{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:52:54Z","timestamp":1792086774135,"version":"4.4.0"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>3D human pose estimation from single-view images is a fundamental and challenging task in computer vision, the key of which lies in effectively capturing the complex spatial dependencies between human joint points. Existing methods usually rely on a single computational paradigm: Graph Convolutional Networks (GCN) excel at capturing local physical constraints, the self-attention mechanism (Attn) is adept at modeling global dynamic correlations, and Multi-Layer Perceptrons (MLP) provide an efficient way for global context encoding. Although previous works have attempted to fuse these methods, they often adopt serial, simple parallel or dual-stream structures, failing to fully explore the synergistic potential among these three heterogeneous computational paradigms, which results in limited representation capability under complex or rare poses. To address the above limitations, this paper proposes a novel Tri-Channel Synergistic Model (TCSM) aiming to construct a more comprehensive and robust feature representation for single-frame pose estimation. The core idea of this model is to decouple the dependencies of different natures in human poses and perform optimal parsing in independent and functionally specific channels. Specifically, our model designs three parallel feature streams: a GCN channel for encoding structure modality based on human topology, an attention channel for capturing long-range dynamic correlation modality, and an MLP channel for efficiently extracting global context modality. To achieve deep synergy, we design a two-stage feature fusion and refinement mechanism, in which the outputs of each channel interact and are iteratively enhanced. Experiments on the Human3.6M benchmark demonstrate that TCSM achieves competitive single-frame performance. The model obtains 47.7 mm MPJPE and 37.8 mm PA-MPJPE without a pose refinement module, and the ablation results verify the contribution of the tri-channel design and the two-stage interaction mechanism.<\/jats:p>","DOI":"10.1371\/journal.pone.0359200","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:38:08Z","timestamp":1792085888000},"page":"e0359200","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tri-channel synergistic model for 3D human pose estimation"],"prefix":"10.1371","volume":"21","author":[{"given":"Ying","family":"Gu","sequence":"first","affiliation":[{"name":"Shandong Jianzhu University","place":["Jinan, Shandong Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0398-6958","authenticated-orcid":true,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University","place":["Jinan, Shandong Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shandong Huayun 3D Technology Co., Ltd.","place":["Jinan, Shandong Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University","place":["Jinan, Shandong Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"key":"pone.0359200.ref001","author":"H Kang","year":"2023"},{"issue":"10","key":"pone.0359200.ref002","article-title":"3D human pose estimation via spatial graph order attention and temporal body aware transformer","volume":"20","author":"K Aouaidjia","year":"2025","journal-title":"PLOS ONE"},{"issue":"2","key":"pone.0359200.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0264302","article-title":"LHPE-nets: A lightweight 2D and 3D human pose estimation model with well-structural deep networks and multi-view pose sample simplification method","volume":"17","author":"H Wang","year":"2022","journal-title":"PLoS One"},{"issue":"12","key":"pone.0359200.ref004","article-title":"JMM-TGT: Self-supervised 3D action recognition through joint motion masking and topology-guided transformer","volume":"20","author":"H Wen","year":"2025","journal-title":"PLoS One"},{"key":"pone.0359200.ref005","doi-asserted-by":"crossref","unstructured":"Zheng C, Zhu S, Mendieta M, Yang T, Chen C, Ding Z. 3D human pose estimation with spatial and temporal transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 11636\u201345. https:\/\/doi.org\/10.1109\/iccv48922.2021.01145","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"pone.0359200.ref006","author":"T Wang","year":"2023"},{"key":"pone.0359200.ref007","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","article-title":"Enhanced skeleton visualization for view invariant human action recognition","volume":"68","author":"M Liu","year":"2017","journal-title":"Pattern Recog"},{"key":"pone.0359200.ref008","doi-asserted-by":"crossref","unstructured":"Cai Y, Ge L, Liu J, Cai J, Cham TJ, Yuan J, et al. Exploiting spatial-temporal relationships for 3d pose estimation via GCN. In: Proceedings of the IEEE\/CVF International conference on computer vision. 2019. 2272\u201381.","DOI":"10.1109\/ICCV.2019.00236"},{"key":"pone.0359200.ref009","doi-asserted-by":"crossref","unstructured":"Zou Z, Tang W. Modulated graph convolutional network for 3D human pose estimation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 11457\u201367. https:\/\/doi.org\/10.1109\/iccv48922.2021.01128","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"pone.0359200.ref010","doi-asserted-by":"crossref","unstructured":"Chen Y, Zhang Z, Yuan C, Li B, Deng Y, Hu W. Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 13339\u201348. https:\/\/doi.org\/10.1109\/iccv48922.2021.01311","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"pone.0359200.ref011","unstructured":"Tang W, Liu Y, Ding H, Ding R, Tang W. STCFormer: Spatio-temporal cross transformer for 3d human pose estimation in videos. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2023. 8877\u201386."},{"issue":"1","key":"pone.0359200.ref012","article-title":"Learning pose grammar to encode human body configuration for 3D pose estimation","volume":"32","author":"H-S Fang","year":"2018","journal-title":"AAAI"},{"key":"pone.0359200.ref013","doi-asserted-by":"crossref","unstructured":"Qiu Z, Yao T, Ngo C-W, Mei T. MLP-3D: A MLP-like 3D architecture with grouped time mixing. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). 2022. 3052\u201362. https:\/\/doi.org\/10.1109\/cvpr52688.2022.00307","DOI":"10.1109\/CVPR52688.2022.00307"},{"key":"pone.0359200.ref014","unstructured":"Tolstikhin I, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T, et al. MLP-Mixer: An all-MLP architecture for vision. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. 2021. 12619\u201330."},{"key":"pone.0359200.ref015","doi-asserted-by":"crossref","unstructured":"Liu M, Yuan J. Recognizing human actions as the evolution of pose estimation maps. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. 2018. 1159\u201368. https:\/\/doi.org\/10.1109\/cvpr.2018.00127","DOI":"10.1109\/CVPR.2018.00127"},{"issue":"3","key":"pone.0359200.ref016","article-title":"Robust 3D pose estimation and Parkinson\u2019s disease classification via dual-stage adaptive temporal perception and graph topology modeling network","volume":"21","author":"M Zuo","year":"2026","journal-title":"PLoS One"},{"issue":"1","key":"pone.0359200.ref017","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","volume":"32","author":"S Yan","year":"2018","journal-title":"AAAI"},{"issue":"2","key":"pone.0359200.ref018","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","article-title":"Contextual transformer networks for visual recognition","volume":"45","author":"Y Li","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0359200.ref019","doi-asserted-by":"crossref","unstructured":"Liu R, Shen J, Wang H, Chen C, Cheung S, Asari V. Attention mechanism exploits temporal contexts: Real-time 3D human pose reconstruction. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020. 5063\u201372. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00511","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"pone.0359200.ref020","doi-asserted-by":"crossref","unstructured":"Hassanin M, Khamiss A, Bennamoun M, Boussaid F, Radwan I. Crossformer: Cross spatio-temporal transformer for 3D human pose estimation. 2022. https:\/\/arxiv.org\/abs\/2203.13387","DOI":"10.2139\/ssrn.4213439"},{"key":"pone.0359200.ref021","author":"W Li","year":"2022"},{"issue":"12","key":"pone.0359200.ref022","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0310831","article-title":"TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors","volume":"19","author":"N Ahmed Khan","year":"2024","journal-title":"PLoS One"},{"key":"pone.0359200.ref023","doi-asserted-by":"crossref","unstructured":"Peng Q, Zheng C, Chen C. A dual-augmentor framework for domain generalization in 3D human pose estimation. In: 2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). 2024. 2240\u20139. https:\/\/doi.org\/10.1109\/cvpr52733.2024.00218","DOI":"10.1109\/CVPR52733.2024.00218"},{"issue":"10","key":"pone.0359200.ref024","doi-asserted-by":"crossref","first-page":"8358","DOI":"10.1609\/aaai.v40i10.37785","article-title":"Lifelong domain adaptive 3D human pose estimation","volume":"40","author":"Q Peng","year":"2026","journal-title":"AAAI"},{"key":"pone.0359200.ref025","doi-asserted-by":"crossref","unstructured":"Martinez J, Hossain R, Romero J, Zisserman A. A simple yet effective baseline for 3d human pose estimation. In: Proc. IEEE Int. Conf. Comput. Vis. (ICCV). 2017. 2640\u20139.","DOI":"10.1109\/ICCV.2017.288"},{"issue":"5","key":"pone.0359200.ref026","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1109\/TMM.2018.2818329","article-title":"Depth pooling based large-scale 3-D action recognition with convolutional neural networks","volume":"20","author":"P Wang","year":"2018","journal-title":"IEEE Trans Multimedia"},{"key":"pone.0359200.ref027","doi-asserted-by":"crossref","unstructured":"Xu T, Takano W. Graph stacked hourglass networks for 3D human pose estimation. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 2021. 16100\u20139. https:\/\/doi.org\/10.1109\/cvpr46437.2021.01584","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"pone.0359200.ref028","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16\u00d716 words: Transformers for image recognition at scale. In: Proc. Int. Conf. Learn. Represent. (ICLR). 2021."},{"key":"pone.0359200.ref029","doi-asserted-by":"crossref","unstructured":"Pavllo D, Feichtenhofer C, Grangier D, Auli M. 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). 2019. 7745\u201354. https:\/\/doi.org\/10.1109\/cvpr.2019.00794","DOI":"10.1109\/CVPR.2019.00794"},{"key":"pone.0359200.ref030","first-page":"507","article-title":"SRNet: Improving generalization in 3D human pose estimation with a split-and-recombine approach","author":"A Zeng","year":"2020","journal-title":"Lecture notes in computer science. Springer International Publishing"},{"key":"pone.0359200.ref031","doi-asserted-by":"crossref","unstructured":"Zhao W, Wang W, Tian Y. GraFormer: Graph-oriented transformer for 3D pose estimation. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). 2022. 20406\u201315. https:\/\/doi.org\/10.1109\/cvpr52688.2022.01979","DOI":"10.1109\/CVPR52688.2022.01979"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:38:16Z","timestamp":1792085896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359200"}},"subtitle":[],"editor":[{"given":"Feng","family":"Ding","sequence":"first","affiliation":[{"name":"Nanchang University","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359200","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]}}}