{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T12:22:37Z","timestamp":1777897357067,"version":"3.51.4"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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","award":["62171251"],"award-info":[{"award-number":["62171251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013108","name":"Special Foundation for the Development of Strategic Emerging Industries of Shenzen Municipality","doi-asserted-by":"publisher","award":["JCYJ20200109143035495"],"award-info":[{"award-number":["JCYJ20200109143035495"]}],"id":[{"id":"10.13039\/501100013108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013108","name":"Special Foundation for the Development of Strategic Emerging Industries of Shenzen Municipality","doi-asserted-by":"publisher","award":["CJGJZD20210408092804011"],"award-info":[{"award-number":["CJGJZD20210408092804011"]}],"id":[{"id":"10.13039\/501100013108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013108","name":"Special Foundation for the Development of Strategic Emerging Industries of Shenzen Municipality","doi-asserted-by":"publisher","award":["JSGG20211108092812020"],"award-info":[{"award-number":["JSGG20211108092812020"]}],"id":[{"id":"10.13039\/501100013108","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.cviu.2026.104707","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T16:36:42Z","timestamp":1773419802000},"page":"104707","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["MuRE: Multi-Relationship Encoder for 3D human pose estimation"],"prefix":"10.1016","volume":"267","author":[{"given":"Yong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5189-8565","authenticated-orcid":false,"given":"Doudou","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5771-3886","authenticated-orcid":false,"given":"Hongbo","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104707_b1","series-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3686","article-title":"2D human pose estimation: New benchmark and state of the art analysis","author":"Andriluka","year":"2014"},{"key":"10.1016\/j.cviu.2026.104707_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.103974","article-title":"Spatr: Mocap 3d human action recognition based on spiral auto-encoder and transformer network","volume":"241","author":"Bouzid","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104707_b3","doi-asserted-by":"crossref","unstructured":"Cai,\u00a0Y., Ge,\u00a0L., Liu,\u00a0J., Cai,\u00a0J., Cham,\u00a0T.J., Yuan,\u00a0J., Thalmann,\u00a0N.M., 2019. Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV.","DOI":"10.1109\/ICCV.2019.00236"},{"key":"10.1016\/j.cviu.2026.104707_b4","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"HTNet: Human topology aware network for 3d human pose estimation","author":"Cai","year":"2023"},{"key":"10.1016\/j.cviu.2026.104707_b5","series-title":"HDFormer: High-order directed transformer for 3D human pose estimation","author":"Chen","year":"2023"},{"key":"10.1016\/j.cviu.2026.104707_b6","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0Y., Wang,\u00a0Z., Peng,\u00a0Y., Zhang,\u00a0Z., Yu,\u00a0G., Sun,\u00a0J., 2018. Cascaded Pyramid Network for Multi-Person Pose Estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"10.1016\/j.cviu.2026.104707_b7","doi-asserted-by":"crossref","unstructured":"Ci,\u00a0H., Wang,\u00a0C., Ma,\u00a0X., Wang,\u00a0Y., 2019. Optimizing Network Structure for 3D Human Pose Estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV.","DOI":"10.1109\/ICCV.2019.00235"},{"key":"10.1016\/j.cviu.2026.104707_b8","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/LSP.2024.3358111","article-title":"TFAN: Twin-flow axis normalization for human motion prediction","volume":"31","author":"Du","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"issue":"7","key":"10.1016\/j.cviu.2026.104707_b9","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.cviu.2026.104707_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2025.104337","article-title":"Establishing a unified evaluation framework for human motion generation: A comparative analysis of metrics","volume":"254","author":"Ismail-Fawaz","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104707_b11","series-title":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7870","article-title":"Exploring latent cross-channel embedding for accurate 3d human pose reconstruction in a diffusion framework","author":"Jiang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104707_b12","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.cviu.2026.104707_b13","series-title":"GraphMLP: A graph MLP-like architecture for 3D human pose estimation","author":"Li","year":"2023"},{"key":"10.1016\/j.cviu.2026.104707_b14","first-page":"1296","article-title":"Pose-oriented transformer with uncertainty-guided refinement for 2d-to-3d human pose estimation","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.cviu.2026.104707_b15","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"AMPose: Alternately mixed global-local attention model for 3D human pose estimation","author":"Lin","year":"2023"},{"key":"10.1016\/j.cviu.2026.104707_b16","series-title":"Computer Vision \u2013 ECCV 2020","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.cviu.2026.104707_b17","doi-asserted-by":"crossref","DOI":"10.34133\/cbsystems.0002","article-title":"Generalized pose decoupled network for unsupervised 3d skeleton sequence-based action representation learning","author":"Liu","year":"2022","journal-title":"Cyborg Bionic Syst."},{"key":"10.1016\/j.cviu.2026.104707_b18","article-title":"Temporal decoupling graph convolutional network for skeleton-based gesture recognition","author":"Liu","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104707_b19","series-title":"Refined temporal pyramidal compression-and-amplification transformer for 3D human pose estimation","author":"Liu","year":"2024"},{"key":"10.1016\/j.cviu.2026.104707_b20","series-title":"2022 26th International Conference on Pattern Recognition","first-page":"1156","article-title":"Jointformer: Single-frame lifting transformer with error prediction and refinement for 3D human pose estimation","author":"Lutz","year":"2022"},{"key":"10.1016\/j.cviu.2026.104707_b21","doi-asserted-by":"crossref","unstructured":"Martinez,\u00a0J., Hossain,\u00a0R., Romero,\u00a0J., Little,\u00a0J.J., 2017. A Simple yet Effective Baseline for 3D Human Pose Estimation. In: Proceedings of the IEEE International Conference on Computer Vision. ICCV.","DOI":"10.1109\/ICCV.2017.288"},{"key":"10.1016\/j.cviu.2026.104707_b22","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.cviu.2026.104707_b23","doi-asserted-by":"crossref","unstructured":"Pavlakos,\u00a0G., Zhou,\u00a0X., Derpanis,\u00a0K.G., Daniilidis,\u00a0K., 2017. Coarse-to-fine volumetric prediction for single-image 3D human pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7025\u20137034.","DOI":"10.1109\/CVPR.2017.139"},{"key":"10.1016\/j.cviu.2026.104707_b24","series-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"10.1016\/j.cviu.2026.104707_b25","doi-asserted-by":"crossref","first-page":"4039","DOI":"10.1109\/TMM.2023.3321438","article-title":"Global and local spatio-temporal encoder for 3D human pose estimation","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104707_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.107898","article-title":"SCGRFuse: An infrared and visible image fusion network based on spatial\/channel attention mechanism and gradient aggregation residual dense blocks","volume":"132","author":"Wang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104707_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIP.2023.3334954","article-title":"Dynamic dense graph convolutional network for skeleton-based human motion prediction","volume":"33","author":"Wang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104707_b28","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0T., Takano,\u00a0W., 2021. Graph Stacked Hourglass Networks for 3D Human Pose Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 16105\u201316114.","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"10.1016\/j.cviu.2026.104707_b29","series-title":"SRNet: Improving generalization in 3D human pose estimation with a split-and-recombine approach","author":"Zeng","year":"2020"},{"issue":"10","key":"10.1016\/j.cviu.2026.104707_b30","doi-asserted-by":"crossref","first-page":"6889","DOI":"10.1109\/TPAMI.2024.3386777","article-title":"A modular neural motion retargeting system decoupling skeleton and shape perception","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104707_b31","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0J., Tu,\u00a0Z., Yang,\u00a0J., Chen,\u00a0Y., Yuan,\u00a0J., 2022. 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. pp. 13232\u201313242.","DOI":"10.1109\/CVPR52688.2022.01288"},{"issue":"6","key":"10.1016\/j.cviu.2026.104707_b32","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1007\/s11263-023-01770-5","article-title":"Learning enriched hop-aware correlation for robust 3d human pose estimation","volume":"131","author":"Zhang","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104707_b33","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1109\/TIP.2023.3345177","article-title":"Facial prior guided micro-expression generation","volume":"33","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104707_b34","doi-asserted-by":"crossref","unstructured":"Zhao,\u00a0L., Peng,\u00a0X., Tian,\u00a0Y., Kapadia,\u00a0M., Metaxas,\u00a0D.N., 2019. Semantic Graph Convolutional Networks for 3D Human Pose Regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR.","DOI":"10.1109\/CVPR.2019.00354"},{"key":"10.1016\/j.cviu.2026.104707_b35","doi-asserted-by":"crossref","unstructured":"Zhao,\u00a0W., Wang,\u00a0W., Tian,\u00a0Y., 2022. GraFormer: Graph-Oriented Transformer for 3D Pose Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 20438\u201320447.","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"10.1016\/j.cviu.2026.104707_b36","doi-asserted-by":"crossref","unstructured":"Zheng,\u00a0C., Zhu,\u00a0S., Mendieta,\u00a0M., Yang,\u00a0T., Chen,\u00a0C., Ding,\u00a0Z., 2021. 3d human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 11656\u201311665.","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"10.1016\/j.cviu.2026.104707_b37","series-title":"Overcoming topology agnosticism: Enhancing skeleton-based action recognition through redefined skeletal topology awareness","author":"Zhou","year":"2024"},{"key":"10.1016\/j.cviu.2026.104707_b38","series-title":"Computer Vision \u2013 ECCV 2016 Workshops","first-page":"186","article-title":"Deep kinematic pose regression","author":"Zhou","year":"2016"},{"key":"10.1016\/j.cviu.2026.104707_b39","doi-asserted-by":"crossref","unstructured":"Zhou,\u00a0Y., Yan,\u00a0X., Cheng,\u00a0Z.Q., Yan,\u00a0Y., Dai,\u00a0Q., Hua,\u00a0X.S., 2024b. BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2049\u20132058.","DOI":"10.1109\/CVPR52733.2024.00200"},{"key":"10.1016\/j.cviu.2026.104707_b40","doi-asserted-by":"crossref","unstructured":"Zou,\u00a0Z., Tang,\u00a0W., 2021. Modulated Graph Convolutional Network for 3D Human Pose Estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 11477\u201311487.","DOI":"10.1109\/ICCV48922.2021.01128"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000743?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000743?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T22:15:43Z","timestamp":1776204943000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226000743"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":40,"alternative-id":["S1077314226000743"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104707","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MuRE: Multi-Relationship Encoder for 3D human pose estimation","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104707","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104707"}}