{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:05:34Z","timestamp":1768413934712,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556786","type":"print"},{"value":"9789819556793","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5679-3_4","type":"book-chapter","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:43Z","timestamp":1768329403000},"page":"47-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DreamDancer: Music-Driven Dance Video Intelligent Generation"],"prefix":"10.1007","author":[{"given":"Dongjin","family":"Huang","sequence":"first","affiliation":[]},{"given":"Jiyu","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Yufei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wenyun","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Yichuan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, L., Lin, K., et al.: DisCo: disentangled control for realistic human dance generation. In: IEEE Computer Vision and Pattern Recognition(CVPR), pp. 9326\u20139336 (2024)","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, J., Liew, J. H., et al.: MagicAnimate: temporally consistent human image animation using diffusion model. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1481\u20131490 (2024)","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"4_CR3","unstructured":"Chang, D., Shi, Y., Gao, Q., et al.: MagicPose: realistic human poses and facial expressions retargeting with identity-aware diffusion. In: Proceedings of the 41st International Conference on Machine Learning (ICML), pp. 1\u201323 (2024)"},{"key":"4_CR4","unstructured":"MooreThreads\/Moore-AnimateAnyone, GitHub repository (2024).https:\/\/github.com\/MooreThreads\/Moore-AnimateAnyone,"},{"key":"4_CR5","unstructured":"Hu, L., Gao, X., Zhang, P., et al.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:2311.17117 (2024)"},{"key":"4_CR6","unstructured":"Lee, H.Y., Yang, X., Liu, M.Y. et al.: Dancing to music. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), pp. 1\u201311 (2019)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Tian, L., Wang, Q., Zhang, B., Bo, L.: EMO: emote portrait alive generating expressive portrait videos with audio2video diffusion model under weak conditions. In: European Conference on Computer Vision (ECCV), pp. 244\u2013260 (2024)","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"4_CR8","unstructured":"Xu, M., Li, H., Su, Q., et al.: Hallo: hierarchical audio-driven visual synthesis for portrait image animation. arXiv preprint arXiv:2406.08801 (2024)"},{"key":"4_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/978-3-030-01249-6_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yang","year":"2018","unstructured":"Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D.: Pose guided human video generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 204\u2013219. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_13"},{"key":"4_CR10","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., et al.: First order motion model for image animation. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), p. 641 (2019)"},{"key":"4_CR11","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.cag.2020.09.009","volume":"94","author":"JP Ferreira","year":"2021","unstructured":"Ferreira, J.P., Coutinho, T.M., Gomes, T.L., et al.: Learning to dance: a graph convolutional adversarial network to generate realistic dance motions from audio. Comput. Graph. 94, 11\u201321 (2021)","journal-title":"Comput. Graph."},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Shlizerman, E., Dery, L., Schoen, H., Kemelmacher-Shlizerman, I.: Audio to body dynamics. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 7574\u20137583 (2018)","DOI":"10.1109\/CVPR.2018.00790"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Guo, X., Zhao, Y., Li, J.: DanceIt: music-inspired dancing video synthesis. In: IEEE Transactions on Image Processing, vol. 30, pp. 5559\u20135572 (2021)","DOI":"10.1109\/TIP.2021.3086082"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D. A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: IEEE International Conference on Computer Vision(ICCV), pp. 13381\u201313392 (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., Yu, W., Tianpei Gu, Lin, C., et al.: Bailando: 3D dance generation by actor-critic gpt with choreographic memory. In: IEEE Computer Vision and Pattern Recognition(CVPR), pp. 11040\u201311049 (2022)","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE International Conference on Computer Vision(ICCV), pp. 3813\u20133824 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, X., Ni, B., Ge, Y.: SimSwap: an efficient framework for high fidelity face swapping. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2003\u20132011 (2020)","DOI":"10.1145\/3394171.3413630"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: IEEE Computer Vision and Pattern Recognition(CVPR), pp. 4685\u20134694 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"4_CR19","unstructured":"Guo, J., Zhang, D., Liu, X., et al.: LivePortrait: efficient portrait animation with stitching and retargeting control. arXiv preprint arXiv:2407.03168 (2025)"},{"key":"4_CR20","unstructured":"Radford, A., Wook Kim, J., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Wang, T. C., Mallya, A., Liu, M. Y.: One-shot free-view neural talking-head synthesis for video conferencing. In: IEEE Computer Vision and Pattern Recognition (CVPR), pp. 10034\u201310044 (2021)","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"4_CR22","unstructured":"Feng, M., Liu, J., Yu, K., et al.: DreaMoving: a human video generation framework based on diffusion models. arXiv preprint arXiv:2312.05107 (2023)"},{"key":"4_CR23","unstructured":"Wang, X., Yuan, H., Zhang, S., et al.: VideoComposer: compositional video synthesis with motion controllability. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), pp. 1\u201318 (2023). Article No. 334"},{"key":"4_CR24","unstructured":"Tevet, G., Raab, S., Gordon, B., et al.: Human motion diffusion model. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cai, Z., Pan, L., et al.: MotionDiffuse: text-driven human motion generation with diffusion model. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 46, no. 6, pp. 4115\u20134128 (2024).","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, B., Liu, W., et al.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5679-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:47Z","timestamp":1768329407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5679-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556786","9789819556793"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5679-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}