\/ICCV.2019.00449"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Yan, X., et al.: Mt-vae: Learning motion transformations to generate multimodal human dynamics. In: Proceedings of the European conference on computer vision (ECCV), pp. 265\u2013281 (2018)","DOI":"10.1007\/978-3-030-01228-1_17"},{"key":"2_CR59","doi-asserted-by":"publisher","unstructured":"Yi, X., Zhou, Y., Xu, F.: Transpose: real-time 3d human translation and pose estimation with six inertial sensors. ACM Trans. Graph. 40(4) (jul 2021). https:\/\/doi.org\/10.1145\/3450626.3459786","DOI":"10.1145\/3450626.3459786"},{"issue":"4","key":"2_CR60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459786","volume":"40","author":"X Yi","year":"2021","unstructured":"Yi, X., Zhou, Y., Xu, F.: Transpose: real-time 3d human translation and pose estimation with six inertial sensors. ACM Trans. Graph. (TOG) 40(4), 1\u201313 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"5","key":"2_CR61","doi-asserted-by":"publisher","first-page":"2245","DOI":"10.1109\/TVCG.2022.3150507","volume":"28","author":"T Yin","year":"2022","unstructured":"Yin, T., Hoyet, L., Christie, M., Cani, M.P., Pettr\u00e9, J.: The one-man-crowd: single user generation of crowd motions using virtual reality. IEEE Trans. Visual Comput. Graphics 28(5), 2245\u20132255 (2022)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: 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":"2_CR63","unstructured":"Zhang, M., et al.: Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"},{"key":"2_CR64","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":"2_CR65","unstructured":"Zhang, M., Li, H., Cai, Z., Ren, J., Yang, L., Liu, Z.: Finemogen: fine-grained spatio-temporal motion generation and editing. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"2_CR66","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"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72630-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T06:37:55Z","timestamp":1768199875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72630-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031726293","9783031726309"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72630-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 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"}}]}}