{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:18:06Z","timestamp":1783509486400,"version":"3.55.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114389","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:44:29Z","timestamp":1783061069000},"page":"114389","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Gen3D-Mamba: Directional state space fusion and hidden state pruning for generalizable 3D skeleton pose estimation"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3974-1373","authenticated-orcid":false,"given":"Jialin","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114389_b1","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.patcog.2026.114389_b2","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.patcog.2026.114389_b3","doi-asserted-by":"crossref","unstructured":"C. Zhang, T. Yang, J. Weng, M. Cao, J. Wang, Y. Zou, Unsupervised Pre-training for Temporal Action Localization Tasks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 14031\u201314041.","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"10.1016\/j.patcog.2026.114389_b4","doi-asserted-by":"crossref","unstructured":"J. Gong, Z. Fan, Q. Ke, H. Rahmani, J. Liu, Meta Agent Teaming Active Learning for Pose Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 11079\u201311089.","DOI":"10.1109\/CVPR52688.2022.01080"},{"key":"10.1016\/j.patcog.2026.114389_b5","first-page":"1234","article-title":"Dynamic dense graph convolutional network for skeleton-based human motion prediction","volume":"32","author":"Wang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114389_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109809","article-title":"Human fall detection using pose estimation: From traditional machine learning to vision transformers","volume":"143","author":"Raza","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114389_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105813","article-title":"Deep learning-based real-time 3D human pose estimation","volume":"119","author":"Zhang","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114389_b8","doi-asserted-by":"crossref","unstructured":"W. Jiang, H. Xue, C. Miao, S. Wang, S. Lin, C. Tian, S. Murali, H. Hu, Z. Sun, L. Su, WiViPose: A Video-aided Wi-Fi Framework for Environment-Independent 3D Human Pose Estimation, in: Proceedings of the ACM International Conference on Mobile Computing and Networking (MobiCom), 2020, pp. 1\u201313.","DOI":"10.1145\/3372224.3380900"},{"key":"10.1016\/j.patcog.2026.114389_b9","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, ICCV, 2021, pp. 11199\u201311208.","DOI":"10.1109\/ICCV48922.2021.01101"},{"key":"10.1016\/j.patcog.2026.114389_b10","doi-asserted-by":"crossref","unstructured":"A. Zeng, X. Sun, F. Huang, M. Liu, Q. Xu, S. Lin, SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach, in: European Conference on Computer Vision, ECCV, 2020, pp. 507\u2013523.","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"10.1016\/j.patcog.2026.114389_b11","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, ICCV, 2017, pp. 2640\u20132649.","DOI":"10.1109\/ICCV.2017.288"},{"key":"10.1016\/j.patcog.2026.114389_b12","doi-asserted-by":"crossref","first-page":"8537","DOI":"10.1109\/TIP.2025.3644785","article-title":"PoseMoE: Mixture-of-experts network for monocular 3D human pose estimation","volume":"34","author":"Liu","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114389_b13","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1109\/TMM.2024.3521755","article-title":"Enhancing 3D human pose estimation amidst severe occlusion with dual transformer fusion","volume":"27","author":"Ghafoor","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114389_b14","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, CVPR, 2024, pp. 1123\u20131132.","DOI":"10.1109\/CVPR52733.2024.00113"},{"key":"10.1016\/j.patcog.2026.114389_b15","article-title":"A skeleton-deconstructed transformer with graph convolution for efficient monocular 3D human pose estimation","author":"Zhong","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114389_b16","doi-asserted-by":"crossref","unstructured":"X. Sun, B. Xiao, S. Liang, Y. Wei, Integral Human Pose Regression, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 529\u2013545.","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"10.1016\/j.patcog.2026.114389_b17","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, X. Zhou, K. Daniilidis, Ordinal Depth Supervision for 3D Human Pose Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 7307\u20137316.","DOI":"10.1109\/CVPR.2018.00763"},{"key":"10.1016\/j.patcog.2026.114389_b18","doi-asserted-by":"crossref","unstructured":"D. Pavllo, C. Feichtenhofer, D. Grangier, M. Auli, 3D Human Pose Estimation in Video with Temporal Convolutions and Semi-Supervised Training, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 7753\u20137762.","DOI":"10.1109\/CVPR.2019.00794"},{"key":"10.1016\/j.patcog.2026.114389_b19","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, CVPR, 2020, pp. 5064\u20135073.","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"10.1016\/j.patcog.2026.114389_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112511","article-title":"Human motion prediction using mixture-of-branch graph convolutional network","volume":"162","author":"Li","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114389_b21","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, CVPR, 2023, pp. 8877\u20138886.","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"10.1016\/j.patcog.2026.114389_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.114125","article-title":"3D human pose estimation with decoupled spatio-temporal hybrid transformer","volume":"180","author":"Peng","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114389_b23","article-title":"DSVTformer: Dual-stream spatial-view-temporal transformer for multi-view 3D human pose estimation","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114389_b24","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.patcog.2026.114389_b25","doi-asserted-by":"crossref","first-page":"1439","DOI":"10.1109\/TMM.2022.3233251","article-title":"Depth-aware multi-person 3D pose estimation with multi-scale waterfall representations","volume":"25","author":"Shen","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114389_b26","doi-asserted-by":"crossref","unstructured":"H. Zheng, H. Li, W. Dai, Z. Zheng, C. Li, J. Zou, H. Xiong, Hipart: Hierarchical pose autoregressive transformer for occluded 3d human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 16807\u201316817.","DOI":"10.1109\/CVPR52734.2025.01566"},{"key":"10.1016\/j.patcog.2026.114389_b27","series-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114389_b28","series-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114389_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109413","article-title":"Knowledge enhanced multi-task learning for simultaneous optimization of human parsing and pose estimation","volume":"138","author":"Zhou","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114389_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112068","article-title":"Three-dimensional human pose estimation based on multi-scale spatial\u2013temporal transformer","volume":"161","author":"Song","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114389_b31","series-title":"Proceedings of the 41st International Conference on Machine Learning","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume":"vol. 235","author":"Dao","year":"2024"},{"key":"10.1016\/j.patcog.2026.114389_b32","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"Vmamba: Visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114389_b33","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3842","article-title":"PoseMamba: Monocular 3D human pose estimation with bidirectional global-local spatio-temporal state space model","volume":"vol. 39","author":"Huang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114389_b34","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10248","article-title":"Pose magic: Efficient and temporally consistent human pose estimation with a hybrid mamba-gcn network","volume":"vol. 39","author":"Zhang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114389_b35","series-title":"2025 International Joint Conference on Neural Networks","first-page":"1","article-title":"Hgmamba: Enhancing 3d human pose estimation with a hypergcn-mamba network","author":"Cui","year":"2025"},{"key":"10.1016\/j.patcog.2026.114389_b36","unstructured":"Z. Yang, J. Bai, H. Li, J. Dai, J. Pan, Y. Yin, B. Li, VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2026, pp. 28458\u201328467."},{"key":"10.1016\/j.patcog.2026.114389_b37","doi-asserted-by":"crossref","unstructured":"S. Long, Q. Zhou, X. Li, X. Lu, C. Ying, Y. Luo, L. Ma, S. Yan, DGMamba: Domain Generalization via Generalized State Space Model, in: Proceedings of the ACM International Conference on Multimedia, 2024.","DOI":"10.1145\/3664647.3681247"},{"key":"10.1016\/j.patcog.2026.114389_b38","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, ICCV, 2021, pp. 11656\u201311665.","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"10.1016\/j.patcog.2026.114389_b39","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, CVPR, 2022, pp. 13147\u201313156.","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"10.1016\/j.patcog.2026.114389_b40","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, CVPR, 2022, pp. 13232\u201313242.","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"10.1016\/j.patcog.2026.114389_b41","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, CVPR, 2023, pp. 4790\u20134799.","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"10.1016\/j.patcog.2026.114389_b42","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.patcog.2026.114389_b43","article-title":"Spectral compression transformer with line pose graph for monocular 3D human pose estimation","author":"Zheng","year":"2025","journal-title":"Pattern Recognit."},{"issue":"7","key":"10.1016\/j.patcog.2026.114389_b44","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."},{"issue":"1\u20132","key":"10.1016\/j.patcog.2026.114389_b45","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","article-title":"HumanEva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion","volume":"87","author":"Sigal","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114389_b46","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.patcog.2026.114389_b47","doi-asserted-by":"crossref","unstructured":"W. Yu, X. Wang, Mambaout: Do we really need mamba for vision?, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025, pp. 4484\u20134496.","DOI":"10.1109\/CVPR52734.2025.00423"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013543?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326013543?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T10:47:49Z","timestamp":1783507669000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326013543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":47,"alternative-id":["S0031320326013543"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114389","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Gen3D-Mamba: Directional state space fusion and hidden state pruning for generalizable 3D skeleton pose estimation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114389","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114389"}}