{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:07:59Z","timestamp":1764842879364,"version":"3.37.3"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010882","name":"Tianjin Municipal Education Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010882","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010229","name":"Natural Science Foundation of Tianjin Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["2023KJ186"],"award-info":[{"award-number":["2023KJ186"]}],"id":[{"id":"10.13039\/501100010229","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1016\/j.sigpro.2024.109551","type":"journal-article","created":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T15:52:59Z","timestamp":1716652379000},"page":"109551","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["Spatio-Temporal Articulation & Coordination Co-attention Graph Network for human motion prediction"],"prefix":"10.1016","volume":"223","author":[{"given":"Shuang","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3707-7779","authenticated-orcid":false,"given":"Jin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Su","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.sigpro.2024.109551_b1","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/TITS.2020.3012034","article-title":"Deep learning-based vehicle behavior prediction for autonomous driving applications: A review","volume":"23","author":"Mozaffari","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.sigpro.2024.109551_b2","doi-asserted-by":"crossref","unstructured":"D. Conte, T. Furukawa, Autonomous Robotic Escort Incorporating Motion Prediction and Human Intention, in: IEEE International Conference on Robotics and Automation, ICRA, 2021, pp. 3480\u20133486.","DOI":"10.1109\/ICRA48506.2021.9561469"},{"issue":"4","key":"10.1016\/j.sigpro.2024.109551_b3","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","article-title":"Motchallenge: A benchmark for single-camera multiple target tracking","volume":"129","author":"Dendorfer","year":"2021","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.sigpro.2024.109551_b4","doi-asserted-by":"crossref","first-page":"2602","DOI":"10.1109\/LRA.2020.2972874","article-title":"Towards efficient human-robot collaboration with robust plan recognition and trajectory prediction","volume":"5","author":"Cheng","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.sigpro.2024.109551_b5","doi-asserted-by":"crossref","unstructured":"J. Martinez, M.J. Black, J. Romero, On Human Motion Prediction Using Recurrent Neural Networks, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 4674\u20134683.","DOI":"10.1109\/CVPR.2017.497"},{"key":"10.1016\/j.sigpro.2024.109551_b6","doi-asserted-by":"crossref","unstructured":"C. Li, Z. Zhang, W.S. Lee, G.H. Lee, Convolutional Sequence to Sequence Model for Human Dynamics, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 5226\u20135234.","DOI":"10.1109\/CVPR.2018.00548"},{"key":"10.1016\/j.sigpro.2024.109551_b7","doi-asserted-by":"crossref","unstructured":"Z. Liu, S. Wu, S. Jin, Q. Liu, S. Lu, R. Zimmermann, L. Cheng, Towards Natural and Accurate Future Motion Prediction of Humans and Animals, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 10004\u201310012.","DOI":"10.1109\/CVPR.2019.01024"},{"key":"10.1016\/j.sigpro.2024.109551_b8","doi-asserted-by":"crossref","unstructured":"W. Mao, M. Liu, M. Salzmann, H. Li, Learning Trajectory Dependencies for Human Motion Prediction, in: IEEE International Conference on Computer Vision, ICCV, 2019, pp. 9488\u20139496.","DOI":"10.1109\/ICCV.2019.00958"},{"key":"10.1016\/j.sigpro.2024.109551_b9","doi-asserted-by":"crossref","unstructured":"M. Li, S. Chen, Y. Zhao, Y. Zhang, Y. Wang, Q. Tian, Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 211\u2013220.","DOI":"10.1109\/CVPR42600.2020.00029"},{"year":"2020","series-title":"SDMTL: Semi-decoupled multi-grained trajectory learning for 3D human motion prediction","author":"Liu","key":"10.1016\/j.sigpro.2024.109551_b10"},{"issue":"6","key":"10.1016\/j.sigpro.2024.109551_b11","doi-asserted-by":"crossref","first-page":"2133","DOI":"10.1109\/TCSVT.2020.3021409","article-title":"TrajectoryCNN: A new spatio-temporal feature learning network for human motion prediction","volume":"31","author":"Liu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.sigpro.2024.109551_b12","doi-asserted-by":"crossref","unstructured":"W. Mao, M. Liu, M. Salzmann, History Repeats Itself: Human Motion Prediction via Motion Attention, in: European Conference on Computer Vision, ECCV, Vol. 12359, 2020, pp. 474\u2013489.","DOI":"10.1007\/978-3-030-58568-6_28"},{"key":"10.1016\/j.sigpro.2024.109551_b13","series-title":"ACM Multimedia","first-page":"713","article-title":"Motion prediction via joint dependency modeling in phase space","author":"Su","year":"2021"},{"key":"10.1016\/j.sigpro.2024.109551_b14","doi-asserted-by":"crossref","unstructured":"Z. Liu, P. Su, S. Wu, X. Shen, H. Chen, Y. Hao, M. Wang, Motion Prediction using Trajectory Cues, in: IEEE International Conference on Computer Vision, ICCV, 2021, pp. 13279\u201313288.","DOI":"10.1109\/ICCV48922.2021.01305"},{"key":"10.1016\/j.sigpro.2024.109551_b15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cviu.2018.01.007","article-title":"Biometric recognition by gait: A survey of modalities and features","volume":"167","author":"Connor","year":"2018","journal-title":"Comput. Vis. Image Underst."},{"issue":"1s","key":"10.1016\/j.sigpro.2024.109551_b16","doi-asserted-by":"crossref","first-page":"23:1","DOI":"10.1145\/3180420","article-title":"Sequential articulated motion reconstruction from a monocular image sequence","volume":"14","author":"Su","year":"2018","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"year":"2022","series-title":"3D human motion prediction: A survey","author":"Lyu","key":"10.1016\/j.sigpro.2024.109551_b17"},{"key":"10.1016\/j.sigpro.2024.109551_b18","doi-asserted-by":"crossref","unstructured":"E. Aksan, M. Kaufmann, O. Hilliges, Structured Prediction Helps 3D Human Motion Modelling, in: IEEE International Conference on Computer Vision, ICCV, 2019, pp. 7143\u20137152.","DOI":"10.1109\/ICCV.2019.00724"},{"key":"10.1016\/j.sigpro.2024.109551_b19","doi-asserted-by":"crossref","unstructured":"K. Fragkiadaki, S. Levine, P. Felsen, J. Malik, Recurrent Network Models for Human Dynamics, in: IEEE International Conference on Computer Vision, ICCV, 2015, pp. 4346\u20134354.","DOI":"10.1109\/ICCV.2015.494"},{"key":"10.1016\/j.sigpro.2024.109551_b20","doi-asserted-by":"crossref","unstructured":"L. Gui, Y. Wang, X. Liang, J.M.F. Moura, Adversarial Geometry-Aware Human Motion Prediction, in: European Conference on Computer Vision, ECCV, 2018, pp. 823\u2013842.","DOI":"10.1007\/978-3-030-01225-0_48"},{"key":"10.1016\/j.sigpro.2024.109551_b21","doi-asserted-by":"crossref","unstructured":"A. Gopalakrishnan, A.A. Mali, D. Kifer, C.L. Giles, A.G.O. II, A Neural Temporal Model for Human Motion Prediction, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 12116\u201312125.","DOI":"10.1109\/CVPR.2019.01239"},{"key":"10.1016\/j.sigpro.2024.109551_b22","doi-asserted-by":"crossref","unstructured":"X. Guo, J. Choi, Human Motion Prediction via Learning Local Structure Representations and Temporal Dependencies, in: AAAI Conference on Artificial Intelligence, AAAI, 2019, pp. 2580\u20132587.","DOI":"10.1609\/aaai.v33i01.33012580"},{"key":"10.1016\/j.sigpro.2024.109551_b23","doi-asserted-by":"crossref","unstructured":"Q. Cui, H. Sun, F. Yang, Learning Dynamic Relationships for 3D Human Motion Prediction, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 6518\u20136526.","DOI":"10.1109\/CVPR42600.2020.00655"},{"key":"10.1016\/j.sigpro.2024.109551_b24","doi-asserted-by":"crossref","unstructured":"Q. Cui, H. Sun, Towards Accurate 3D Human Motion Prediction From Incomplete Observations, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 4801\u20134810.","DOI":"10.1109\/CVPR46437.2021.00477"},{"key":"10.1016\/j.sigpro.2024.109551_b25","doi-asserted-by":"crossref","unstructured":"Q. Li, G. Chalvatzaki, J. Peters, Y. Wang, Directed Acyclic Graph Neural Network for Human Motion Prediction, in: IEEE International Conference on Robotics and Automation, ICRA, 2021, pp. 3197\u20133204.","DOI":"10.1109\/ICRA48506.2021.9561540"},{"key":"10.1016\/j.sigpro.2024.109551_b26","doi-asserted-by":"crossref","first-page":"7760","DOI":"10.1109\/TIP.2021.3108708","article-title":"Multiscale spatio-temporal graph neural networks for 3D skeleton-based motion prediction","volume":"30","author":"Li","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.sigpro.2024.109551_b27","doi-asserted-by":"crossref","unstructured":"H. Zhou, C. Guo, H. Zhang, Y. Wang, Learning Multiscale Correlations for Human Motion Prediction, in: IEEE International Conference on Development and Learning, ICDL, 2021, pp. 1\u20137.","DOI":"10.1109\/ICDL49984.2021.9515609"},{"key":"10.1016\/j.sigpro.2024.109551_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2020.102380","article-title":"VDARN: Video disentangling attentive relation network for few-shot and zero-shot action recognition","volume":"113","author":"Su","year":"2021","journal-title":"Ad Hoc Netw."},{"key":"10.1016\/j.sigpro.2024.109551_b29","doi-asserted-by":"crossref","unstructured":"S. Yan, Y. Xiong, D. Lin, Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition, in: AAAI Conference on Artificial Intelligence, AAAI, 2018, pp. 7444\u20137452.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"10.1016\/j.sigpro.2024.109551_b30","unstructured":"R. J\u00f3zefowicz, W. Zaremba, I. Sutskever, An Empirical Exploration of Recurrent Network Architectures, in: F.R. Bach, D.M. Blei (Eds.), International Conference on Machine Learning, ICML, Vol. 37, 2015, pp. 2342\u20132350."},{"key":"10.1016\/j.sigpro.2024.109551_b31","doi-asserted-by":"crossref","unstructured":"A. Jain, A.R. Zamir, S. Savarese, A. Saxena, Structural-RNN: Deep Learning on Spatio-Temporal Graphs, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 5308\u20135317.","DOI":"10.1109\/CVPR.2016.573"},{"key":"10.1016\/j.sigpro.2024.109551_b32","doi-asserted-by":"crossref","unstructured":"E. Corona, A. Pumarola, G. Aleny\u00e0, F. Moreno-Noguer, Context-Aware Human Motion Prediction, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 6990\u20136999.","DOI":"10.1109\/CVPR42600.2020.00702"},{"key":"10.1016\/j.sigpro.2024.109551_b33","unstructured":"O. Azencot, N.B. Erichson, V. Lin, M.W. Mahoney, Forecasting Sequential Data Using Consistent Koopman Autoencoders, in: International Conference on Machine Learning, ICML, 2020, pp. 475\u2013485."},{"key":"10.1016\/j.sigpro.2024.109551_b34","doi-asserted-by":"crossref","first-page":"2562","DOI":"10.1109\/TIP.2020.3038362","article-title":"Multitask non-autoregressive model for human motion prediction","volume":"30","author":"Li","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.sigpro.2024.109551_b35","unstructured":"D. Pavllo, D. Grangier, M. Auli, QuaterNet: A Quaternion-based Recurrent Model for Human Motion, in: British Machine Vision Conference, BMVC, 2018, p. 299."},{"key":"10.1016\/j.sigpro.2024.109551_b36","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ins.2020.08.123","article-title":"Efficient human motion prediction using temporal convolutional generative adversarial network","volume":"545","author":"Cui","year":"2021","journal-title":"Inform. Sci."},{"key":"10.1016\/j.sigpro.2024.109551_b37","doi-asserted-by":"crossref","unstructured":"T.S. Kim, A. Reiter, Interpretable 3D Human Action Analysis with Temporal Convolutional Networks, in: IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, 2017, pp. 1623\u20131631.","DOI":"10.1109\/CVPRW.2017.207"},{"key":"10.1016\/j.sigpro.2024.109551_b38","series-title":"Advances in Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.sigpro.2024.109551_b39","doi-asserted-by":"crossref","unstructured":"Y. Cai, L. Huang, Y. Wang, T. Cham, J. Cai, J. Yuan, J. Liu, X. Yang, Y. Zhu, X. Shen, D. Liu, J. Liu, N. Magnenat-Thalmann, Learning Progressive Joint Propagation for Human Motion Prediction, in: European Conference on Computer Vision, ECCV, 2020, pp. 226\u2013242.","DOI":"10.1007\/978-3-030-58571-6_14"},{"issue":"9","key":"10.1016\/j.sigpro.2024.109551_b40","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.1007\/s11263-021-01483-7","article-title":"Multi-level motion attention for human motion prediction","volume":"129","author":"Mao","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.sigpro.2024.109551_b41","doi-asserted-by":"crossref","unstructured":"E. Aksan, M. Kaufmann, P. Cao, O. Hilliges, A Spatio-temporal Transformer for 3D Human Motion Prediction, in: International Conference on 3D Vision, 3DV, 2021, pp. 565\u2013574.","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"10.1016\/j.sigpro.2024.109551_b42","doi-asserted-by":"crossref","unstructured":"A. Mart\u00ednez-Gonz\u00e1lez, M. Villamizar, J.M. Odobez, Pose Transformers (PoTR): Human motion prediction with non-autoregressive transformers, in: IEEE International Conference on Computer Vision, ICCV, 2021, pp. 2276\u20132284.","DOI":"10.1109\/ICCVW54120.2021.00257"},{"key":"10.1016\/j.sigpro.2024.109551_b43","unstructured":"J. Wang, H. Xu, M. Narasimhan, et al., Multi-person 3D motion prediction with Multi-Range Transformers, in: Advances in Neural Information Processing Systems, NIPS, 2021, pp. 6036\u20136049."},{"year":"2020","series-title":"A generalization of transformer networks to graphs","author":"Dwivedi","key":"10.1016\/j.sigpro.2024.109551_b44"},{"key":"10.1016\/j.sigpro.2024.109551_b45","unstructured":"C. Ying, T. Cai, S. Luo, S. Zheng, G. Ke, D. He, Y. Shen, T.-Y. Liu, Do transformers really perform badly for graph representation?, in: Advances in Neural Information Processing Systems, NIPS, 2021, pp. 28877\u201328888."},{"year":"2021","series-title":"Graphit: Encoding graph structure in transformers","author":"Mialon","key":"10.1016\/j.sigpro.2024.109551_b46"},{"key":"10.1016\/j.sigpro.2024.109551_b47","unstructured":"S. Yun, M. Jeong, R. Kim, J. Kang, H.J. Kim, Graph transformer networks, in: Advances in neural information processing systems, NIPS, 2019, pp. 3201\u20133214."},{"key":"10.1016\/j.sigpro.2024.109551_b48","doi-asserted-by":"crossref","unstructured":"W. Bao, Q. Yu, Y. Kong, Evidential Deep Learning for Open Set Action Recognition, in: IEEE International Conference on Computer Vision, ICCV, 2021, pp. 13329\u201313338.","DOI":"10.1109\/ICCV48922.2021.01310"},{"issue":"7","key":"10.1016\/j.sigpro.2024.109551_b49","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","article-title":"Human3.6M: Large scale datasets and predictive methods for 3D human sensing in natural environments","volume":"36","author":"Ionescu","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.sigpro.2024.109551_b50","doi-asserted-by":"crossref","unstructured":"T. von Marcard, R. Henschel, M.J. Black, B. Rosenhahn, G. Pons-Moll, Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera, in: European Conference on Computer Vision, ECCV, 2018, pp. 614\u2013631.","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"10.1016\/j.sigpro.2024.109551_b51","doi-asserted-by":"crossref","unstructured":"L. Dang, Y. Nie, C. Long, Q. Zhang, G. Li, MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction, in: IEEE International Conference on Computer Vision, ICCV, 2021, pp. 11467\u201311476.","DOI":"10.1109\/ICCV48922.2021.01127"}],"container-title":["Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168424001701?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168424001701?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T22:03:14Z","timestamp":1720044194000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0165168424001701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":51,"alternative-id":["S0165168424001701"],"URL":"https:\/\/doi.org\/10.1016\/j.sigpro.2024.109551","relation":{},"ISSN":["0165-1684"],"issn-type":[{"type":"print","value":"0165-1684"}],"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Spatio-Temporal Articulation & Coordination Co-attention Graph Network for human motion prediction","name":"articletitle","label":"Article Title"},{"value":"Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sigpro.2024.109551","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109551"}}