{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T15:23:27Z","timestamp":1787412207011,"version":"build-2736575974"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.imavis.2026.106115","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:35:21Z","timestamp":1783640121000},"page":"106115","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FAGNet: A full attention-modulated geometric learning network for 3D pose estimation"],"prefix":"10.1016","volume":"174","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9668-4272","authenticated-orcid":false,"given":"Xiaofeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongnan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghuai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106115_b1","series-title":"Computer Vision\u2013ACCV 2014: 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part II 12","first-page":"332","article-title":"3D human pose estimation from monocular images with deep convolutional neural network","author":"Li","year":"2015"},{"key":"10.1016\/j.imavis.2026.106115_b2","series-title":"International Conference on Intelligent Robotics and Applications","first-page":"176","article-title":"3D human pose estimation in video for human-computer\/robot interaction","author":"Huo","year":"2023"},{"key":"10.1016\/j.imavis.2026.106115_b3","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.aej.2024.08.072","article-title":"Enhancing human pose estimation in sports training: Integrating spatiotemporal transformer for improved accuracy and real-time performance","volume":"109","author":"Xi","year":"2024","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.imavis.2026.106115_b4","doi-asserted-by":"crossref","first-page":"133330","DOI":"10.1109\/ACCESS.2020.3010248","article-title":"The progress of human pose estimation: A survey and taxonomy of models applied in 2D human pose estimation","volume":"8","author":"Munea","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.imavis.2026.106115_b5","series-title":"Real-Time Vision for Human-Computer Interaction","author":"Kisacanin","year":"2005"},{"issue":"3","key":"10.1016\/j.imavis.2026.106115_b6","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1049\/cit2.12255","article-title":"Precise region semantics-assisted GAN for pose-guided person image generation","volume":"9","author":"Liu","year":"2024","journal-title":"CAAI Trans. Intell. Technol."},{"key":"10.1016\/j.imavis.2026.106115_b7","doi-asserted-by":"crossref","first-page":"1959","DOI":"10.1007\/s00521-022-07806-0","article-title":"C3N: Content-constrained convolutional network for mural image completion","volume":"35","author":"Peng","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.imavis.2026.106115_b8","doi-asserted-by":"crossref","first-page":"23519","DOI":"10.1038\/s41598-024-72368-1","article-title":"PRN: progressive reasoning network and its image completion applications","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.imavis.2026.106115_b9","series-title":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition","first-page":"1","article-title":"Benchmarking skeleton-based motion encoder models for clinical applications: Estimating parkinson\u2019s disease severity in walking sequences","author":"Adeli","year":"2024"},{"key":"10.1016\/j.imavis.2026.106115_b10","series-title":"International Conference on Advanced Concepts for Intelligent Vision Systems","first-page":"321","article-title":"Augmented reality with human body interaction based on monocular 3d pose estimation","author":"Lin","year":"2010"},{"issue":"4","key":"10.1016\/j.imavis.2026.106115_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073596","article-title":"Vnect: Real-time 3d human pose estimation with a single rgb camera","volume":"36","author":"Mehta","year":"2017","journal-title":"Acm Trans. Graph. (Tog)"},{"key":"10.1016\/j.imavis.2026.106115_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103275","article-title":"A review of 3D human pose estimation algorithms for markerless motion capture","volume":"212","author":"Desmarais","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.imavis.2026.106115_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2021.103407","article-title":"Fall detection using body geometry and human pose estimation in video sequences","volume":"82","author":"Beddiar","year":"2022","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.imavis.2026.106115_b14","doi-asserted-by":"crossref","unstructured":"J. Wang, D. Luvizon, W. Xu, L. Liu, K. Sarkar, C. Theobalt, Scene-aware egocentric 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13031\u201313040.","DOI":"10.1109\/CVPR52729.2023.01252"},{"key":"10.1016\/j.imavis.2026.106115_b15","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106115_b16","series-title":"Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III 14","first-page":"156","article-title":"3D human pose estimation using convolutional neural networks with 2d pose information","author":"Park","year":"2016"},{"key":"10.1016\/j.imavis.2026.106115_b17","doi-asserted-by":"crossref","unstructured":"S. Mehraban, V. Adeli, B. Taati, Motionagformer: Enhancing 3d human pose estimation with a transformer-gcnformer network, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 6920\u20136930.","DOI":"10.1109\/WACV57701.2024.00677"},{"key":"10.1016\/j.imavis.2026.106115_b18","doi-asserted-by":"crossref","unstructured":"Y. Chen, Z. Zhang, C. Yuan, B. Li, Y. Deng, W. Hu, Channel-wise topology refinement graph convolution for skeleton-based action recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 13359\u201313368.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"10.1016\/j.imavis.2026.106115_b19","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part X 16","first-page":"318","article-title":"A comprehensive study of weight sharing in graph networks for 3d human pose estimation","author":"Liu","year":"2020"},{"key":"10.1016\/j.imavis.2026.106115_b20","doi-asserted-by":"crossref","unstructured":"W. Hu, C. Zhang, F. Zhan, L. Zhang, T.-T. Wong, Conditional directed graph convolution for 3d human pose estimation, in: Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 602\u2013611.","DOI":"10.1145\/3474085.3475219"},{"key":"10.1016\/j.imavis.2026.106115_b21","doi-asserted-by":"crossref","unstructured":"T. Xu, W. Takano, Graph stacked hourglass networks for 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 16105\u201316114.","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"10.1016\/j.imavis.2026.106115_b22","article-title":"Multi-label co-regularization for semi-supervised facial action unit recognition","volume":"32","author":"Niu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106115_b23","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII 16","first-page":"769","article-title":"Pose2mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose","author":"Choi","year":"2020"},{"key":"10.1016\/j.imavis.2026.106115_b24","doi-asserted-by":"crossref","unstructured":"L. Zhao, X. Peng, Y. Tian, M. Kapadia, D.N. Metaxas, Semantic graph convolutional networks for 3d human pose regression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3425\u20133435.","DOI":"10.1109\/CVPR.2019.00354"},{"key":"10.1016\/j.imavis.2026.106115_b25","doi-asserted-by":"crossref","unstructured":"C. Zhuang, Q. Ma, Dual graph convolutional networks for graph-based semi-supervised classification, in: Proceedings of the 2018 World Wide Web Conference, 2018, pp. 499\u2013508.","DOI":"10.1145\/3178876.3186116"},{"key":"10.1016\/j.imavis.2026.106115_b26","doi-asserted-by":"crossref","unstructured":"H. Ci, C. Wang, X. Ma, Y. Wang, Optimizing network structure for 3d human pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 2262\u20132271.","DOI":"10.1109\/ICCV.2019.00235"},{"key":"10.1016\/j.imavis.2026.106115_b27","doi-asserted-by":"crossref","unstructured":"Q. Zhao, C. Zheng, M. Liu, P. Wang, C. Chen, Poseformerv2: Exploring frequency domain for efficient and robust 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 8877\u20138886.","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"10.1016\/j.imavis.2026.106115_b28","doi-asserted-by":"crossref","unstructured":"C. Zheng, S. Zhu, M. Mendieta, T. Yang, C. Chen, Z. Ding, 3d human pose estimation with spatial and temporal transformers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11656\u201311665.","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"10.1016\/j.imavis.2026.106115_b29","doi-asserted-by":"crossref","unstructured":"Z. Tang, Z. Qiu, Y. Hao, R. Hong, T. Yao, 3D human pose estimation with spatio-temporal criss-cross attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 4790\u20134799.","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"10.1016\/j.imavis.2026.106115_b30","doi-asserted-by":"crossref","unstructured":"W. Zhu, X. Ma, Z. Liu, L. Liu, W. Wu, Y. Wang, Motionbert: A unified perspective on learning human motion representations, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15085\u201315099.","DOI":"10.1109\/ICCV51070.2023.01385"},{"key":"10.1016\/j.imavis.2026.106115_b31","doi-asserted-by":"crossref","unstructured":"N.D. Reddy, L. Guigues, L. Pishchulin, J. Eledath, S.G. Narasimhan, Tessetrack: End-to-end learnable multi-person articulated 3d pose tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15190\u201315200.","DOI":"10.1109\/CVPR46437.2021.01494"},{"key":"10.1016\/j.imavis.2026.106115_b32","doi-asserted-by":"crossref","unstructured":"Y. Chen, Z. Wang, Y. Peng, Z. Zhang, G. Yu, J. Sun, Cascaded pyramid network for multi-person pose estimation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7103\u20137112.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"10.1016\/j.imavis.2026.106115_b33","doi-asserted-by":"crossref","unstructured":"G. Moon, J.Y. Chang, K.M. Lee, Camera distance-aware top-down approach for 3d multi-person pose estimation from a single rgb image, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 10133\u201310142.","DOI":"10.1109\/ICCV.2019.01023"},{"key":"10.1016\/j.imavis.2026.106115_b34","doi-asserted-by":"crossref","unstructured":"W. Yu, M. Luo, P. Zhou, C. Si, Y. Zhou, X. Wang, J. Feng, S. Yan, Metaformer is actually what you need for vision, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10819\u201310829.","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"10.1016\/j.imavis.2026.106115_b35","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, X. Zhou, K. Daniilidis, Ordinal depth supervision for 3d human pose estimation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7307\u20137316.","DOI":"10.1109\/CVPR.2018.00763"},{"key":"10.1016\/j.imavis.2026.106115_b36","doi-asserted-by":"crossref","unstructured":"T. Wehrbein, M. Rudolph, B. Rosenhahn, B. Wandt, Probabilistic monocular 3d human pose estimation with normalizing flows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11199\u201311208.","DOI":"10.1109\/ICCV48922.2021.01101"},{"issue":"1","key":"10.1016\/j.imavis.2026.106115_b37","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","article-title":"Anatomy-aware 3d human pose estimation with bone-based pose decomposition","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106115_b38","doi-asserted-by":"crossref","unstructured":"R. Liu, J. Shen, H. Wang, C. Chen, S.-c. Cheung, V. Asari, Attention mechanism exploits temporal contexts: Real-time 3d human pose reconstruction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 5064\u20135073.","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"10.1016\/j.imavis.2026.106115_b39","doi-asserted-by":"crossref","unstructured":"M.R.I. Hossain, J.J. Little, Exploiting temporal information for 3d human pose estimation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 68\u201384.","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"10.1016\/j.imavis.2026.106115_b40","doi-asserted-by":"crossref","unstructured":"J. Martinez, R. Hossain, J. Romero, J.J. Little, A simple yet effective baseline for 3d human pose estimation, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2640\u20132649.","DOI":"10.1109\/ICCV.2017.288"},{"key":"10.1016\/j.imavis.2026.106115_b41","doi-asserted-by":"crossref","unstructured":"K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5693\u20135703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"10.1016\/j.imavis.2026.106115_b42","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1016\/j.neunet.2023.11.003","article-title":"Enhancement, integration, expansion: Activating representation of detailed features for occluded person re-identification","volume":"169","author":"Ning","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.imavis.2026.106115_b43","doi-asserted-by":"crossref","unstructured":"W. Shan, Z. Liu, X. Zhang, Z. Wang, K. Han, S. Wang, S. Ma, W. Gao, Diffusion-based 3d human pose estimation with multi-hypothesis aggregation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 14761\u201314771.","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"10.1016\/j.imavis.2026.106115_b44","doi-asserted-by":"crossref","unstructured":"Y. Zhan, F. Li, R. Weng, W. Choi, Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13116\u201313125.","DOI":"10.1109\/CVPR52688.2022.01277"},{"key":"10.1016\/j.imavis.2026.106115_b45","doi-asserted-by":"crossref","unstructured":"J.N. Kundu, S. Seth, P. YM, V. Jampani, A. Chakraborty, R.V. Babu, Uncertainty-aware adaptation for self-supervised 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 20448\u201320459.","DOI":"10.1109\/CVPR52688.2022.01980"},{"key":"10.1016\/j.imavis.2026.106115_b46","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.1109\/TMM.2022.3141231","article-title":"Exploiting temporal contexts with strided transformer for 3d human pose estimation","volume":"25","author":"Li","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2026.106115_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111200","article-title":"Mv-reid: 3d multi-view transformation network for occluded person re-identification","volume":"283","author":"Yu","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"2","key":"10.1016\/j.imavis.2026.106115_b48","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1109\/TPAMI.2022.3163709","article-title":"Voxeltrack: Multi-person 3d human pose estimation and tracking in the wild","volume":"45","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106115_b49","series-title":"European Conference on Computer Vision","first-page":"142","article-title":"Faster voxelpose: Real-time 3d human pose estimation by orthographic projection","author":"Ye","year":"2022"},{"key":"10.1016\/j.imavis.2026.106115_b50","doi-asserted-by":"crossref","unstructured":"Q. Cai, X. Hu, S. Hou, L. Yao, Y. Huang, Disentangled diffusion-based 3d human pose estimation with hierarchical spatial and temporal denoiser, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 882\u2013890.","DOI":"10.1609\/aaai.v38i2.27847"},{"key":"10.1016\/j.imavis.2026.106115_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2023.09.001","article-title":"Transformer-based rapid human pose estimation network","author":"Wang","year":"2023","journal-title":"Comput. Graph."},{"key":"10.1016\/j.imavis.2026.106115_b52","doi-asserted-by":"crossref","unstructured":"Z. Zou, W. Tang, Modulated graph convolutional network for 3D human pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11477\u201311487.","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"10.1016\/j.imavis.2026.106115_b53","article-title":"A single 2d pose with context is worth hundreds for 3d human pose estimation","volume":"36","author":"Zhao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106115_b54","series-title":"Hdformer: High-order directed transformer for 3D human pose estimation","author":"Chen","year":"2023"},{"key":"10.1016\/j.imavis.2026.106115_b55","doi-asserted-by":"crossref","unstructured":"J. Peng, Y. Zhou, P. Mok, Ktpformer: Kinematics and trajectory prior knowledge-enhanced transformer for 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 1123\u20131132.","DOI":"10.1109\/CVPR52733.2024.00113"},{"key":"10.1016\/j.imavis.2026.106115_b56","unstructured":"B.X. Yu, Z. Zhang, Y. Liu, S.-h. Zhong, Y. Liu, C.W. Chen, Gla-gcn: Global-local adaptive graph convolutional network for 3d human pose estimation from monocular video, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 8818\u20138829."},{"key":"10.1016\/j.imavis.2026.106115_b57","doi-asserted-by":"crossref","unstructured":"A. Zeng, X. Sun, L. Yang, N. Zhao, M. Liu, Q. Xu, Learning skeletal graph neural networks for hard 3d pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11436\u201311445.","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"10.1016\/j.imavis.2026.106115_b58","article-title":"Understanding batch normalization","volume":"31","author":"Bjorck","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106115_b59","article-title":"Understanding and improving layer normalization","volume":"32","author":"Xu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106115_b60","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.imavis.2026.106115_b61","series-title":"Kolmogorov-Arnold Networks: Key Developments and Uses","author":"Kilani","year":"2024"},{"key":"10.1016\/j.imavis.2026.106115_b62","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/978-3-319-60801-3_27","article-title":"Multilayer perceptron (MLP)","author":"Taud","year":"2018","journal-title":"Geomat. Approaches Model. Land Chang. Scenar."},{"key":"10.1016\/j.imavis.2026.106115_b63","doi-asserted-by":"crossref","unstructured":"W. Li, H. Liu, H. Tang, P. Wang, L. Van Gool, Mhformer: Multi-hypothesis transformer for 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13147\u201313156.","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"10.1016\/j.imavis.2026.106115_b64","doi-asserted-by":"crossref","unstructured":"J. Zhang, Z. Tu, J. Yang, Y. Chen, J. Yuan, Mixste: Seq2seq mixed spatio-temporal encoder for 3d human pose estimation in video, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13232\u201313242.","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"10.1016\/j.imavis.2026.106115_b65","series-title":"European Conference on Computer Vision","first-page":"461","article-title":"P-stmo: Pre-trained spatial temporal many-to-one model for 3d human pose estimation","author":"Shan","year":"2022"},{"key":"10.1016\/j.imavis.2026.106115_b66","series-title":"Double-chain constraints for 3D human pose estimation in images and videos","author":"Kang","year":"2023"},{"key":"10.1016\/j.imavis.2026.106115_b67","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110925","article-title":"GraphMLP: A graph MLP-like architecture for 3D human pose estimation","volume":"158","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"issue":"7","key":"10.1016\/j.imavis.2026.106115_b68","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":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106115_b69","series-title":"2017 International Conference on 3D Vision (3DV)","first-page":"506","article-title":"Monocular 3d human pose estimation in the wild using improved cnn supervision","author":"Mehta","year":"2017"},{"key":"10.1016\/j.imavis.2026.106115_b70","series-title":"European Conference on Computer Vision","first-page":"343","article-title":"WorldPose: A world cup dataset for global 3D human pose estimation","author":"Jiang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106115_b71","series-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2017"},{"key":"10.1016\/j.imavis.2026.106115_b72","article-title":"Weight decay with tailored adam on scale-invariant weights for better generalization","author":"Jia","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626002222?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626002222?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T14:41:59Z","timestamp":1787409719000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626002222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":72,"alternative-id":["S0262885626002222"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106115","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FAGNet: A full attention-modulated geometric learning network for 3D pose estimation","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106115","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 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":"106115"}}