{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:43:36Z","timestamp":1793205816171,"version":"4.5.0"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733468","type":"print"},{"value":"9783031733475","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73347-5_7","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"110-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["MacDiff: Unified Skeleton Modeling with\u00a0Masked Conditional Diffusion"],"prefix":"10.1007","author":[{"given":"Lehong","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lilang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-9576","authenticated-orcid":false,"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"7_CR1","unstructured":"Alex\u00a0Nichol, P.D.: Improved denoising diffusion probabilistic models. arXiv preprint arXiv:2102.09672 (2021)"},{"issue":"10","key":"7_CR2","doi-asserted-by":"publisher","first-page":"6131","DOI":"10.1109\/TITS.2020.3006768","volume":"22","author":"F Camara","year":"2020","unstructured":"Camara, F., et al.: Pedestrian models for autonomous driving part I: low-level models, from sensing to tracking. IEEE Trans. Intell. Transp. Syst. 22(10), 6131\u20136151 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.H., Zhang, J., Li, Y., Pang, Y., Xia, X., Liu, T.: HumanMAC: masked motion completion for human motion prediction. In: Int. Conf. Comput. Vis. (2023)","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"7_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Int. Conf. Mach. Learn. (2020)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: IEEE Conference on Computer Visual Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"7_CR6","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Hierarchically self-supervised transformer for human skeleton representation learning. In: European Conference Computer Vision (2022)","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"7_CR8","unstructured":"Chen, Z., Liu, H., Guo, T., Chen, Z., Song, P., Tang, H.: Contrastive learning from spatio-temporal mixed skeleton sequences for self-supervised skeleton-based action recognition. arXiv preprint arXiv:2207.03065 (2022)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Ci, H., et al.: GFPose: learning 3D human pose prior with gradient fields. In: IEEE Conference Computer Vision Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00465"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Ci, Y., et al.: UniHCP: a unified model for human-centric perceptions. In: IEEE Conference Computer Vision Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"7_CR11","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advance Neural Information Processing System (2021)"},{"key":"7_CR12","unstructured":"Dong, Y., Cordonnier, J.B., Loukas, A.: Attention is not all you need: pure attention loses rank doubly exponentially with depth. arXiv preprint arXiv:2103.03404 (2021)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Flaborea, A., Collorone, L., di\u00a0Melendugno Stefano\u00a0D\u2019Arrigo, G.M.D., Prenkaj, B., Galasso, F.: Multimodal motion conditioned diffusion model for skeleton-based video anomaly detection. In: International Conference Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00947"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Foo, L.G., Li, T., Rahmani, H., Ke, Q., Liu, J.: Unified pose sequence modeling. In: IEEE Conference Computer Vision Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01251"},{"issue":"1","key":"7_CR15","first-page":"19","volume":"1","author":"Z Goldfeld","year":"2020","unstructured":"Goldfeld, Z., Polyanskiy, Y.: The information bottleneck problem and its applications in machine learning. IEEE JSAIT 1(1), 19\u201338 (2020)","journal-title":"IEEE JSAIT"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L.G., Fan, Z., Ke, Q., Rahmani, H., Liu, J.: DiffPose: toward more reliable 3D pose estimation. In: IEEE Conference Computer Vision Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: IEEE Conference Computer Vision Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR18","unstructured":"Ho, J., Jain, A., bbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arXiv:2006.11239 (2020)"},{"key":"7_CR19","unstructured":"Huang, W., Rong, Y., Xu, T., Sun, F., Huang, J.: Tackling over-smoothing for general graph convolutional networks. arXiv preprint arXiv:2008.09864 (2020)"},{"key":"7_CR20","unstructured":"Hudson, D.A., et al.: SODA: bottleneck diffusion models for representation learning. arXiv preprint arXiv:2311.17901 (2023)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Kim, B., Chang, H.J., Kim, J., , Choi, J.Y.: Global-local motion transformer for unsupervised skeleton-based action learning. In: European Conference Computer Vision (2022)","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"7_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"7_CR23","unstructured":"Kun,\u00a0S., Liu, X., E.S.: PREDICT and CLUSTER: Unsupervised skeleton based action recognition. arXiv preprint arXiv:1911.12409 (2019)"},{"issue":"10","key":"7_CR24","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.3390\/s20102886","volume":"20","author":"J Lee","year":"2020","unstructured":"Lee, J., Ahn, B.: Real-time human action recognition with a low-cost RGB camera and mobile robot platform. Sensors 20(10), 2886 (2020)","journal-title":"Sensors"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, M., Ni, B., Wang, H., Yang, J., Zhang, W.: 3D human action representation learning via cross-view consistency pursuit. In: IEEE Conference Computer Vision Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Lin, L., Song, S., Yang, W., Liu, J.: MS2L: multi-task self-supervised learning for skeleton based action recognition. In: ACM International Conference Multimedia (2020)","DOI":"10.1145\/3394171.3413548"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Lin, L., Zhang, J., Liu, J.: Actionlet-dependent contrastive learning for unsupervised skeleton-based action recognition. In: IEEE Conference Computer Vision Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00234"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Liu, J., Song, S., Liu, C., Li, Y., , Hu, Y.: A benchmark dataset and comparison study for multi-modal human action analytics. In: ACM TOMM (2020)","DOI":"10.1145\/3365212"},{"key":"7_CR29","volume-title":"NTU RGB+D 120: A large-scale benchmark for 3D human activity understanding","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+D 120: A large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach, Intell (2019)"},{"key":"7_CR30","unstructured":"Liu, Z., Li, B., Han, C., Guo, T., Nie, X.: Masked reconstruction contrastive learning with information bottleneck principle. arXiv preprint arXiv:2211.09013 (2022)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Gool, R.T.L.V.: RePaint: inpainting using denoising diffusion probabilistic models. In: IEEE Conference Computer Vision Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Mao, Y., Deng, J., Zhou, W., Fang, Y., Ouyang, W., Li, H.: Masked motion predictors are strong 3D action representation learners. In: International Conference Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Mao, Y., Zhou, W., Lu, Z., Deng, J., Li, H.: CMD: self-supervised 3D action representation learning with cross-modal mutual distillation. In: European Conference Computer Vision (2022)","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"7_CR34","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"7_CR35","unstructured":"Nam, J., et al.: Diffusion model for dense matching. In: International Conference on Learning Representation (2024)"},{"key":"7_CR36","unstructured":"Namekata, K., Sabour, A., Fidler, S., Kim, S.W.: EmerDiff: emerging pixel-level semantic knowledge in diffusion models. In: International Conference on Learning Representation (2024)"},{"key":"7_CR37","unstructured":"van\u00a0den Oord, A., Vinyals, O., koray kavukcuoglu: neural discrete representation learning. In: Advance Neural Information Processing System (2017)"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Preechakul, K., Chatthee, N., Wizadwongsa, S., Suwajanakorn, S.: Diffusion autoencoders: toward a meaningful and decodable representation. In: IEEE Conference on Computer Vision Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Rao, H., Xu, S., Hu, X., Cheng, J., Hu, B.: Augmented skeleton based contrastive action learning with momentum LSTM for unsupervised action recognition. In: Information Sciences (2021)","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. arXiv preprint arXiv:2112.10752 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"7_CR42","unstructured":"Saharia, C., et al: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., , Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: IEEE Conference on Computer Vision Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"7_CR44","doi-asserted-by":"crossref","unstructured":"Shwartz-Ziv, R., LeCun, Y.: To compress or not to compress - self-supervised learning and information theory: a view. arXiv preprint arXiv:2304.09355 (2023)","DOI":"10.3390\/e26030252"},{"key":"7_CR45","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Su, Y., Lin, G., Wu, Q.: Self-supervised 3D skeleton action representation learning with motion consistency and continuity. In: Internationl Conference Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"7_CR47","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: International Conference Learning Representation (2023)"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., , Snoek, C.G.: Skeleton-contrastive 3D action representation learning. In: ACM Interanational Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475307"},{"key":"7_CR49","unstructured":"Tianyu, G., Hong, L., Zhan, C., Mengyuan, L., Tao, W., Runwei, D.: Contrastive learning from extremely augmented skeleton sequences for self-supervised action recognition. In: AAAI (2022)"},{"key":"7_CR50","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advance Neural Information Processing System (2022)"},{"key":"7_CR51","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advance Neural Information Processing System (2017)"},{"key":"7_CR52","unstructured":"Wang, H., Guo, X., Deng, Z.H., Lu, Y.: What makes for good representations for contrastive learning. In: Advance Neural Information Processing System (2020)"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Wang, H., Guo, X., Deng, Z., Lu, Y.: Rethinking minimal sufficient representation in contrastive learning. In: IEEE Conference Computing Vision Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01557"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., Fang, Z., Li, X., Li, X., Chen, C., Liu, M.: Skeleton-in-context: unified skeleton sequence modeling with in-context learning. arXiv preprint arXiv:2312.03703 (2023)","DOI":"10.1109\/CVPR52733.2024.00236"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Wu, W., Hua, Y., Zheng, C., Wu, S., Chen, C., Lu, A.: SkeletonMAE: spatial-temporal masked autoencoders for self-supervised skeleton action recognition. arXiv preprint arXiv:2209.02399 (2022)","DOI":"10.1109\/ICMEW59549.2023.00045"},{"key":"7_CR56","unstructured":"Yuan, J., Zhang, J., Sun, S., Torr, P., Zhao, B.: Real-Fake: effective training data synthesis through distribution matching. In: International Conference Learning Representations (2024)"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hou, Y., Zhang, W., Li, W.: Contrastive positive mining for unsupervised 3D action representation learning. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"7_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, L., Liu, J.: Prompted contrast with masked motion modeling: towards versatile 3D action representation learning. In: ACMMM (2023)","DOI":"10.1145\/3581783.3611774"},{"key":"7_CR59","unstructured":"Zhang, M., et al.: MotionDiffuse: text-driven human motion generation with diffusion model. IEEE Transaction Pattern Analysis Machice Intelligence, pp. 1\u201315 (2024)"},{"key":"7_CR60","unstructured":"Zhang, Y., Zhou, D., Hooi, B., Wang, K., Feng, J.: Expanding small-scale datasets with guided imagination. In: Advance Neural Information Processing System (2023)"},{"key":"7_CR61","unstructured":"Zhang, Z., Zhao, Z., Lin, Z.: Unsupervised representation learning from pre-trained diffusion probabilistic models. In: Advance Neural Information Processing System (2022)"},{"key":"7_CR62","doi-asserted-by":"crossref","unstructured":"Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., , Gong, Z.: Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"7_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Liu, Z., Liu, L., Wu, W., Wang, Y.: MotionBERT: a unified perspective on learning human motion representations. In: International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01385"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73347-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:45:11Z","timestamp":1730108711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}