{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:25:24Z","timestamp":1784399124190,"version":"3.55.0"},"publisher-location":"Cham","reference-count":84,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730351","type":"print"},{"value":"9783031730368","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73036-8_2","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:06:52Z","timestamp":1732093612000},"page":"18-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["CoMusion: Towards Consistent Stochastic Human Motion Prediction via\u00a0Motion Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7113-081X","authenticated-orcid":false,"given":"Jiarui","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4657-307X","authenticated-orcid":false,"given":"Girish","family":"Chowdhary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Cao, P., Hilliges, O.: A spatio-temporal transformer for 3D human motion prediction. In: 3DV, pp. 565\u2013574 (2021)","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alexanderson, S., Nagy, R., Beskow, J., Henter, G.E.: Listen, denoise, action! Audio-driven motion synthesis with diffusion models. ACM Trans. Graph. 42(4), 44:1\u201344:20 (2023)","DOI":"10.1145\/3592458"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Aliakbarian, M.S., Saleh, F.S., Salzmann, M., Petersson, L., Gould, S.: A stochastic conditioning scheme for diverse human motion prediction. In: CVPR, pp. 5222\u20135231. Computer Vision Foundation \/ IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., Palmero, C.: BeLFusion: latent diffusion for behavior-driven human motion prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Kender, J., Liu, Z.: HP-GAN: probabilistic 3D human motion prediction via GAN. In: CVPR Workshops, pp. 1418\u20131427 (2018)","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Bhattacharyya, A., Schiele, B., Fritz, M.: Accurate and diverse sampling of sequences based on a \u201cbest of many\u201d sample objective. In: CVPR, pp. 8485\u20138493 (2018)","DOI":"10.1109\/CVPR.2018.00885"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Milbich, T., Dorkenwald, M., Ommer, B.: Behavior-driven synthesis of human dynamics. In: CVPR, pp. 12236\u201312246. Computer Vision Foundation \/ IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01206"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Bouazizi, A., Holzbock, A., Kressel, U., Dietmayer, K., Belagiannis, V.: MotionMixer: MLP-based 3D human body pose forecasting. In: IJCAI, pp. 791\u2013798 (2022)","DOI":"10.24963\/ijcai.2022\/111"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"B\u00fctepage, J., Black, M.J., Kragic, D., Kjellstr\u00f6m, H.: Deep representation learning for human motion prediction and classification. In: CVPR, pp. 1591\u20131599 (2017)","DOI":"10.1109\/CVPR.2017.173"},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/978-3-030-58571-6_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Cai","year":"2020","unstructured":"Cai, Y., et al.: Learning progressive joint propagation for human motion prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 226\u2013242. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_14"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L.H., Zhang, J., Li, Y., Pang, Y., Xia, X., Liu, T.: HumanMAC: masked motion completion for human motion prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"2_CR12","unstructured":"Croitoru, F., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. CoRR abs\/2209.04747 (2022)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., Theobalt, C.: MoFusion: a framework for denoising-diffusion-based motion synthesis. In: CVPR, pp. 9760\u20139770. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Dang, L., Nie, Y., Long, C., Zhang, Q., Li, G.: MSR-GCN: multi-scale residual graph convolution networks for human motion prediction. In: ICCV, pp. 11447\u201311456 (2021)","DOI":"10.1109\/ICCV48922.2021.01127"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Dang, L., Nie, Y., Long, C., Zhang, Q., Li, G.: Diverse human motion prediction via Gumbel-Softmax sampling from an auxiliary space. In: MM, pp. 5162\u20135171 (2022)","DOI":"10.1145\/3503161.3547956"},{"key":"2_CR16","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat GANs on image synthesis. In: NeurIPS, pp. 8780\u20138794 (2021)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: ICCV, pp. 4346\u20134354 (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"2_CR18","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS, pp. 2672\u20132680 (2014)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Gui, L., Zhang, K., Wang, Y., Liang, X., Moura, J.M.F., Veloso, M.: Teaching robots to predict human motion. In: IROS, pp. 562\u2013567 (2018)","DOI":"10.1109\/IROS.2018.8594452"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Guo, W., Bie, X., Alameda-Pineda, X., Moreno-Noguer, F.: Multi-person extreme motion prediction. In: CVPR, pp. 13043\u201313054 (2022)","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Guo, W., et al.: Back to MLP: a simple baseline for human motion prediction. In: WACV, pp. 4798\u20134808 (2023)","DOI":"10.1109\/WACV56688.2023.00479"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social GAN: socially acceptable trajectories with generative adversarial networks. In: CVPR, pp. 2255\u20132264. Computer Vision Foundation \/ IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00240"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Gurumurthy, S., Sarvadevabhatla, R.K., Babu, R.V.: DeLiGAN: generative adversarial networks for diverse and limited data. In: CVPR, pp. 4941\u20134949 (2017)","DOI":"10.1109\/CVPR.2017.525"},{"issue":"4","key":"2_CR24","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.J.: Robust motion in-betweening. ACM Trans. Graph. 39(4), 60 (2020)","journal-title":"ACM Trans. Graph."},{"key":"2_CR25","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Huang, R., et al.: FastDiff: a fast conditional diffusion model for high-quality speech synthesis. In: IJCAI, pp. 4157\u20134163 (2022)","DOI":"10.24963\/ijcai.2022\/577"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. TPAMI 36(7), 1325\u20131339 (2014)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: CVPR, pp. 5308\u20135317 (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"2_CR29","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: human motion as a foreign language. CoRR abs\/2306.14795 (2023)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Ju, X., Zeng, A., Jianan, W., Qiang, X., Lei, Z.: Human-art: a versatile human-centric dataset bridging natural and artificial scenes. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Kindratenko, V., et al.: HAL: computer system for scalable deep learning. In: Practice and Experience in Advanced Research Computing, PEARC 2020, pp. 41\u201348. Association for Computing Machinery, New York, NY, USA (2020)","DOI":"10.1145\/3311790.3396649"},{"key":"2_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"2_CR33","unstructured":"Kingma, D.P., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. CoRR abs\/2107.00630 (2021)"},{"key":"2_CR34","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: VIBE: video inference for human body pose and shape estimation. In: CVPR, pp. 5252\u20135262. Computer Vision Foundation \/ IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"2_CR36","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: DiffWave: a versatile diffusion model for audio synthesis. In: ICLR (2021)"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Gor, M., Babu, R.V.: BiHMP-GAN: bidirectional 3D human motion prediction GAN. In: AAAI, pp. 8553\u20138560 (2019)","DOI":"10.1609\/aaai.v33i01.33018553"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Lee, N., Choi, W., Vernaza, P., Choy, C.B., Torr, P.H.S., Chandraker, M.: DESIRE: distant future prediction in dynamic scenes with interacting agents. In: CVPR, pp. 2165\u20132174. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.233"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, Z., Lee, W.S., Lee, G.H.: Convolutional sequence to sequence model for human dynamics. In: CVPR, pp. 5226\u20135234 (2018)","DOI":"10.1109\/CVPR.2018.00548"},{"key":"2_CR40","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-031-20068-7_2","volume-title":"ECCV 2022","author":"M Li","year":"2022","unstructured":"Li, M., Chen, S., Zhang, Z., Xie, L., Tian, Q., Zhang, Y.: Skeleton-parted graph scattering networks for 3D human motion prediction. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 18\u201336. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_2"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Intention aware robot crowd navigation with attention-based interaction graph. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160660"},{"key":"2_CR42","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. Graph. 34(6), 248:1\u2013248:16 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"2_CR43","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ODE solver for diffusion probabilistic model sampling in around 10 steps. In: NeurIPS (2022)"},{"key":"2_CR44","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. CoRR abs\/2211.01095 (2022)"},{"key":"2_CR45","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-031-20068-7_24","volume-title":"ECCV 2022","author":"T Lucas","year":"2022","unstructured":"Lucas, T., Baradel, F., Weinzaepfel, P., Rogez, G.: PoseGPT: quantization-based 3D human motion generation and forecasting. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 417\u2013435. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_24"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Ma, H., Li, J., Hosseini, R., Tomizuka, M., Choi, C.: Multi-objective diverse human motion prediction with knowledge distillation. In: CVPR, pp. 8151\u20138161 (2022)","DOI":"10.1109\/CVPR52688.2022.00799"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Ma, T., Nie, Y., Long, C., Zhang, Q., Li, G.: Progressively generating better initial guesses towards next stages for high-quality human motion prediction. In: CVPR, pp. 6427\u20136436 (2022)","DOI":"10.1109\/CVPR52688.2022.00633"},{"key":"2_CR48","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: ICCV, pp. 5441\u20135450 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"2_CR49","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_CR50","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M.: Generating smooth pose sequences for diverse human motion prediction. In: ICCV, pp. 13289\u201313298 (2021)","DOI":"10.1109\/ICCV48922.2021.01306"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M., Li, H.: Learning trajectory dependencies for human motion prediction. In: ICCV, pp. 9488\u20139496 (2019)","DOI":"10.1109\/ICCV.2019.00958"},{"issue":"9","key":"2_CR52","doi-asserted-by":"publisher","first-page":"2513","DOI":"10.1007\/s11263-021-01483-7","volume":"129","author":"W Mao","year":"2021","unstructured":"Mao, W., Liu, M., Salzmann, M., Li, H.: Multi-level motion attention for human motion prediction. IJCV 129(9), 2513\u20132535 (2021)","journal-title":"IJCV"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: CVPR, pp. 4674\u20134683 (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"2_CR54","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171 (2021)"},{"issue":"1","key":"2_CR55","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/TIV.2016.2578706","volume":"1","author":"B Paden","year":"2016","unstructured":"Paden, B., C\u00e1p, M., Yong, S.Z., Yershov, D.S., Frazzoli, E.: A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Trans. Intell. Veh. 1(1), 33\u201355 (2016)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"2_CR56","unstructured":"Pearce, T., et al.: Imitating human behaviour with diffusion models. In: ICLR (2023)"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10674\u201310685 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Salzmann, T., Pavone, M., Ryll, M.: Motron: multimodal probabilistic human motion forecasting. In: CVPR, pp. 6447\u20136456 (2022)","DOI":"10.1109\/CVPR52688.2022.00635"},{"issue":"1\u20132","key":"2_CR59","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal, L., Balan, A.O., Black, M.J.: HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. IJCV 87(1\u20132), 4\u201327 (2010)","journal-title":"IJCV"},{"key":"2_CR60","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML, vol.\u00a037, pp. 2256\u20132265. JMLR.org (2015)"},{"key":"2_CR61","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"2_CR62","unstructured":"Sun, J., Chowdhary, G.: Towards accurate human motion prediction via iterative refinement. CoRR abs\/2305.04443 (2023)"},{"issue":"9","key":"2_CR63","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.3390\/s20092653","volume":"20","author":"W Taylor","year":"2020","unstructured":"Taylor, W., Shah, S.A., Dashtipour, K., Zahid, A., Abbasi, Q.H., Imran, M.A.: An intelligent non-invasive real-time human activity recognition system for next-generation healthcare. Sensors 20(9), 2653 (2020)","journal-title":"Sensors"},{"key":"2_CR64","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: ICLR (2023)"},{"issue":"5","key":"2_CR65","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1167\/2.5.2","volume":"2","author":"NF Troje","year":"2002","unstructured":"Troje, N.F.: Decomposing biological motion: a framework for analysis and synthesis of human gait patterns. J. Vis. 2(5), 2\u20132 (2002)","journal-title":"J. Vis."},{"key":"2_CR66","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, C.K.: EDGE: editable dance generation from music. In: CVPR, pp. 448\u2013458. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"2_CR67","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"2_CR68","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: ICCV, pp. 3352\u20133361 (2017)","DOI":"10.1109\/ICCV.2017.361"},{"key":"2_CR69","unstructured":"Wang, Z., Zheng, H., He, P., Chen, W., Zhou, M.: Diffusion-GAN: training GANs with diffusion. In: ICLR (2023)"},{"key":"2_CR70","doi-asserted-by":"crossref","unstructured":"Wei, D., et al.: Human joint kinematics diffusion-refinement for stochastic motion prediction. In: AAAI, pp. 6110\u20136118 (2023)","DOI":"10.1609\/aaai.v37i5.25754"},{"issue":"8","key":"2_CR71","doi-asserted-by":"publisher","first-page":"2530","DOI":"10.1111\/j.1467-8659.2010.01822.x","volume":"29","author":"H van Welbergen","year":"2010","unstructured":"van Welbergen, H., van Basten, B.J.H., Egges, A., Ruttkay, Z., Overmars, M.H.: Real time animation of virtual humans: a trade-off between naturalness and control. Comput. Graph. Forum 29(8), 2530\u20132554 (2010)","journal-title":"Comput. Graph. Forum"},{"key":"2_CR72","doi-asserted-by":"crossref","unstructured":"Whang, J., Delbracio, M., Talebi, H., Saharia, C., Dimakis, A.G., Milanfar, P.: Deblurring via stochastic refinement. In: CVPR, pp. 16272\u201316282. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01581"},{"key":"2_CR73","unstructured":"Xiao, Z., Kreis, K., Vahdat, A.: Tackling the generative learning trilemma with denoising diffusion GANs. In: ICLR (2022)"},{"key":"2_CR74","doi-asserted-by":"crossref","unstructured":"Xu, S., Li, Z., Wang, Y.X., Gui, L.Y.: InterDiff: generating 3D human-object interactions with physics-informed diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"2_CR75","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-031-20047-2_15","volume-title":"ECCV 2022","author":"S Xu","year":"2022","unstructured":"Xu, S., Wang, Y.X., Gui, L.Y.: Diverse human motion prediction guided by multi-level spatial-temporal anchors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 251\u2013269. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_15"},{"key":"2_CR76","unstructured":"Xu, S., Wang, Y.X., Gui, L.Y.: Stochastic multi-person 3D motion forecasting. In: ICLR (2023)"},{"key":"2_CR77","doi-asserted-by":"crossref","unstructured":"Yang, J., Zeng, A., Li, F., Liu, S., Zhang, R., Zhang, L.: Neural interactive keypoint detection. In: ICCV, pp. 15122\u201315132 (2023)","DOI":"10.1109\/ICCV51070.2023.01388"},{"key":"2_CR78","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58545-7_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Kitani, K.: DLow: diversifying latent flows for diverse human motion prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 346\u2013364. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_20"},{"key":"2_CR79","unstructured":"Yuan, Y., Kitani, K.M.: Diverse trajectory forecasting with determinantal point processes. In: ICLR (2020)"},{"key":"2_CR80","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., Kautz, J.: PhysDiff: physics-guided human motion diffusion model. In: ICCV, pp. 16010\u201316021 (2023)","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"2_CR81","unstructured":"Zhang, M., et al.: MotionDiffuse: text-driven human motion generation with diffusion model. CoRR abs\/2208.15001 (2022)"},{"key":"2_CR82","unstructured":"Zhang, Q., Chen, Y.: Fast sampling of diffusion models with exponential integrator. In: ICLR (2023)"},{"key":"2_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Black, M.J., Tang, S.: We are more than our joints: predicting how 3D bodies move. In: CVPR, pp. 3372\u20133382. Computer Vision Foundation \/ IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"2_CR84","unstructured":"Zhao, Z., Bai, J., Chen, D., Wang, D., Pan, Y.: Taming diffusion models for music-driven conducting motion generation. CoRR abs\/2306.10065 (2023)"}],"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\/978-3-031-73036-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:50:15Z","timestamp":1732096215000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73036-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730351","9783031730368"],"references-count":84,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73036-8_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 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"}}]}}