{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:20:11Z","timestamp":1765340411193,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"Joint Fund of Ministry of Education of China","award":["8091B022149, 8091B02072404"],"award-info":[{"award-number":["8091B022149, 8091B02072404"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132016, 62302372"],"award-info":[{"award-number":["62132016, 62302372"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2020JC-23"],"award-info":[{"award-number":["2020JC-23"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754938","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"5557-5566","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AStF: Motion Style Tranfer via Adaptive Statistics Fusor"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8849-1936","authenticated-orcid":false,"given":"Hanmo","family":"Chen","sequence":"first","affiliation":[{"name":"Hangzhou Institute of Technology, Xidian University, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5888-0504","authenticated-orcid":false,"given":"Chenghao","family":"Xu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2544-3057","authenticated-orcid":false,"given":"Jiexi","family":"Yan","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392469"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687559"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657457"},{"key":"e_1_3_2_2_4_1","unstructured":"Jinhe Bi Yujun Wang Haokun Chen Xun Xiao Artur Hecker Volker Tresp and Yunpu Ma. 2025a. LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering. In ACL."},{"key":"e_1_3_2_2_5_1","volume-title":"PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection. arXiv:2502.12119 [cs.CV] https:\/\/arxiv.org\/abs\/2502.12119","author":"Bi Jinhe","year":"2025","unstructured":"Jinhe Bi, Yifan Wang, Danqi Yan, Xun Xiao, Artur Hecker, Volker Tresp, and Yunpu Ma. 2025b. PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection. arXiv:2502.12119 [cs.CV] https:\/\/arxiv.org\/abs\/2502.12119"},{"key":"e_1_3_2_2_6_1","unstructured":"Jinhe Bi Danqi Yan Yifan Wang Wenke Huang Haokun Chen Guancheng Wan Mang Ye Xun Xiao Hinrich Schuetze Volker Tresp et al. 2025c. CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process. arXiv preprint arXiv:2505.13408 (2025)."},{"key":"e_1_3_2_2_7_1","volume-title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls. arXiv preprint arXiv:2407.21136","author":"Bian Yuxuan","year":"2024","unstructured":"Yuxuan Bian, Ailing Zeng, Xuan Ju, Xian Liu, Zhaoyang Zhang, Wei Liu, and Qiang Xu. 2024. MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls. arXiv preprint arXiv:2407.21136 (2024)."},{"key":"e_1_3_2_2_8_1","volume-title":"Haozheng Zhang, and Hubert PH Shum.","author":"Chang Ziyi","year":"2022","unstructured":"Ziyi Chang, Edmund JC Findlay, Haozheng Zhang, and Hubert PH Shum. 2022. Unifying human motion synthesis and style transfer with denoising diffusion probabilistic models. arXiv preprint arXiv:2212.08526 (2022)."},{"key":"e_1_3_2_2_9_1","volume-title":"International conference on machine learning. PmLR, 1597-1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PmLR, 1597-1607."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_2_11_1","volume-title":"Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516","author":"Dinh Laurent","year":"2014","unstructured":"Laurent Dinh, David Krueger, and Yoshua Bengio. 2014. Nice: Non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3237"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_2_14_1","volume-title":"Generative human motion stylization in latent space. arXiv preprint arXiv:2401.13505","author":"Guo Chuan","year":"2024","unstructured":"Chuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, and Li Cheng. 2024. Generative human motion stylization in latent space. arXiv preprint arXiv:2401.13505 (2024)."},{"key":"e_1_3_2_2_15_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2017.3271464"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"volume-title":"Computer Graphics Forum","author":"Hu Lei","key":"e_1_3_2_2_18_1","unstructured":"Lei Hu, Zihao Zhang, Yongjing Ye, Yiwen Xu, and Shihong Xia. 2024. Diffusion-based Human Motion Style Transfer with Semantic Guidance. In Computer Graphics Forum, Vol. 43. Wiley Online Library, e15169."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3516429"},{"key":"e_1_3_2_2_21_1","volume-title":"PackDiT: Joint Human Motion and Text Generation via Mutual Prompting. arXiv preprint arXiv:2501.16551","author":"Jiang Zhongyu","year":"2025","unstructured":"Zhongyu Jiang, Wenhao Chai, Zhuoran Zhou, Cheng-Yen Yang, Hsiang-Wei Huang, and Jenq-Neng Hwang. 2025. PackDiT: Joint Human Motion and Text Generation via Mutual Prompting. arXiv preprint arXiv:2501.16551 (2025)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00168"},{"key":"e_1_3_2_2_24_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_25_1","unstructured":"Diederik P Kingma Max Welling et al. 2013. Auto-encoding variational bayes."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01776"},{"key":"e_1_3_2_2_27_1","volume-title":"Unimotion: Unifying 3d human motion synthesis and understanding. arXiv preprint arXiv:2409.15904","author":"Li Chuqiao","year":"2024","unstructured":"Chuqiao Li, Julian Chibane, Yannan He, Naama Pearl, Andreas Geiger, and Gerard Pons-Moll. 2024. Unimotion: Unifying 3d human motion synthesis and understanding. arXiv preprint arXiv:2409.15904 (2024)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"e_1_3_2_2_29_1","volume-title":"Machine learning approaches for 3D motion synthesis and musculoskeletal dynamics estimation: a Survey","author":"Loi Iliana","year":"2023","unstructured":"Iliana Loi, Evangelia I Zacharaki, and Konstantinos Moustakas. 2023. Machine learning approaches for 3D motion synthesis and musculoskeletal dynamics estimation: a Survey. IEEE transactions on visualization and computer graphics, Vol. 30, 8 (2023), 5810-5829."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.248125"},{"key":"e_1_3_2_2_31_1","volume-title":"International conference on machine learning. PMLR, 3481-3490","author":"Mescheder Lars","year":"2018","unstructured":"Lars Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which training methods for GANs do actually converge?. In International conference on machine learning. PMLR, 3481-3490."},{"key":"e_1_3_2_2_32_1","volume-title":"Fran\u00e7ois Schnitzler, and Pierre Hellier.","author":"Mourot Lucas","year":"2022","unstructured":"Lucas Mourot, Ludovic Hoyet, Fran\u00e7ois Le Clerc, Fran\u00e7ois Schnitzler, and Pierre Hellier. 2022. A survey on deep learning for skeleton-based human animation. In Computer Graphics Forum, Vol. 41. Wiley Online Library, 122-157."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3480145"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00084"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658995"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6593-6603","author":"Tao Tianxin","key":"e_1_3_2_2_37_1","unstructured":"Tianxin Tao, Xiaohang Zhan, Zhongquan Chen, and Michiel van de Panne. 2022. Style-ERD: Responsive and coherent online motion style transfer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6593-6603."},{"key":"e_1_3_2_2_38_1","volume-title":"Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2016. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)."},{"key":"e_1_3_2_2_39_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01340"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766999"},{"key":"e_1_3_2_2_43_1","first-page":"5004","article-title":"LLM Knows Body Language, Too","author":"Xu Chenghao","year":"2024","unstructured":"Chenghao Xu, Guangtao Lyu, Jiexi Yan, Muli Yang, and Cheng Deng. 2024a. LLM Knows Body Language, Too: Translating Speech Voices into Human Gestures. In ACL. 5004-5013.","journal-title":"Translating Speech Voices into Human Gestures. In ACL."},{"key":"e_1_3_2_2_44_1","volume-title":"Keep and Extent: Unified Knowledge Embedding for Few-shot Image Generation","author":"Xu Chenghao","year":"2025","unstructured":"Chenghao Xu, Jiexi Yan, and Cheng Deng. 2025. Keep and Extent: Unified Knowledge Embedding for Few-shot Image Generation. IEEE TIP (2025)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485484"},{"key":"e_1_3_2_2_46_1","volume-title":"UniMuMo: Unified Text, Music and Motion Generation. arXiv preprint arXiv:2410.04534","author":"Yang Han","year":"2024","unstructured":"Han Yang, Kun Su, Yutong Zhang, Jiaben Chen, Kaizhi Qian, Gaowen Liu, and Chuang Gan. 2024. UniMuMo: Unified Text, Music and Motion Generation. arXiv preprint arXiv:2410.04534 (2024)."},{"key":"e_1_3_2_2_47_1","volume-title":"Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation. arXiv preprint arXiv:2412.11193","author":"Zeng Ling-An","year":"2024","unstructured":"Ling-An Zeng, Guohong Huang, Gaojie Wu, and Wei-Shi Zheng. 2024. Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation. arXiv preprint arXiv:2412.11193 (2024)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680864"},{"key":"e_1_3_2_2_49_1","volume-title":"HSI: A Holistic Style Injector for Arbitrary Style Transfer. arXiv preprint arXiv:2502.04369","author":"Zhang Shuhao","year":"2025","unstructured":"Shuhao Zhang, Hui Kang, Yang Liu, Fang Mei, and Hongjuan Li. 2025. HSI: A Holistic Style Injector for Arbitrary Style Transfer. arXiv preprint arXiv:2502.04369 (2025)."},{"key":"e_1_3_2_2_50_1","volume-title":"European Conference on Computer Vision. Springer, 405-421","author":"Zhong Lei","year":"2024","unstructured":"Lei Zhong, Yiming Xie, Varun Jampani, Deqing Sun, and Huaizu Jiang. 2024. Smoodi: Stylized motion diffusion model. In European Conference on Computer Vision. Springer, 405-421."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02112"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330935"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:16:39Z","timestamp":1765340199000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754938"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3754938","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754938","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}