{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T04:08:04Z","timestamp":1750910884394,"version":"3.41.0"},"reference-count":68,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011789","name":"Department of Science and Technology of Jilin Province","doi-asserted-by":"publisher","award":["20240101345JC"],"award-info":[{"award-number":["20240101345JC"]}],"id":[{"id":"10.13039\/501100011789","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Human pose estimation (HPE) has made significant progress with deep learning; however, it still faces challenges in handling occlusions, complex poses, and complex multi-person scenarios. To address these issues, we propose PoseNet++, a novel approach based on a 3-stacked hourglass architecture, incorporating three key innovations: the multi-scale spatial pyramid attention hourglass module (MSPAHM), coordinate-channel prior convolutional attention (C-CPCA), and the PinSK Bottleneck Residual Module (PBRM). MSPAHM enhances long-range channel dependencies, enabling the model to better capture structural relationships between limb joints, particularly under occlusion. C-CPCA combines coordinate attention (CA) and channel prior convolutional attention (CPCA) to prioritize keypoints\u2019 regions and reduce the confusion in complex multi-person scenarios. The PBRM improves pose estimation accuracy by optimizing the receptive field and convolutional kernel selection, thus enhancing the network\u2019s feature extraction capabilities in multi-scale and complex poses. On the MPII validation set, PoseNet++\u2009improves the PCKh score by 3.3% relative to the baseline 3-stacked hourglass network, while reducing the number of model parameters and the number of floating-point operations by 60.3% and 53.1%, respectively. Compared with other mainstream human pose estimation models in recent years, PoseNet++\u2009achieves the state-of-the-art performance on the MPII, LSP, COCO and CrowdPose datasets. At the same time, the model complexity of PoseNet++\u2009is much lower than that of methods with similar accuracy.<\/jats:p>","DOI":"10.1371\/journal.pone.0326232","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T17:49:50Z","timestamp":1750873790000},"page":"e0326232","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["PoseNet++: A multi-scale and optimized feature extraction network for high-precision human pose estimation"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2784-1018","authenticated-orcid":true,"given":"Chao","family":"Lv","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geyao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"issue":"5","key":"pone.0326232.ref001","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","article-title":"Human Action Recognition and Prediction: A Survey","volume":"130","author":"Y Kong","year":"2022","journal-title":"Int J Comput Vis"},{"key":"pone.0326232.ref002","first-page":"2030","article-title":"Recognizing human actions from still images with latent poses. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition;","volume":"2010","author":"W Yang"},{"issue":"9","key":"pone.0326232.ref003","doi-asserted-by":"crossref","first-page":"4500","DOI":"10.1109\/TIP.2019.2910414","article-title":"Pose-invariant embedding for deep person re-identification","volume":"28","author":"L Zheng","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"pone.0326232.ref004","first-page":"483","volume-title":"Stacked hourglass networks for human pose estimation. In: Proceedings of the European Conference on Computer Vision","author":"A Newell","year":"2016"},{"key":"pone.0326232.ref005","first-page":"717","volume-title":"Human pose estimation via convolutional part heatmap regression. In: Proceedings of the European Conference on Computer Vision","author":"A Bulat","year":"2016"},{"key":"pone.0326232.ref006","first-page":"1653","article-title":"Deeppose: Human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;","author":"A Toshev","year":"2014"},{"key":"pone.0326232.ref007","first-page":"4724","article-title":"Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;","author":"SE Wei","year":"2016"},{"key":"pone.0326232.ref008","first-page":"648","article-title":"Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;","author":"J Tompson","year":"2015"},{"key":"pone.0326232.ref009","first-page":"79","volume-title":"Stacked hourglass network for robust facial landmark localisation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"J Yang","year":"2017"},{"key":"pone.0326232.ref010","doi-asserted-by":"crossref","first-page":"108784","DOI":"10.1016\/j.compbiomed.2024.108784","article-title":"Channel prior convolutional attention for medical image segmentation","volume":"178","author":"H Huang","year":"2024","journal-title":"Comput Biol Med"},{"key":"pone.0326232.ref011","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"Q Hou","year":"2021"},{"key":"pone.0326232.ref012","doi-asserted-by":"crossref","first-page":"108261","DOI":"10.1016\/j.engappai.2024.108261","article-title":"Multi-scale spatial pyramid attention mechanism for image recognition: An effective approach","volume":"133","author":"Y Yu","year":"2024","journal-title":"Eng Appl Art Intell"},{"issue":"9","key":"pone.0326232.ref013","doi-asserted-by":"crossref","first-page":"9202","DOI":"10.1609\/aaai.v39i9.32996","article-title":"Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection","volume":"39","author":"J Yang","year":"2025","journal-title":"AAAI"},{"key":"pone.0326232.ref014","first-page":"510","article-title":"Selective kernel networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"X Li","year":"2019"},{"key":"pone.0326232.ref015","first-page":"3686","article-title":"2d human pose estimation: New benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;","author":"M Andriluka","year":"2014"},{"key":"pone.0326232.ref016","first-page":"5","volume-title":"Clustered pose and nonlinear appearance models for human pose estimation. In: Proceedings of the British Machine Vision Conference","author":"S Johnson","year":"2010"},{"key":"pone.0326232.ref017","first-page":"740","volume-title":"Microsoft coco: Common objects in context. In: Proceedings of the European Conference on Computer Vision","author":"TY Lin","year":"2014"},{"key":"pone.0326232.ref018","first-page":"10863","article-title":"Crowdpose: Efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"J Li","year":"2019"},{"key":"pone.0326232.ref019","first-page":"1014","article-title":"Pictorial structures revisited: People detection and articulated pose estimation. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition;","author":"M Andriluka","year":"2009"},{"key":"pone.0326232.ref020","first-page":"623","article-title":"Monocular 3d pose estimation and tracking by detection. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition;","author":"M Andriluka","year":"2010"},{"issue":"6","key":"pone.0326232.ref021","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1049\/iet-cvi.2016.0249","article-title":"Mixing body\u2010parts model for 2D human pose estimation in stereo videos","volume":"11","author":"MI L\u00f3pez\u2010Quintero","year":"2017","journal-title":"IET Computer Vision"},{"key":"pone.0326232.ref022","first-page":"886","article-title":"Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition;","author":"N Dalal","year":"2005"},{"issue":"5","key":"pone.0326232.ref023","doi-asserted-by":"crossref","first-page":"3115","DOI":"10.1007\/s00530-022-01019-0","article-title":"2D Human pose estimation: a survey","volume":"29","author":"H Chen","year":"2022","journal-title":"Multimedia Systems"},{"key":"pone.0326232.ref024","first-page":"7291","article-title":"Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;","author":"Z Cao","year":"2017"},{"key":"pone.0326232.ref025","first-page":"7103","article-title":"Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;","author":"Y Chen","year":"2018"},{"key":"pone.0326232.ref026","first-page":"5386","article-title":"Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"B Cheng","year":"2020"},{"key":"pone.0326232.ref027","article-title":"SPCNet: spatial preserve and content-aware network for human pose estimation In: european conference on artificial intelligence","volume-title":"Front Artificial Intell Applications","author":"Yabo Xiao","year":"2020"},{"issue":"4","key":"pone.0326232.ref028","article-title":"Multipath affinage stacked\u2014hourglass networks for human pose estimation","volume":"14","author":"G Hua","year":"2020","journal-title":"Front Comput Sci"},{"issue":"22","key":"pone.0326232.ref029","doi-asserted-by":"crossref","first-page":"10143","DOI":"10.3390\/app142210143","article-title":"SMS-Net: Bridging the Gap Between High Accuracy and Low Computational Cost in Pose Estimation","volume":"14","author":"W-J Noh","year":"2024","journal-title":"Appl Sci"},{"key":"pone.0326232.ref030","first-page":"192","volume-title":"Two-stream framework for activity recognition with 2d human pose estimation. In: International Conference on Image Analysis and Recognition","author":"W Chang","year":"2020"},{"key":"pone.0326232.ref031","first-page":"7132","article-title":"Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and","author":"J Hu","year":"2018","journal-title":"Pattern Recognition"},{"key":"pone.0326232.ref032","first-page":"3","volume-title":"Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision","author":"S Woo","year":"2018"},{"key":"pone.0326232.ref033","first-page":"1281","volume-title":"Learning feature pyramids for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision","author":"W Yang","year":"2017"},{"key":"pone.0326232.ref034","first-page":"197","article-title":"Deeply Learned compositional models for human pose estimation","volume-title":"Lecture Notes in Computer Science","author":"W Tang","year":"2018"},{"key":"pone.0326232.ref035","first-page":"7093","article-title":"Distribution-aware coordinate representation for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"F Zhang","year":"2020"},{"key":"pone.0326232.ref036","first-page":"5992","volume-title":"Anchor loss: Modulating loss scale based on prediction difficulty. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"S Ryou","year":"2019"},{"key":"pone.0326232.ref037","first-page":"5693","article-title":"Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"K Sun","year":"2019"},{"key":"pone.0326232.ref038","doi-asserted-by":"crossref","first-page":"107410","DOI":"10.1016\/j.patcog.2020.107410","article-title":"Structure-aware human pose estimation with graph convolutional networks","volume":"106","author":"Y Bin","year":"2020","journal-title":"Pattern Recognition"},{"key":"pone.0326232.ref039","first-page":"5700","article-title":"The devil is in the details: Delving into unbiased data processing for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition;","author":"J Huang","year":"2020"},{"key":"pone.0326232.ref040","first-page":"11313","volume-title":"Tokenpose: Learning keypoint tokens for human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Y Li","year":"2021"},{"issue":"6","key":"pone.0326232.ref041","doi-asserted-by":"crossref","first-page":"2827","DOI":"10.1109\/TPAMI.2021.3049156","article-title":"Cascaded parsing of human-object interaction recognition","volume":"44","author":"T Zhou","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0326232.ref042","doi-asserted-by":"crossref","first-page":"107863","DOI":"10.1016\/j.patcog.2021.107863","article-title":"An adversarial human pose estimation network injected with graph structure","volume":"115","author":"L Tian","year":"2021","journal-title":"Pattern Recognition"},{"key":"pone.0326232.ref043","first-page":"89","volume-title":"Simcc: A simple coordinate classification perspective for human pose estimation. In: Proceedings of the European Conference on Computer Vision","author":"Y Li","year":"2022"},{"key":"pone.0326232.ref044","doi-asserted-by":"crossref","first-page":"156702","DOI":"10.1109\/ACCESS.2024.3446247","article-title":"EdgePose: Real-Time Human Pose Estimation Scheme for Industrial Scenes","volume":"12","author":"L Zhang","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0326232.ref045","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.cag.2019.09.002","article-title":"Human pose regression by combining indirect part detection and contextual information","volume":"85","author":"DC Luvizon","year":"2019","journal-title":"Computers Graphics"},{"issue":"5","key":"pone.0326232.ref046","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1007\/s00530-021-00755-z","article-title":"Body parts relevance learning via expectation\u2013maximization for human pose estimation","volume":"27","author":"L Yue","year":"2021","journal-title":"Multimedia Systems"},{"issue":"4","key":"pone.0326232.ref047","doi-asserted-by":"crossref","first-page":"2853","DOI":"10.1007\/s11063-021-10523-9","article-title":"Attention Refined Network for Human Pose Estimation","volume":"53","author":"X Wang","year":"2021","journal-title":"Neural Process Lett"},{"issue":"7","key":"pone.0326232.ref048","doi-asserted-by":"crossref","first-page":"9521","DOI":"10.1007\/s11063-023-11212-5","article-title":"Improving Human Pose Estimation Based on Stacked Hourglass Network","volume":"55","author":"X Zou","year":"2023","journal-title":"Neural Process Lett"},{"key":"pone.0326232.ref049","doi-asserted-by":"crossref","first-page":"128318","DOI":"10.1016\/j.neucom.2024.128318","article-title":"Human pose estimation based on frequency domain and attention module","volume":"604","author":"S Zhou","year":"2024","journal-title":"Neurocomputing"},{"issue":"12","key":"pone.0326232.ref050","doi-asserted-by":"crossref","first-page":"12692","DOI":"10.1109\/TCSVT.2024.3435014","article-title":"Human Pose Estimation via Parse Graph of Body Structure","volume":"34","author":"S Liu","year":"2024","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"pone.0326232.ref051","first-page":"468","volume-title":"Recurrent human pose estimation. In: 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition","author":"V Belagiannis","year":"2017"},{"key":"pone.0326232.ref052","first-page":"1831","article-title":"Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and","author":"X Chu","year":"2017","journal-title":"Pattern Recognition"},{"issue":"5","key":"pone.0326232.ref053","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1109\/TMM.2017.2762010","article-title":"Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation","volume":"20","author":"G Ning","year":"2018","journal-title":"IEEE Trans Multimedia"},{"key":"pone.0326232.ref054","first-page":"17","volume-title":"Self adversarial training for human pose estimation. In: 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","author":"CJ Chou","year":"2018"},{"key":"pone.0326232.ref055","first-page":"1","volume-title":"A feature aggregation hourglass network for human pose estimation. In: 2021 International Joint Conference on Neural Networks","author":"F Lu","year":"2021"},{"key":"pone.0326232.ref056","first-page":"396","volume-title":"Occlusion-aware siamese network for human pose estimation. In: Proceedings of the European Conference on Computer Vision","author":"L Zhou","year":"2020"},{"issue":"3","key":"pone.0326232.ref057","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1007\/s11760-022-02271-7","article-title":"Human pose estimation based on feature enhancement and multi-scale feature fusion","volume":"17","author":"D Cao","year":"2022","journal-title":"SIViP"},{"issue":"5","key":"pone.0326232.ref058","doi-asserted-by":"crossref","first-page":"2005","DOI":"10.1007\/s00371-022-02460-y","article-title":"MSPENet: multi-scale adaptive fusion and position enhancement network for human pose estimation","volume":"39","author":"J Xu","year":"2022","journal-title":"Vis Comput"},{"issue":"9","key":"pone.0326232.ref059","doi-asserted-by":"crossref","first-page":"4425","DOI":"10.3390\/s23094425","article-title":"HPnet: Hybrid Parallel Network for Human Pose Estimation","volume":"23","author":"H Li","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"2","key":"pone.0326232.ref060","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.1007\/s10489-022-03623-z","article-title":"Decision-level information fusion powered human pose estimation","volume":"53","author":"Y Zhang","year":"2022","journal-title":"Appl Intell"},{"issue":"1","key":"pone.0326232.ref061","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s00371-021-02317-w","article-title":"Human pose estimation with gated multi-scale feature fusion and spatial mutual information","volume":"39","author":"X Zhao","year":"2021","journal-title":"Vis Comput"},{"key":"pone.0326232.ref062","article-title":"Rtmpose: Real-time multi-person pose estimation based on mmpose","author":"T Jiang","year":"2025","journal-title":"arXiv"},{"issue":"4","key":"pone.0326232.ref063","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.1109\/TCSVT.2020.3005522","article-title":"Learning to Acquire the Quality of Human Pose Estimation","volume":"31","author":"L Zhao","year":"2021","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"2","key":"pone.0326232.ref064","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"K He","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0326232.ref065","doi-asserted-by":"crossref","unstructured":"Fang H-S, Xie S, Tai Y-W, Lu C. RMPE: Regional Multi-person Pose Estimation. In: 2017 IEEE International Conference on Computer Vision (ICCV), 2017. 2353\u201362. doi: 10.1109\/iccv.2017.256","DOI":"10.1109\/ICCV.2017.256"},{"key":"pone.0326232.ref066","article-title":"Optimizing human pose estimation through focused human and joint regions","author":"Y Jiao","year":"2025","journal-title":"arXiv"},{"issue":"1","key":"pone.0326232.ref067","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0316536","article-title":"Dual-hybrid intrusion detection system to detect False Data Injection in smart grids","volume":"20","author":"SH Mohammed","year":"2025","journal-title":"PLoS One"},{"issue":"2","key":"pone.0326232.ref068","doi-asserted-by":"crossref","first-page":"2271","DOI":"10.11591\/ijece.v15i2.pp2271-2281","article-title":"Advancing network security: a comparative research of machine learning techniques for intrusion detection","volume":"15","author":"S Rysbekov","year":"2025","journal-title":"IJECE"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T17:50:11Z","timestamp":1750873811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326232"}},"subtitle":[],"editor":[{"given":"Sushank","family":"Chaudhary","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,25]]},"references-count":68,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0326232","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,25]]}}}