{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T11:32:16Z","timestamp":1784287936484,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2024QY1400"],"award-info":[{"award-number":["2024QY1400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680980","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"10200-10209","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7291-6198","authenticated-orcid":false,"given":"Zixuan","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7430-5261","authenticated-orcid":false,"given":"Jiayi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9720-3220","authenticated-orcid":false,"given":"Xiaoyu","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2370-8841","authenticated-orcid":false,"given":"Shikun","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5972-3955","authenticated-orcid":false,"given":"Songtao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8449-278X","authenticated-orcid":false,"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University & Key Laboratory of Pervasive Computing, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"MikuMikuDance. https:\/\/sites.google.com\/view\/vpvp\/."},{"key":"e_1_3_2_1_2_1","volume-title":"GrooveNet: Realtime music-driven dance movement generation using artificial neural networks. networks 8, 17","author":"Alemi Omid","year":"2017","unstructured":"Omid Alemi, Jules Fran\u00e7oise, and Philippe Pasquier. 2017. GrooveNet: Realtime music-driven dance movement generation using artificial neural networks. networks 8, 17 (2017), 26."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/354384.354463"},{"key":"e_1_3_2_1_4_1","unstructured":"Alexander Berman and Valencia James. 2015. Kinetic imaginations: Exploring the possibilities of combining AI and dance. In Twenty-fourth international joint conference on artificial intelligence."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/EGUK.2002.1011270"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459932","article-title":"Choreomaster: choreography-oriented musicdriven dance synthesis","volume":"40","author":"Chen Kang","year":"2021","unstructured":"Kang Chen, Zhipeng Tan, Jin Lei, Song-Hai Zhang, Yuan-Chen Guo, Weidong Zhang, and Shi-Min Hu. 2021. Choreomaster: choreography-oriented musicdriven dance synthesis. ACM Transactions on Graphics (TOG) 40, 4 (2021), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_7_1","volume-title":"Monocular human pose estimation: A survey of deep learning-based methods. Computer vision and image understanding 192","author":"Chen Yucheng","year":"2020","unstructured":"Yucheng Chen, Yingli Tian, and Mingyi He. 2020. Monocular human pose estimation: A survey of deep learning-based methods. Computer vision and image understanding 192 (2020), 102897."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-37620-8_17"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46135-3_41"},{"key":"e_1_3_2_1_10_1","volume-title":"Computer Graphics Forum","author":"Christie Marc","year":"1982","unstructured":"Marc Christie and Jean-Marie Normand. 2005. A semantic space partitioning approach to virtual camera composition. In Computer Graphics Forum, Vol. 24. Amsterdam: North Holland, 1982-, 247--256."},{"key":"e_1_3_2_1_11_1","volume-title":"Computer Graphics Forum","author":"Christie Marc","unstructured":"Marc Christie, Patrick Olivier, and Jean-Marie Normand. 2008. Camera control in computer graphics. In Computer Graphics Forum, Vol. 27. Wiley Online Library, 2197--2218."},{"key":"e_1_3_2_1_12_1","volume-title":"Generative choreography using deep learning. arXiv preprint arXiv:1605.06921","author":"Crnkovic-Friis Luka","year":"2016","unstructured":"Luka Crnkovic-Friis and Louise Crnkovic-Friis. 2016. Generative choreography using deep learning. arXiv preprint arXiv:1605.06921 (2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"Alec Radford, and Ilya Sutskever.","author":"Dhariwal Prafulla","year":"2020","unstructured":"Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, and Ilya Sutskever. 2020. Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549486"},{"key":"e_1_3_2_1_15_1","volume-title":"Example-based automatic music-driven conventional dance motion synthesis","author":"Fan Rukun","year":"2011","unstructured":"Rukun Fan, Songhua Xu, and Weidong Geng. 2011. Example-based automatic music-driven conventional dance motion synthesis. IEEE transactions on visualization and computer graphics 18, 3 (2011), 501--515."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3181975"},{"key":"e_1_3_2_1_17_1","unstructured":"Deepak Gopinath and JungdamWon. 2020. Fairmotion-tools to load process and visualize motion capture data."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967592"},{"key":"e_1_3_2_1_19_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_21_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3067359"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00437"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793915"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations.","author":"Huang Ruozi","year":"2021","unstructured":"Ruozi Huang, Huang Hu, Wei Wu, Kei Sawada, Mi Zhang, and Daxin Jiang. 2021. Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480533","article-title":"Camera keyframing with style and control","volume":"40","author":"Jiang Hongda","year":"2021","unstructured":"Hongda Jiang, Marc Christie, Xi Wang, Libin Liu, Bin Wang, and Baoquan Chen. 2021. Camera keyframing with style and control. ACM Transactions on Graphics (TOG) 40, 6 (2021), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392427"},{"key":"e_1_3_2_1_28_1","volume-title":"Cinematographic Camera Diffusion Model. arXiv e-prints","author":"Jiang Hongda","year":"2024","unstructured":"Hongda Jiang, Xi Wang, Marc Christie, Libin Liu, and Baoquan Chen. 2024. Cinematographic Camera Diffusion Model. arXiv e-prints (2024), arXiv-2402."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Xuekun Jiang Anyi Rao Jingbo Wang Dahua Lin and Bo Dai. 2024. Cinematic Behavior Transfer via NeRF-based Differentiable Filming. (2024).","DOI":"10.1109\/CVPR52733.2024.00642"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612674"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618356"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"e_1_3_2_1_34_1","volume-title":"Dancing to music. Advances in neural information processing systems 32","author":"Lee Hsin-Ying","year":"2019","unstructured":"Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu, Ting-Chun Wang, Yu-Ding Lu, Ming-Hsuan Yang, and Jan Kautz. 2019. Dancing to music. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"Music similarity-based approach to generating dance motion sequence. Multimedia tools and applications 62","author":"Lee Minho","year":"2013","unstructured":"Minho Lee, Kyogu Lee, and Jaeheung Park. 2013. Music similarity-based approach to generating dance motion sequence. Multimedia tools and applications 62 (2013), 895--912."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85412-8_11"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524497"},{"key":"e_1_3_2_1_42_1","volume-title":"Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images. arXiv preprint arXiv:2407.09694","author":"Luan Tianyu","year":"2024","unstructured":"Tianyu Luan, Zhongpai Gao, Luyuan Xie, Abhishek Sharma, Hao Ding, Benjamin Planche, Meng Zheng, Ange Lou, Terrence Chen, Junsong Yuan, and Ziyan Wu. 2024. Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images. arXiv preprint arXiv:2407.09694 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16326"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bica.2015.09.009"},{"key":"e_1_3_2_1_45_1","volume-title":"Matt McVicar, Eric Battenberg, and Oriol Nieto.","author":"McFee Brian","year":"2015","unstructured":"Brian McFee, Colin Raffel, Dawen Liang, Daniel PW Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto. 2015. librosa: Audio and music signal analysis in python.. In SciPy. 18--24."},{"key":"e_1_3_2_1_46_1","volume-title":"A survey of computer vision-based human motion capture. Computer vision and image understanding 81, 3","author":"Moeslund Thomas B","year":"2001","unstructured":"Thomas B Moeslund and Erik Granum. 2001. A survey of computer vision-based human motion capture. Computer vision and image understanding 81, 3 (2001), 231--268."},{"key":"e_1_3_2_1_47_1","volume-title":"A survey of advances in vision-based human motion capture and analysis. Computer vision and image understanding 104, 2--3","author":"Moeslund Thomas B","year":"2006","unstructured":"Thomas B Moeslund, Adrian Hilton, and Volker Kr\u00fcger. 2006. A survey of advances in vision-based human motion capture and analysis. Computer vision and image understanding 104, 2--3 (2006), 90--126."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2181492"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588028.3603647"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619120"},{"key":"e_1_3_2_1_52_1","volume-title":"Duolando: Follower gpt with off-policy reinforcement learning for dance accompaniment. arXiv preprint arXiv:2403.18811","author":"Siyao Li","year":"2024","unstructured":"Li Siyao, Tianpei Gu, Zhitao Yang, Zhengyu Lin, Ziwei Liu, Henghui Ding, Lei Yang, and Chen Change Loy. 2024. Duolando: Follower gpt with off-policy reinforcement learning for dance accompaniment. arXiv preprint arXiv:2403.18811 (2024)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"e_1_3_2_1_54_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Siyao Li","year":"2023","unstructured":"Li Siyao, Weijiang Yu, Tianpei Gu, Chunze Lin, Quan Wang, Chen Qian, Chen Change Loy, and Ziwei Liu. 2023. Bailando: 3D Dance GPT With Choreographic Memory. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2981989"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480570"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00754"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548090"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475180"},{"key":"e_1_3_2_1_62_1","volume-title":"The secret of immersion: actor driven camera movement generation for auto-cinematography. arXiv preprint arXiv:2303.17041","author":"Wu Xinyi","year":"2023","unstructured":"Xinyi Wu, Haohong Wang, and Aggelos K Katsaggelos. 2023. The secret of immersion: actor driven camera movement generation for auto-cinematography. arXiv preprint arXiv:2303.17041 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE59613.2023.10315539"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612046"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414005"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR54900.2022.00055"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485664"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680980","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:35Z","timestamp":1750295855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":66,"alternative-id":["10.1145\/3664647.3680980","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680980","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}