{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:48:57Z","timestamp":1781797737847,"version":"3.54.5"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726606","type":"print"},{"value":"9783031726613","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-72661-3_20","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:53:01Z","timestamp":1732607581000},"page":"345-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Realistic Human Motion Generation with\u00a0Cross-Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8339-5229","authenticated-orcid":false,"given":"Zeping","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1445-3196","authenticated-orcid":false,"given":"Shaoli","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"20_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":"20_CR2","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":"20_CR3","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. arXiv preprint arXiv:2302.03665 (2023)","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"20_CR4","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":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chung, H., Sim, B., Ye, J.C.: Come-closer-diffuse-faster: accelerating conditional diffusion models for inverse problems through stochastic contraction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12413\u201312422 (2022)","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"20_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"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Ghosh, P., Song, J., Aksan, E., Hilliges, O.: Learning human motion models for long-term predictions. In: 2017 International Conference on 3D Vision (3DV), pp. 458\u2013466. IEEE (2017)","DOI":"10.1109\/3DV.2017.00059"},{"key":"20_CR8","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":"20_CR9","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_34","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Guo, C., et alL.: 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":"20_CR11","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":"20_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"20_CR13","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":"20_CR14","unstructured":"Lee, H.Y., et al.: Dancing to music. Adv. Neural Inform. Process. Syst. 32 (2019)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Kang, D., Pei, W., Zhe, X., Zhang, Y., He, Z., Bao, L.: Audio2gestures: generating diverse gestures from speech audio with conditional variational autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11293\u201311302 (2021)","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, S., Zhao, Y., Zhang, Y., Wang, Y., Tian, Q.: Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 214\u2013223 (2020)","DOI":"10.1109\/CVPR42600.2020.00029"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Finedance: A fine-grained choreography dataset for 3d full body dance generation. arXiv preprint arXiv:2212.03741 (2023)","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"20_CR18","unstructured":"Li, Z., Zhou, Y., Xiao, S., He, C., Huang, Z., Li, H.: Auto-conditioned recurrent networks for extended complex human motion synthesis. arXiv preprint arXiv:1707.05363 (2017)"},{"key":"20_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Videofusion: decomposed diffusion models for high-quality video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10209\u201310218 (2023)","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"20_CR22","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":"20_CR23","unstructured":"Nie, W., Guo, B., Huang, Y., Xiao, C., Vahdat, A., Anandkumar, A.: Diffusion models for adversarial purification. arXiv preprint arXiv:2205.07460 (2022)"},{"key":"20_CR24","unstructured":"Pavllo, D., Grangier, D., Auli, M.: Quaternet: A quaternion-based recurrent model for human motion. arXiv preprint arXiv:1805.06485 (2018)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3d human motion synthesis with transformer vae. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"20_CR26","doi-asserted-by":"publisher","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Temos: generating diverse human motions from textual descriptions. In: European Conference on Computer Vision. pp. 480\u2013497. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28","DOI":"10.1007\/978-3-031-20047-2_28"},{"issue":"4","key":"20_CR27","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.: The kit motion-language dataset. Big Data 4(4), 236\u2013252 (2016)","journal-title":"Big Data"},{"key":"20_CR28","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"20_CR29","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, vol. 1(2). arXiv preprint arXiv:2204.06125 (2022)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Z., Pan, Z., Zhou, X., Kang, L.: Diffusion motion: generate text-guided 3d human motion by diffusion model. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096441"},{"key":"20_CR31","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":"20_CR32","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR33","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418 (2023)"},{"key":"20_CR34","first-page":"12533","volume":"34","author":"A Sinha","year":"2021","unstructured":"Sinha, A., Song, J., Meng, C., Ermon, S.: D2c: diffusion-decoding models for few-shot conditional generation. Adv. Neural. Inf. Process. Syst. 34, 12533\u201312548 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR35","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":"20_CR36","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."},{"key":"20_CR37","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"20_CR38","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"20_CR39","doi-asserted-by":"publisher","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: exposing human motion generation to clip space. In: European Conference on Computer Vision, pp. 358\u2013374. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_21","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"20_CR40","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":"20_CR41","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":"20_CR42","first-page":"11287","volume":"34","author":"A Vahdat","year":"2021","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. Adv. Neural. Inf. Process. Syst. 34, 11287\u201311302 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR43","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural. Inf. Process. Syst. 30 (2017)"},{"key":"20_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30 (2017)"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Leng, Z., Li, F.W., Wu, S.C., Liang, X.: Fg-t2m: fine-grained text-driven human motion generation via diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22035\u201322044 (2023)","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Wei, D., et al.: Human joint kinematics diffusion-refinement for stochastic motion prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 6110\u20136118 (2023)","DOI":"10.1609\/aaai.v37i5.25754"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Xu, X., Wu, C., Rosenman, S., Lal, V., Che, W., Duan, N.: Bridgetower: building bridges between encoders in vision-language representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 10637\u201310647 (2023)","DOI":"10.1609\/aaai.v37i9.26263"},{"key":"20_CR48","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose: simple vision transformer baselines for human pose estimation. Adv. Neural. Inf. Process. Syst. 35, 38571\u201338584 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Yang, R., Srivastava, P., Mandt, S.: Diffusion probabilistic modeling for video generation. arXiv preprint arXiv:2203.09481 (2022)","DOI":"10.3390\/e25101469"},{"issue":"6","key":"20_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417838","volume":"39","author":"Y Yoon","year":"2020","unstructured":"Yoon, Y., et al.: Speech gesture generation from the trimodal context of text, audio, and speaker identity. ACM Trans. Graph. (TOG) 39(6), 1\u201316 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR51","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":"20_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: T2m-gpt: Generating human motion from textual descriptions with discrete representations. arXiv preprint arXiv:2301.06052 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"20_CR53","unstructured":"Zhang, M., et al.: Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"},{"key":"20_CR54","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":"20_CR55","doi-asserted-by":"crossref","unstructured":"Zhuang, H., Zhang, Y., Liu, S.: A pilot study of query-free adversarial attack against stable diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2384\u20132391 (2023)","DOI":"10.1109\/CVPRW59228.2023.00236"}],"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\/978-3-031-72661-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:21:36Z","timestamp":1732609296000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72661-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031726606","9783031726613"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72661-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 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"}}]}}