{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:48:08Z","timestamp":1760057288340,"version":"build-2065373602"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07953-w","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:12:44Z","timestamp":1760026364000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An efficient human pose keypoint detection algorithm base on YOLOv8"],"prefix":"10.1007","volume":"81","author":[{"given":"Shengqi","family":"Yang","sequence":"first","affiliation":[]},{"given":"Haiying","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yifeng","family":"Du","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Chaoqun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Lida","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"7953_CR1","doi-asserted-by":"crossref","unstructured":"Bulat A, Tzimiropoulos G (2016) Human pose estimation via convolutional part heatmap regression. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VII 14, Springer, pp 717\u2013732","DOI":"10.1007\/978-3-319-46478-7_44"},{"key":"7953_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111302","volume":"197","author":"H Shang","year":"2022","unstructured":"Shang H, Liu C, Wang R (2022) Measurement methods of 3d shape of large-scale complex surfaces based on computer vision: a review. Measurement 197:111302","journal-title":"Measurement"},{"key":"7953_CR3","doi-asserted-by":"crossref","unstructured":"Wang P, Fu Y, Zhang J, Wang P, Zheng Y, Aggarwal C (2018) You are how you drive: Peer and temporal-aware representation learning for driving behavior analysis. In: 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 2457\u20132466","DOI":"10.1145\/3219819.3219985"},{"key":"7953_CR4","first-page":"1","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1\u20137","journal-title":"Adv Neural Inf Process Syst"},{"issue":"4","key":"7953_CR5","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1109\/TVCG.2012.56","volume":"18","author":"J Tong","year":"2012","unstructured":"Tong J, Zhou J, Liu L, Pan Z, Yan H (2012) Scanning 3d full human bodies using kinects. IEEE Trans Visual Comput Graphics 18(4):643\u2013650","journal-title":"IEEE Trans Visual Comput Graphics"},{"key":"7953_CR6","doi-asserted-by":"crossref","unstructured":"Redmon J (2016) You only look once: Unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u201310","DOI":"10.1109\/CVPR.2016.91"},{"key":"7953_CR7","doi-asserted-by":"crossref","unstructured":"Ragab MG, Abdulkader SJ, Muneer A, Alqushaibi A, Sumiea EH, Qureshi R, Al-Selwi SM, Alhussian H (2024) A comprehensive systematic review of yolo for medical object detection (2018 to 2023). IEEE Access, pp 1\u201322","DOI":"10.1109\/ACCESS.2024.3386826"},{"key":"7953_CR8","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60:91\u2013110","journal-title":"Int J Comput Vision"},{"key":"7953_CR9","doi-asserted-by":"crossref","unstructured":"Bay H (2006) Surf: Speeded up robust features. Computer Vision\u2013ECCV, pp 1\u201314","DOI":"10.1007\/11744023_32"},{"key":"7953_CR10","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), Ieee, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"7953_CR11","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. CoRR abs\/1603.06937:1\u201317","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"7953_CR12","doi-asserted-by":"crossref","unstructured":"Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 5693\u20135703","DOI":"10.1109\/CVPR.2019.00584"},{"key":"7953_CR13","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu Y, Zhang J, Zhang Q, Tao D (2022) Vitpose: simple vision transformer baselines for human pose estimation. Adv Neural Inf Process Syst 35:38571\u201338584","journal-title":"Adv Neural Inf Process Syst"},{"key":"7953_CR14","doi-asserted-by":"crossref","unstructured":"Yang Z, Zeng A, Yuan C, Li Y (2023) Effective whole-body pose estimation with two-stages distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 4210\u20134220","DOI":"10.1109\/ICCVW60793.2023.00455"},{"issue":"1","key":"7953_CR15","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/T-C.1973.223602","volume":"100","author":"MA Fischler","year":"1973","unstructured":"Fischler MA, Elschlager RA (1973) The representation and matching of pictorial structures. IEEE Trans Comput 100(1):67\u201392","journal-title":"IEEE Trans Comput"},{"issue":"9","key":"7953_CR16","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7953_CR17","doi-asserted-by":"crossref","unstructured":"Yang Y, Ramanan D (2011) Articulated pose estimation with flexible mixtures-of-parts. In: CVPR 2011, IEEE, pp 1385\u20131392","DOI":"10.1109\/CVPR.2011.5995741"},{"issue":"6","key":"7953_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275022","volume":"37","author":"T N\u00e4geli","year":"2018","unstructured":"N\u00e4geli T, Oberholzer S, Pl\u00fcss S, Alonso-Mora J, Hilliges O (2018) Flycon: real-time environment-independent multi-view human pose estimation with aerial vehicles. ACM Trans Graphics (TOG) 37(6):1\u201314","journal-title":"ACM Trans Graphics (TOG)"},{"key":"7953_CR19","doi-asserted-by":"crossref","unstructured":"Toshev A, Szegedy C (2014) Deeppose: Human pose estimation via deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1653\u20131660","DOI":"10.1109\/CVPR.2014.214"},{"key":"7953_CR20","doi-asserted-by":"crossref","unstructured":"Wang J, Qiu K, Peng H, Fu J, Zhu J (2019) Ai coach: Deep human pose estimation and analysis for personalized athletic training assistance. In: 27th ACM International Conference on Multimedia, pp 374\u2013382","DOI":"10.1145\/3343031.3350910"},{"key":"7953_CR21","doi-asserted-by":"crossref","unstructured":"Wei SE, Ramakrishna V, Kanade T, Sheikh Y (2016) Convolutional pose machines. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 4724\u20134732","DOI":"10.1109\/CVPR.2016.511"},{"key":"7953_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2021.3103741","volume":"43","author":"Z Cao","year":"2021","unstructured":"Cao Z, Hidalgo G, Simon T, Wei SE, Sheikh Y (2021) Openpose: realtime multi-person 2d pose estimation using part affinity fields. IEEE Trans Pattern Anal Mach Intell 43:1\u201314","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7953_CR23","first-page":"1","volume-title":"Computer Vision and Pattern Recognition","author":"A Farhadi","year":"2018","unstructured":"Farhadi A, Redmon J (2018) Yolov3: an incremental improvement. Computer Vision and Pattern Recognition. Springer, Berlin\/Heidelberg, Germany, pp 1\u20136"},{"key":"7953_CR24","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W et\u00a0al (2022) Yolov6: A single-stage object detection framework for industrial applications. ArXiv Preprint ArXiv:2209.02976, pp 1\u201317"},{"key":"7953_CR25","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM (2023) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"7953_CR26","doi-asserted-by":"crossref","unstructured":"Varghese R, Sambath M (2024) Yolov8: A novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), IEEE, pp 1\u20136","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"7953_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105057","volume":"147","author":"M Kang","year":"2024","unstructured":"Kang M, Ting CM, Ting FF, Phan RCW (2024) Asf-yolo: a novel yolo model with attentional scale sequence fusion for cell instance segmentation. Image Vis Comput 147:105057","journal-title":"Image Vis Comput"},{"key":"7953_CR28","doi-asserted-by":"crossref","unstructured":"Dai Y, Gieseke F, Oehmcke S, Wu Y, Barnard K (2021) Attentional feature fusion. In: EEE\/CVF Winter Conference on Applications of Computer Vision, pp 3560\u20133569","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"7953_CR29","unstructured":"Wang A, Chen H, Liu L, Chen K, Lin Z, Han J, Ding G (2024) Yolov10: Real-time end-to-end object detection. ArXiv Preprint ArXiv:2405.14458, pp 1\u201321"},{"key":"7953_CR30","doi-asserted-by":"crossref","unstructured":"Zhang J, Li X, Li J, Liu L, Xue Z, Zhang B, Jiang Z, Huang T, Wang Y, Wang C (2023) Rethinking mobile block for efficient attention-based models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE Computer Society, pp 1389\u20131400","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"7953_CR31","first-page":"1","volume-title":"ICASSP 2023\u20132023 IEEE International Conference on Acoustics","author":"D Ouyang","year":"2023","unstructured":"Ouyang D, He S, Zhang G, Luo M, Guo H, Zhan J, Huang Z (2023) Efficient multi-scale attention module with cross-spatial learning. ICASSP 2023\u20132023 IEEE International Conference on Acoustics. IEEE, Speech and Signal Processing (ICASSP), pp 1\u20135"},{"key":"7953_CR32","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"7953_CR33","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7953_CR34","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh IH, Mark\u00a0Liao HY (2025) Yolov9: Learning what you want to learn using programmable gradient information. In: European Conference on Computer Vision, Springer, pp 1\u201321","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"7953_CR35","unstructured":"Khanam R, Hussain M (2024) Yolov11: An overview of the key architectural enhancements. ArXiv Preprint ArXiv:2410.17725, pp 1\u20139"},{"key":"7953_CR36","doi-asserted-by":"crossref","unstructured":"Li J, Wang C, Zhu H, Mao Y, Fang HS, Lu C (2019) Crowdpose: Efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 10863\u201310872","DOI":"10.1109\/CVPR.2019.01112"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07953-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07953-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07953-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:13:01Z","timestamp":1760026381000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07953-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":36,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["7953"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07953-w","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"22 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This research was funded by the National Natural Science Foundation of China, Nos. 62473232, U2006222 and the Innovation Ability Enhancement Project of Shandong Province Science and Technology Small Medium Enterprise, No. 2023TSCG0159.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Funding"}},{"value":"The authors declare no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The data used in this article comply with ethical requirements, and informed consent is not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}],"article-number":"1431"}}