{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:22:42Z","timestamp":1781587362785,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":69,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shenzhen Science and Technology Innovation Commission","award":["JSGG20220831105002004"],"award-info":[{"award-number":["JSGG20220831105002004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680849","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10833-10842","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["MagicFight: Personalized Martial Arts Combat Video Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2826-9231","authenticated-orcid":false,"given":"Jiancheng","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4820-0704","authenticated-orcid":false,"given":"Mingfu","family":"Yan","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0172-6887","authenticated-orcid":false,"given":"Songyan","family":"Chen","sequence":"additional","affiliation":[{"name":"China Telecom Cloud Technology Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8443-6877","authenticated-orcid":false,"given":"Yi","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0677-7358","authenticated-orcid":false,"given":"Shifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences & Shenzhen University of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. Video generation models as world simulators. https:\/\/openai.com\/research\/ video-generation-models-as-world-simulators."},{"key":"e_1_3_2_1_2_1","unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Karsten Kreis Miika Aittala Timo Aila Samuli Laine Bryan Catanzaro et al. 2022. ediffi: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5968--5976","author":"Bhunia Ankan Kumar","year":"2023","unstructured":"Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Jorma Laaksonen, Mubarak Shah, and Fahad Shahbaz Khan. 2023. Person image synthesis via denoising diffusion model. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5968--5976."},{"key":"e_1_3_2_1_4_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"e_1_3_2_1_7_1","volume-title":"Magicdance: Realistic human dance video generation with motions & facial expressions transfer. arXiv preprint arXiv:2311.12052","author":"Chang Di","year":"2023","unstructured":"Di Chang, Yichun Shi, Quankai Gao, Jessica Fu, Hongyi Xu, Guoxian Song, Qing Yan, Xiao Yang, and Mohammad Soleymani. 2023. Magicdance: Realistic human dance video generation with motions & facial expressions transfer. arXiv preprint arXiv:2311.12052 (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et al. 2023. VideoCrafter1: Open Diffusion Models for High-Quality Video Generation. arXiv preprint arXiv:2310.19512 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICML60161.2023.10424842"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_2_1_11_1","unstructured":"Mengyang Feng Jinlin Liu Kai Yu Yuan Yao Zheng Hui Xiefan Guo Xianhui Lin Haolan Xue Chen Shi Xiaowen Li et al. 2024. DreaMoving: A Human Video Generation Framework based on Diffusion Models. arXiv e-prints (2024) arXiv--2312."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"e_1_3_2_1_13_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Photorealistic video generation with diffusion models. arXiv preprint arXiv:2312.06662","author":"Gupta Agrim","year":"2023","unstructured":"Agrim Gupta, Lijun Yu, Kihyuk Sohn, Xiuye Gu, Meera Hahn, Li Fei-Fei, Irfan Essa, Lu Jiang, and Jos\u00e9 Lezama. 2023. Photorealistic video generation with diffusion models. arXiv preprint arXiv:2312.06662 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00220"},{"key":"e_1_3_2_1_16_1","unstructured":"Jonathan Ho William Chan Chitwan Saharia Jay Whang Ruiqi Gao Alexey Gritsenko Diederik P Kingma Ben Poole Mohammad Norouzi David J Fleet et al. 2022. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_18_1","volume-title":"Fleet","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan, Mohammad Norouzi, and David J. Fleet. 2022. Video Diffusion Models. In NeurIPS. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/39235c56aef13fb05a6adc95eb9d8d66-Abstract-Conference.html"},{"key":"e_1_3_2_1_19_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Hong Wenyi","year":"2023","unstructured":"Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, and Jie Tang. 2023. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=rB6TpjAuSRy"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"e_1_3_2_1_21_1","volume-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation. CVPR","author":"Hu Li","year":"2024","unstructured":"Li Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, and Liefeng Bo. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. CVPR (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"StructLDM: Structured Latent Diffusion for 3D Human Generation. arXiv preprint arXiv:2404.01241","author":"Hu Tao","year":"2024","unstructured":"Tao Hu, Fangzhou Hong, and Ziwei Liu. 2024. StructLDM: Structured Latent Diffusion for 3D Human Generation. arXiv preprint arXiv:2404.01241 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement. arXiv preprint arXiv:2309.14709","author":"Huang Jiancheng","year":"2023","unstructured":"Jiancheng Huang, Yifan Liu, and Shifeng Chen. 2023. Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement. arXiv preprint arXiv:2309.14709 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Entwined Inversion: Tune-Free Inversion For Real Image Faithful Reconstruction and Editing","author":"Huang Jiancheng","year":"2024","unstructured":"Jiancheng Huang, Yifan Liu, Jiaxi Lv, and Shifeng Chen. 2024. Entwined Inversion: Tune-Free Inversion For Real Image Faithful Reconstruction and Editing. In ICASSP. IEEE, 2920--2924."},{"key":"e_1_3_2_1_25_1","volume-title":"Computational Visual Media","author":"Huang Jiancheng","unstructured":"Jiancheng Huang, Yifan Liu, Linxiao Shi, Jin Qin, and Shifeng Chen. 2024 d. BK-Editer: Body-Keeping Text-Conditioned Real Image Editing. In Computational Visual Media. Springer, 235--251."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Jiancheng Huang Mingfu Yan Yifan Liu and Shifeng Chen. 2024 e. SBCR: Stochasticity Beats Content Restriction Problem in Training and Tuning Free Image Editing. In ICMR. 878--887.","DOI":"10.1145\/3652583.3658020"},{"key":"e_1_3_2_1_27_1","volume-title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:257038979","author":"Huang Lianghua","year":"2023","unstructured":"Lianghua Huang, Di Chen, Yu Liu, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023. Composer: Creative and Controllable Image Synthesis with Composable Conditions. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:257038979"},{"key":"e_1_3_2_1_28_1","volume-title":"WaveDM: Wavelet-Based Diffusion Models for Image Restoration","author":"Huang Yi","year":"2024","unstructured":"Yi Huang, Jiancheng Huang, Jianzhuang Liu, Yu Dong, Jiaxi Lv, and Shifeng Chen. 2024. WaveDM: Wavelet-Based Diffusion Models for Image Restoration. IEEE TMM (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Diffusion Model-Based Image Editing: A Survey. arXiv preprint arXiv:2402.17525","author":"Huang Yi","year":"2024","unstructured":"Yi Huang, Jiancheng Huang, Yifan Liu, Mingfu Yan, Jiaxi Lv, Jianzhuang Liu, Wei Xiong, He Zhang, Shifeng Chen, and Liangliang Cao. 2024. Diffusion Model-Based Image Editing: A Survey. arXiv preprint arXiv:2402.17525 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 22680--22690","author":"Karras Johanna","year":"2023","unstructured":"Johanna Karras, Aleksander Holynski, Ting-Chun Wang, and Ira Kemelmacher-Shlizerman. 2023. DreamPose: Fashion Video Synthesis with Stable Diffusion. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 22680--22690."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"e_1_3_2_1_33_1","volume-title":"Kingma and Max Welling","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681046"},{"key":"e_1_3_2_1_35_1","volume-title":"https:\/\/github.com\/MooreThreads\/Moore-AnimateAnyone","year":"2023","unstructured":"lixunsong. 2023. Moore-AnimateAnyone. (2023). https:\/\/github.com\/MooreThreads\/Moore-AnimateAnyone"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"e_1_3_2_1_38_1","volume-title":"Making a ?completely blind? image quality analyzer","author":"Mittal Anish","year":"2012","unstructured":"Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. 2012. Making a ?completely blind? image quality analyzer. IEEE Signal processing letters, Vol. 20, 3 (2012), 209--212."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"e_1_3_2_1_40_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:245335086","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:245335086"},{"key":"e_1_3_2_1_41_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In The Twelfth International Conference on Learning Representations.","author":"Podell Dustin","year":"2024","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2024. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 15932--15942","author":"Xiaodong Cun Chenyang QI","year":"2023","unstructured":"Chenyang QI, Xiaodong Cun, Yong Zhang, Chenyang Lei, Xintao Wang, Ying Shan, and Qifeng Chen. 2023. FateZero: Fusing Attentions for Zero-shot Text-based Video Editing. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 15932--15942."},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_44_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018224"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_47_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"e_1_3_2_1_49_1","volume-title":"First order motion model for image animation. Advances in neural information processing systems","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First order motion model for image animation. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_2_1_51_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Singer Uriel","year":"2023","unstructured":"Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman. 2023. Make-A-Video: Text-to-Video Generation without Text-Video Data. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=nJfylDvgzlq"},{"key":"e_1_3_2_1_52_1","volume-title":"Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly.","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)."},{"key":"e_1_3_2_1_53_1","volume-title":"Disco: Disentangled control for referring human dance generation in real world. CVPR","author":"Wang Tan","year":"2024","unstructured":"Tan Wang, Linjie Li, Kevin Lin, Chung-Ching Lin, Zhengyuan Yang, Hanwang Zhang, Zicheng Liu, and Lijuan Wang. 2024. Disco: Disentangled control for referring human dance generation in real world. CVPR (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"VideoComposer: Compositional Video Synthesis with Motion Controllability. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=h4r00NGkjR","author":"Wang Xiang","year":"2023","unstructured":"Xiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen, Jiuniu Wang, Yingya Zhang, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023. VideoComposer: Compositional Video Synthesis with Motion Controllability. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=h4r00NGkjR"},{"key":"e_1_3_2_1_55_1","volume-title":"LEO: Generative Latent Image Animator for Human Video Synthesis. arXiv preprint arXiv:2305.03989","author":"Wang Yaohui","year":"2023","unstructured":"Yaohui Wang, Xin Ma, Xinyuan Chen, Antitza Dantcheva, Bo Dai, and Yu Qiao. 2023. LEO: Generative Latent Image Animator for Human Video Synthesis. arXiv preprint arXiv:2305.03989 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_58_1","volume-title":"Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons. arXiv preprint arXiv:2401.13363","author":"Xu Zhe","year":"2024","unstructured":"Zhe Xu, Kun Wei, Xu Yang, and Cheng Deng. 2024. Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons. arXiv preprint arXiv:2401.13363 (2024)."},{"key":"e_1_3_2_1_59_1","volume-title":"Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, and Mike Zheng Shou.","author":"Xu Zhongcong","year":"2024","unstructured":"Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, and Mike Zheng Shou. 2024. Magicanimate: Temporally consistent human image animation using diffusion model. CVPR (2024)."},{"key":"e_1_3_2_1_60_1","volume-title":"Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157","author":"Yan Wilson","year":"2021","unstructured":"Wilson Yan, Yunzhi Zhang, Pieter Abbeel, and Aravind Srinivas. 2021. Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157 (2021)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"e_1_3_2_1_63_1","volume-title":"Dwnet: Dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139","author":"Zablotskaia Polina","year":"2019","unstructured":"Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, and Leonid Sigal. 2019. Dwnet: Dense warp-based network for pose-guided human video generation. arXiv preprint arXiv:1910.09139 (2019)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_67_1","volume-title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models. arXiv preprint arXiv:2311.04145","author":"Zhang Shiwei","year":"2023","unstructured":"Shiwei Zhang, Jiayu Wang, Yingya Zhang, Kang Zhao, Hangjie Yuan, Zhiwu Qin, Xiang Wang, Deli Zhao, and Jingren Zhou. 2023. I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models. arXiv preprint arXiv:2311.04145 (2023)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"e_1_3_2_1_69_1","volume-title":"Zuozhuo Dai, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, and Siyu Zhu.","author":"Zhu Shenhao","year":"2024","unstructured":"Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, and Siyu Zhu. 2024. Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance. arXiv preprint arXiv:2403.14781 (2024)."}],"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\/3664647.3680849","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":69,"alternative-id":["10.1145\/3664647.3680849","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680849","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"}}]}}