{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:04:57Z","timestamp":1780931097686,"version":"3.54.1"},"reference-count":50,"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.2026.113993","type":"journal-article","created":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T15:07:34Z","timestamp":1779548854000},"page":"113993","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["MXPose: Multiplex interactive learning for multi-view 3D Human Pose Estimation"],"prefix":"10.1016","volume":"180","author":[{"given":"Wanruo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1867-5324","authenticated-orcid":false,"given":"Zhou","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113993_b1","doi-asserted-by":"crossref","unstructured":"K. Iskakov, E. Burkov, V. Lempitsky, Y. Malkov, Learnable triangulation of human pose, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 7718\u20137727.","DOI":"10.1109\/ICCV.2019.00781"},{"key":"10.1016\/j.patcog.2026.113993_b2","doi-asserted-by":"crossref","unstructured":"B. Jiang, L. Hu, S. Xia, Probabilistic triangulation for uncalibrated multi-view 3D human pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 14850\u201314860.","DOI":"10.1109\/ICCV51070.2023.01364"},{"key":"10.1016\/j.patcog.2026.113993_b3","series-title":"European Conference on Computer Vision","first-page":"695","article-title":"Structural triangulation: A closed-form solution to constrained 3d human pose estimation","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.113993_b4","first-page":"12721","article-title":"Triangulation residual loss for data-efficient 3D pose estimation","volume":"36","author":"Zhao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113993_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110316","article-title":"Kinematics-aware spatial-temporal feature transform for 3D human pose estimation","volume":"150","author":"Du","year":"2024","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2026.113993_b6","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1007\/s00138-020-01120-2","article-title":"A generalizable approach for multi-view 3d human pose regression","volume":"32","author":"Kadkhodamohammadi","year":"2021","journal-title":"Mach. Vis. Appl."},{"key":"10.1016\/j.patcog.2026.113993_b7","series-title":"European Conference on Computer Vision","first-page":"197","article-title":"Voxelpose: Towards multi-camera 3d human pose estimation in wild environment","author":"Tu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113993_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.107863","article-title":"An adversarial human pose estimation network injected with graph structure","volume":"115","author":"Tian","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113993_b9","article-title":"STGFormer: Spatio-temporal GraphFormer for 3D human pose estimation in video","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113993_b10","article-title":"Spectral compression transformer with line pose graph for monocular 3D human pose estimation","author":"Zheng","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113993_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103830","article-title":"View consistency aware holistic triangulation for 3D human pose estimation","volume":"236","author":"Wan","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.113993_b12","series-title":"Transfusion: Cross-view fusion with transformer for 3d human pose estimation","author":"Ma","year":"2021"},{"key":"10.1016\/j.patcog.2026.113993_b13","doi-asserted-by":"crossref","unstructured":"Y. He, R. Yan, K. Fragkiadaki, S.-I. Yu, Epipolar transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 7779\u20137788.","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"10.1016\/j.patcog.2026.113993_b14","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.patcog.2026.113993_b15","series-title":"Self-supervised contrastive graph representation with node and graph augmentation","author":"Duan","year":"2023"},{"key":"10.1016\/j.patcog.2026.113993_b16","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.patcog.2026.113993_b17","doi-asserted-by":"crossref","unstructured":"H.D. Nguyen, X.-S. Vu, D.-T. Le, Modular graph transformer networks for multi-label image classification, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 9092\u20139100.","DOI":"10.1609\/aaai.v35i10.17098"},{"key":"10.1016\/j.patcog.2026.113993_b18","article-title":"Higher-order implicit fairing networks for 3D human pose estimation","author":"Quan","year":"2021","journal-title":"Proc. Br. Mach. Vis. Conf."},{"key":"10.1016\/j.patcog.2026.113993_b19","series-title":"PH-GCN: Boosting human action recognition through multi-level granularity with pair-wise hyper GCN","author":"Alsarhan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113993_b20","series-title":"April-GCN: Adjacency position-velocity relationship interaction learning GCN for human motion prediction","author":"Gu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113993_b21","series-title":"Informed patch enhanced HyperGCN for skeleton-based action recognition","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.113993_b22","series-title":"2025 International Joint Conference on Neural Networks","article-title":"HGMamba: Enhancing 3D human pose estimation with a HyperGCN-mamba network","author":"Cui","year":"2025"},{"key":"10.1016\/j.patcog.2026.113993_b23","series-title":"2021 IEEE\/CVF International Conference on Computer Vision","article-title":"Hypergraph neural networks for hypergraph matching","author":"Liao","year":"2021"},{"key":"10.1016\/j.patcog.2026.113993_b24","doi-asserted-by":"crossref","unstructured":"Y. Bengio, J. Louradour, R. Collobert, J. Weston, Curriculum learning, in: Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"10.1016\/j.patcog.2026.113993_b25","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, X. Zhou, K.G. Derpanis, K. Daniilidis, Coarse-to-fine volumetric prediction for single-image 3D human pose, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7025\u20137034.","DOI":"10.1109\/CVPR.2017.139"},{"key":"10.1016\/j.patcog.2026.113993_b26","series-title":"Reconsideration of multi-stage deep network for human pose estimation","author":"Verma","year":"2021"},{"key":"10.1016\/j.patcog.2026.113993_b27","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"},{"issue":"7","key":"10.1016\/j.patcog.2026.113993_b28","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.patcog.2026.113993_b29","series-title":"2017 International Conference on 3D Vision","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.2026.113993_b30","doi-asserted-by":"crossref","unstructured":"H. Rhodin, J. Sp\u00f6rri, I. Katircioglu, V. Constantin, F. Meyer, E. M\u00fcller, M. Salzmann, P. Fua, Learning monocular 3d human pose estimation from multi-view images, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 8437\u20138446.","DOI":"10.1109\/CVPR.2018.00880"},{"key":"10.1016\/j.patcog.2026.113993_b31","doi-asserted-by":"crossref","unstructured":"K. Zhou, L. Zhang, F. Lu, X.-D. Zhou, Y. Shi, Efficient hierarchical multi-view fusion transformer for 3D human pose estimation, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 7512\u20137520.","DOI":"10.1145\/3581783.3612098"},{"key":"10.1016\/j.patcog.2026.113993_b32","doi-asserted-by":"crossref","unstructured":"F. Zhou, J. Yin, P. Li, Lifting by image\u2013leveraging image cues for accurate 3d human pose estimation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 7632\u20137640.","DOI":"10.1609\/aaai.v38i7.28596"},{"key":"10.1016\/j.patcog.2026.113993_b33","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.patcog.2026.113993_b34","doi-asserted-by":"crossref","unstructured":"H. Li, B. Shi, W. Dai, H. Zheng, B. Wang, Y. Sun, M. Guo, C. Li, J. Zou, H. Xiong, Pose-oriented transformer with uncertainty-guided refinement for 2d-to-3d human pose estimation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 1296\u20131304.","DOI":"10.1609\/aaai.v37i1.25213"},{"key":"10.1016\/j.patcog.2026.113993_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109631","article-title":"Multi-hypothesis representation learning for transformer-based 3D human pose estimation","volume":"141","author":"Li","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113993_b36","doi-asserted-by":"crossref","unstructured":"J. Gong, L.G. Foo, Z. Fan, Q. Ke, H. Rahmani, J. Liu, Diffpose: Toward more reliable 3d pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 13041\u201313051.","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"10.1016\/j.patcog.2026.113993_b37","doi-asserted-by":"crossref","unstructured":"H. Ci, M. Wu, W. Zhu, X. Ma, H. Dong, F. Zhong, Y. Wang, Gfpose: Learning 3d human pose prior with gradient fields, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 4800\u20134810.","DOI":"10.1109\/CVPR52729.2023.00465"},{"key":"10.1016\/j.patcog.2026.113993_b38","series-title":"2018 International Conference on 3D Vision","first-page":"474","article-title":"Rethinking pose in 3d: Multi-stage refinement and recovery for markerless motion capture","author":"Tome","year":"2018"},{"issue":"3","key":"10.1016\/j.patcog.2026.113993_b39","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1007\/s11263-021-01570-9","article-title":"Consensus-based optimization for 3D human pose estimation in camera coordinates","volume":"130","author":"Luvizon","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113993_b40","doi-asserted-by":"crossref","unstructured":"H. Qiu, C. Wang, J. Wang, N. Wang, W. Zeng, Cross view fusion for 3d human pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4342\u20134351.","DOI":"10.1109\/ICCV.2019.00444"},{"key":"10.1016\/j.patcog.2026.113993_b41","series-title":"2023 IEEE International Conference on Image Processing","first-page":"1600","article-title":"Progressive multi-view fusion for 3D human pose estimation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113993_b42","doi-asserted-by":"crossref","unstructured":"L. Zhang, K. Zhou, F. Lu, X.-D. Zhou, Y. Shi, Deep semantic graph transformer for multi-view 3d human pose estimation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 7205\u20137214.","DOI":"10.1609\/aaai.v38i7.28549"},{"key":"10.1016\/j.patcog.2026.113993_b43","article-title":"ESMformer: Error-aware self-supervised transformer for multi-view 3D human pose estimation","volume":"158","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.patcog.2026.113993_b44","doi-asserted-by":"crossref","first-page":"4122","DOI":"10.1109\/TPAMI.2022.3188716","article-title":"Adaptive multi-view and temporal fusing transformer for 3d human pose estimation","volume":"45","author":"Shuai","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113993_b45","doi-asserted-by":"crossref","unstructured":"M. Kocabas, S. Karagoz, E. Akbas, Self-supervised learning of 3d human pose using multi-view geometry, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 1077\u20131086.","DOI":"10.1109\/CVPR.2019.00117"},{"key":"10.1016\/j.patcog.2026.113993_b46","doi-asserted-by":"crossref","unstructured":"B. Wandt, M. Rudolph, P. Zell, H. Rhodin, B. Rosenhahn, Canonpose: Self-supervised monocular 3d human pose estimation in the wild, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 13294\u201313304.","DOI":"10.1109\/CVPR46437.2021.01309"},{"key":"10.1016\/j.patcog.2026.113993_b47","doi-asserted-by":"crossref","unstructured":"X. Chen, P. Wei, L. Lin, Deductive learning for weakly-supervised 3d human pose estimation via uncalibrated cameras, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 1089\u20131096.","DOI":"10.1609\/aaai.v35i2.16194"},{"key":"10.1016\/j.patcog.2026.113993_b48","doi-asserted-by":"crossref","unstructured":"X. Gong, L. Song, M. Zheng, B. Planche, T. Chen, J. Yuan, D. Doermann, Z. Wu, Progressive multi-view human mesh recovery with self-supervision, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 676\u2013684.","DOI":"10.1609\/aaai.v37i1.25144"},{"key":"10.1016\/j.patcog.2026.113993_b49","series-title":"2022 IEEE International Conference on Image Processing","first-page":"1231","article-title":"Spatio-temporal attention graph for monocular 3d human pose estimation","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113993_b50","series-title":"European Conference on Computer Vision","first-page":"176","article-title":"FLEX: extrinsic parameters-free multi-view 3D human motion reconstruction","author":"Gordon","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009581?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009581?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:43:14Z","timestamp":1780929794000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009581"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":50,"alternative-id":["S0031320326009581"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113993","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":"MXPose: Multiplex interactive learning for multi-view 3D Human Pose Estimation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113993","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":"113993"}}