{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T06:52:17Z","timestamp":1792133537239,"version":"4.4.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172020"],"award-info":[{"award-number":["62172020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611774","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"7175-7183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5039-8916","authenticated-orcid":false,"given":"Jiahang","family":"Zhang","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3229-4096","authenticated-orcid":false,"given":"Lilang","family":"Lin","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9576","authenticated-orcid":false,"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Directional Self-Supervised Learning for Heavy Image Augmentations","author":"Bai Yalong","unstructured":"Yalong Bai, Yifan Yang, Wei Zhang, and Tao Mei. 2022. Directional Self-Supervised Learning for Heavy Image Augmentations. In IEEE CVPR."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3006768"},{"key":"e_1_3_2_1_3_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020b. A simple framework for contrastive learning of visual representations. In ICML."},{"key":"e_1_3_2_1_4_1","volume-title":"Improved baselines with momentum contrastive learning. arxiv","author":"Chen Xinlei","year":"2003","unstructured":"Xinlei Chen, Haoqi Fan, Ross Girshick, and Kaiming He. 2020a. Improved baselines with momentum contrastive learning. arxiv: 2003.04297"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Yuxiao Chen Long Zhao Jianbo Yuan Yu Tian Zhaoyang Xia Shijie Geng Ligong Han and Dimitris N Metaxas. 2022. Hierarchically Self-supervised Transformer for Human Skeleton Representation Learning. In ECCV.","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"e_1_3_2_1_6_1","volume-title":"Skeleton-based action recognition with shift graph convolutional network","author":"Cheng Ke","unstructured":"Ke Cheng, Yifan Zhang, Xiangyu He, Weihan Chen, Jian Cheng, and Hanqing Lu. 2020. Skeleton-based action recognition with shift graph convolutional network. In IEEE CVPR."},{"key":"e_1_3_2_1_7_1","volume-title":"Hierarchical transformer: Unsupervised representation learning for skeleton-based human action recognition","author":"Cheng Yi-Bin","unstructured":"Yi-Bin Cheng, Xipeng Chen, Junhong Chen, Pengxu Wei, Dongyu Zhang, and Liang Lin. 2021. Hierarchical transformer: Unsupervised representation learning for skeleton-based human action recognition. In IEEE ICME."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Jianfeng Dong Shengkai Sun Zhonglin Liu Shujie Chen Baolong Liu and Xun Wang. 2023. Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning. In AAAI.","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"e_1_3_2_1_9_1","volume-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"Du Yong","unstructured":"Yong Du, Wei Wang, and Liang Wang. 2015. Hierarchical recurrent neural network for skeleton based action recognition. In IEEE CVPR."},{"key":"e_1_3_2_1_10_1","unstructured":"Luca Franco Paolo Mandica Bharti Munjal and Fabio Galasso. 2023. Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations. In ICLR."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yulu Gan Xianzheng Ma Yihang Lou Yan Bai Renrui Zhang Nian Shi and Lin Luo. 2023. Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation. (2023).","DOI":"10.1609\/aaai.v37i6.25922"},{"key":"e_1_3_2_1_12_1","unstructured":"Tianyu Guo Hong Liu Zhan Chen Mengyuan Liu Tao Wang and Runwei Ding. 2022. Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition. In AAAI."},{"key":"e_1_3_2_1_13_1","volume-title":"Masked autoencoders are scalable vision learners","author":"He Kaiming","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In IEEE CVPR."},{"key":"e_1_3_2_1_14_1","volume-title":"Momentum contrast for unsupervised visual representation learning","author":"He Kaiming","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In IEEE CVPR."},{"key":"e_1_3_2_1_15_1","volume-title":"A new representation of skeleton sequences for 3d action recognition","author":"Ke Qiuhong","unstructured":"Qiuhong Ke, Mohammed Bennamoun, Senjian An, Ferdous Sohel, and Farid Boussaid. 2017. A new representation of skeleton sequences for 3d action recognition. In IEEE CVPR."},{"key":"e_1_3_2_1_16_1","volume-title":"Jungho Kim, and Jin Young Choi.","author":"Kim Boeun","year":"2022","unstructured":"Boeun Kim, Hyung Jin Chang, Jungho Kim, and Jin Young Choi. 2022. Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning. ECCV (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Mixco: Mix-up contrastive learning for visual representation. arXiv:2010.06300","author":"Kim Sungnyun","year":"2020","unstructured":"Sungnyun Kim, Gihun Lee, Sangmin Bae, and Se-Young Yun. 2020. Mixco: Mix-up contrastive learning for visual representation. arXiv:2010.06300 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20102886"},{"key":"e_1_3_2_1_19_1","volume-title":"i-Mix: A domain-agnostic strategy for contrastive representation learning. arXiv:2010.08887","author":"Lee Kibok","year":"2020","unstructured":"Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, and Honglak Lee. 2020. i-Mix: A domain-agnostic strategy for contrastive representation learning. arXiv:2010.08887 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"3d human action representation learning via cross-view consistency pursuit","author":"Li Linguo","unstructured":"Linguo Li, Minsi Wang, Bingbing Ni, Hang Wang, Jiancheng Yang, and Wenjun Zhang. 2021. 3d human action representation learning via cross-view consistency pursuit. In IEEE CVPR."},{"key":"e_1_3_2_1_21_1","unstructured":"Lilang Lin Sijie Song Wenhan Yang and Jiaying Liu. 2020. Ms2l: Multi-task self-supervised learning for skeleton based action recognition. In ACM MM."},{"key":"e_1_3_2_1_22_1","volume-title":"IEEE TPAMI","volume":"42","author":"Liu Jun","year":"2019","unstructured":"Jun Liu, Amir Shahroudy, Mauricio Perez, Gang Wang, Ling-Yu Duan, and Alex C Kot. 2019. Ntu rgb d 120: A large-scale benchmark for 3d human activity understanding. IEEE TPAMI, Vol. 42, 10 (2019), 2684--2701."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365212"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1177\/1550147719894532"},{"key":"e_1_3_2_1_26_1","volume-title":"CMD: Self-supervised 3D Action Representation Learning with Cross-Modal Mutual Distillation. In ECCV.","author":"Mao Yunyao","year":"2022","unstructured":"Yunyao Mao, Wengang Zhou, Zhenbo Lu, Jiajun Deng, and Houqiang Li. 2022. CMD: Self-supervised 3D Action Representation Learning with Cross-Modal Mutual Distillation. In ECCV."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"e_1_3_2_1_28_1","volume-title":"Representation learning with contrastive predictive coding. arxiv","author":"van den Oord Aaron","year":"1807","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arxiv: 1807.03748"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219"},{"key":"e_1_3_2_1_30_1","volume-title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining. arXiv:2302.02318","author":"Qi Zekun","year":"2023","unstructured":"Zekun Qi, Runpei Dong, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, and Li Yi. 2023. Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining. arXiv:2302.02318 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"A Simple Data Mixing Prior for Improving Self-Supervised Learning","author":"Ren Sucheng","unstructured":"Sucheng Ren, Huiyu Wang, Zhengqi Gao, Shengfeng He, Alan Yuille, Yuyin Zhou, and Cihang Xie. 2022. A Simple Data Mixing Prior for Improving Self-Supervised Learning. In IEEE CVPR."},{"key":"e_1_3_2_1_32_1","volume-title":"David Jacobs, Anoop Cherian, and Rama Chellappa.","author":"Shah Anshul","year":"2023","unstructured":"Anshul Shah, Aniket Roy, Ketul Shah, Shlok Kumar Mishra, David Jacobs, Anoop Cherian, and Rama Chellappa. 2023. HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions. arXiv:2304.00387 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Ntu rgb d: A large scale dataset for 3d human activity analysis","author":"Shahroudy Amir","unstructured":"Amir Shahroudy, Jun Liu, Tian-Tsong Ng, and Gang Wang. 2016. Ntu rgb d: A large scale dataset for 3d human activity analysis. In IEEE CVPR."},{"key":"e_1_3_2_1_34_1","volume-title":"Un-mix: Rethinking image mixtures for unsupervised visual representation learning. In AAAI. 2216--2224.","author":"Shen Zhiqiang","year":"2022","unstructured":"Zhiqiang Shen, Zechun Liu, Zhuang Liu, Marios Savvides, Trevor Darrell, and Eric Xing. 2022. Un-mix: Rethinking image mixtures for unsupervised visual representation learning. In AAAI. 2216--2224."},{"key":"e_1_3_2_1_35_1","volume-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi Lei","unstructured":"Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. 2019. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In IEEE CVPR."},{"key":"e_1_3_2_1_36_1","unstructured":"Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2020. Decoupled spatial-temporal attention network for skeleton-based action recognition. arxiv: 1709.04875"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Sijie Song Cuiling Lan Junliang Xing Wenjun Zeng and Jiaying Liu. 2017. An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In AAAI.","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"e_1_3_2_1_38_1","volume-title":"Skeleton-indexed deep multi-modal feature learning for high performance human action recognition","author":"Song Sijie","unstructured":"Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, and Jiaying Liu. 2018. Skeleton-indexed deep multi-modal feature learning for high performance human action recognition. In IEEE ICME."},{"key":"e_1_3_2_1_39_1","volume-title":"Richly activated graph convolutional network for action recognition with incomplete skeletons","author":"Song Yi-Fan","unstructured":"Yi-Fan Song, Zhang Zhang, and Liang Wang. 2019. Richly activated graph convolutional network for action recognition with incomplete skeletons. In IEEE ICIP."},{"key":"e_1_3_2_1_40_1","volume-title":"Unsupervised skeleton based action recognition","author":"Su Kun","unstructured":"Kun Su, Xiulong Liu, and Eli Shlizerman. 2020. Predict & cluster: Unsupervised skeleton based action recognition. In IEEE CVPR."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Fida Mohammad Thoker Hazel Doughty and Cees GM Snoek. 2021. Skeleton-contrastive 3D action representation learning. In ACM MM.","DOI":"10.1145\/3474085.3475307"},{"key":"e_1_3_2_1_42_1","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent Pascal","year":"2010","unstructured":"Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol, and L\u00e9on Bottou. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research, Vol. 11, 12 (2010).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_43_1","first-page":"6224","article-title":"Contrast-reconstruction representation learning for self-supervised skeleton-based action recognition","volume":"31","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, Jun Wen, Chenyang Si, Yuntao Qian, and Liang Wang. 2022. Contrast-reconstruction representation learning for self-supervised skeleton-based action recognition. IEEE TIP, Vol. 31 (2022), 6224--6238.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_44_1","volume-title":"Co2: Consistent contrast for unsupervised visual representation learning. arxiv","author":"Wei Chen","year":"2010","unstructured":"Chen Wei, Huiyu Wang, Wei Shen, and Alan Yuille. 2020. Co2: Consistent contrast for unsupervised visual representation learning. arxiv: 2010.02217"},{"key":"e_1_3_2_1_45_1","unstructured":"Wenhan Wu Yilei Hua Shiqian Wu Chen Chen Aidong Lu et al. 2022. SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition. arXiv:2209.02399 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Simmim: A simple framework for masked image modeling","author":"Xie Zhenda","year":"2022","unstructured":"Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, and Han Hu. 2022. Simmim: A simple framework for masked image modeling. In IEEE CVPR."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Sijie Yan Yuanjun Xiong and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI. 7444--7452.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_48_1","volume-title":"Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo.","author":"Yun Sangdoo","year":"2019","unstructured":"Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo. 2019. Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV."},{"key":"e_1_3_2_1_49_1","unstructured":"Chen Zhan Liu Hong Guo Tianyu Chen Zhengyan Song Pinhao and Tang Hao. 2022. Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition. In arXiv: 2207.03065."},{"key":"e_1_3_2_1_50_1","unstructured":"Hongyi Zhang Moustapha Cisse Yann N Dauphin and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arxiv: 1710.09412"},{"key":"e_1_3_2_1_51_1","volume-title":"Contrastive positive mining for unsupervised 3d action representation learning","author":"Zhang Haoyuan","unstructured":"Haoyuan Zhang, Yonghong Hou, Wenjing Zhang, and Wanqing Li. 2022. Contrastive positive mining for unsupervised 3d action representation learning. In ECCV. Springer."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Jiahang Zhang Lilang Lin and Jiaying Liu. 2023. Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations. In AAAI.","DOI":"10.1609\/aaai.v37i3.25451"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Nenggan Zheng Jun Wen Risheng Liu Liangqu Long Jianhua Dai and Zhefeng Gong. 2018. Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.11853"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611774","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:15:21Z","timestamp":1755821721000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611774"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3611774","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611774","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}