{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T12:20:35Z","timestamp":1770985235114,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T00:00:00Z","timestamp":1756512000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T00:00:00Z","timestamp":1756512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"This work was funded by Xiamen Science and Technology Plan Projects - Industry-University-Research Collaboration Projects","award":["2024CXY0435"],"award-info":[{"award-number":["2024CXY0435"]}]},{"name":"This work was funded by Xiamen Science and Technology Plan Projects - Industry-University-Research Collaboration Projects","award":["2023CXY0416"],"award-info":[{"award-number":["2023CXY0416"]}]},{"name":"Fujian Provincial Department of Education Project - Young and Middle-aged Teacher Education Project","award":["JAT200455"],"award-info":[{"award-number":["JAT200455"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"DOI":"10.1007\/s44163-025-00492-6","type":"journal-article","created":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T03:26:36Z","timestamp":1756524396000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A human location and action recognition method based on improved Yolov11 model"],"prefix":"10.1007","volume":"5","author":[{"given":"Shunyi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yongkang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Hanqing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Cai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,30]]},"reference":[{"key":"492_CR1","doi-asserted-by":"publisher","unstructured":"Zou ZX, Chen KY, Shi ZW, et al. Object detection in 20 years: a survey. 2019. arXiv https:\/\/doi.org\/10.48550\/arXiv.1905.05055","DOI":"10.48550\/arXiv.1905.05055"},{"key":"492_CR2","volume-title":"Image processing, analysis and machine vision","author":"M Sonka","year":"2013","unstructured":"Sonka M, Hlavac V, Boyle R. Image processing, analysis and machine vision. 4th ed. London: Springer; 2013.","edition":"4"},{"key":"492_CR3","doi-asserted-by":"publisher","unstructured":"Khanam R, Hussain M. What is YOLOv5: a deep look into the internal features of the popular object detector. 2024. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2207.02696","DOI":"10.48550\/arXiv.2207.02696"},{"key":"492_CR4","doi-asserted-by":"publisher","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. 2022. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2407.20892","DOI":"10.48550\/arXiv.2407.20892"},{"key":"492_CR5","doi-asserted-by":"publisher","unstructured":"Yaseen M, Najjaran H. What is YOLOv8: an in-depth exploration of the internal features of the next-generation object detector. 2024. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2408.15857S","DOI":"10.48550\/arXiv.2408.15857S"},{"key":"492_CR6","doi-asserted-by":"publisher","unstructured":"Ridnik T, Sharir G, Ben-Cohen A, Ben-Baruch E, Noy A. ML-decoder: scalable and versatile classification head. https:\/\/doi.org\/10.48550\/arXiv.2111.12933","DOI":"10.48550\/arXiv.2111.12933"},{"key":"492_CR7","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need. 2017. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"492_CR8","doi-asserted-by":"publisher","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS. CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision. Springer; 2018. pp. 3\u201319. https:\/\/doi.org\/10.48550\/arXiv.1807.06521.","DOI":"10.48550\/arXiv.1807.06521"},{"key":"492_CR9","doi-asserted-by":"publisher","unstructured":"Yang F, Wang T. SCB-Dataset3: a benchmark for detecting student classroom behaviour. Zenodo. 2023. https:\/\/doi.org\/10.48550\/arXiv.2310.02522","DOI":"10.48550\/arXiv.2310.02522"},{"key":"492_CR10","doi-asserted-by":"publisher","unstructured":"Wang CX, Jin Z. Brighten-and-Colorize: a decoupled network for customized low-light image enhancement. 2023. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2308.03029","DOI":"10.48550\/arXiv.2308.03029"},{"issue":"9","key":"492_CR11","doi-asserted-by":"publisher","first-page":"63280","DOI":"10.48550\/arXiv.2011.00241","volume":"10","author":"S Vadera","year":"2020","unstructured":"Vadera S, Ameen S. Methods for pruning deep neural networks. IEEE Access. 2020;10(9):63280\u2013300. https:\/\/doi.org\/10.48550\/arXiv.2011.00241.","journal-title":"IEEE Access"},{"issue":"3","key":"492_CR12","first-page":"905","volume":"17","author":"P Seint","year":"2021","unstructured":"Seint P, Zin T, Tin P. Intelligent monitoring for elder care using vision-based technology. Int J Innov Comput Inf Control. 2021;17(3):905\u201318.","journal-title":"Int J Innov Comput Inf Control"},{"issue":"10","key":"492_CR13","doi-asserted-by":"publisher","first-page":"3013","DOI":"10.3390\/s25103013","volume":"25","author":"N Alzahrani","year":"2025","unstructured":"Alzahrani N, Bchir O, Ismail MMB. YOLO-act: unified spatiotemporal detection of human actions across multi-frame sequences. Sensors. 2025;25(10):3013. https:\/\/doi.org\/10.3390\/s25103013.","journal-title":"Sensors"},{"key":"492_CR14","doi-asserted-by":"publisher","first-page":"109090","DOI":"10.48550\/arXiv.2401.10379","volume":"223","author":"CM Badgujar","year":"2024","unstructured":"Badgujar CM, Poulose A, Gan H. Agricultural object detection with you look only once (yolo) algorithm: a bibliometric and systematic literature review. Comput Electron Agric. 2024;223:109090. https:\/\/doi.org\/10.48550\/arXiv.2401.10379.","journal-title":"Comput Electron Agric"},{"issue":"35","key":"492_CR15","doi-asserted-by":"publisher","first-page":"83535","DOI":"10.1007\/s11042-024-17615-9","volume":"83","author":"A Vijayakumar","year":"2024","unstructured":"Vijayakumar A, Vairavasundaram S. Yolo-based object detection models: a review and its applications. Multimed Tools Appl. 2024;83(35):83535\u201374. https:\/\/doi.org\/10.1007\/s11042-024-17615-9.","journal-title":"Multimed Tools Appl"},{"key":"492_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3380212","author":"MMA Parambil","year":"2024","unstructured":"Parambil MMA, Ali L, Swavaf M, Bouktif S, Gochoo M, Aljassmi H, Alnajjar F. Navigating the yolo landscape: a comparative study of object detection models for emotion recognition. IEEE Access. 2024. https:\/\/doi.org\/10.1109\/ACCESS.2024.3380212.","journal-title":"IEEE Access"},{"issue":"19","key":"492_CR17","doi-asserted-by":"publisher","first-page":"8982","DOI":"10.1007\/s10489-023-05363-2","volume":"54","author":"FX Gaya-Morey","year":"2024","unstructured":"Gaya-Morey FX, Manresa-Yee C, Buades-Rubio JM. Deep learning for computer vision based activity recognition and fall detection of the elderly: a systematic review. Appl Intell. 2024;54(19):8982\u20139007. https:\/\/doi.org\/10.1007\/s10489-023-05363-2.","journal-title":"Appl Intell"},{"key":"492_CR18","doi-asserted-by":"publisher","unstructured":"Sitaraman SR, Narayana MVS, Lande J, Shnain AH. Center intersection of union loss with you only look once for object detection and recognition. In: 2024 international conference on intelligent algorithms for computational intelligence systems (IACIS). IEEE; 2024. pp. 1\u20134. https:\/\/doi.org\/10.1109\/IACIS60239.2024.10451234.","DOI":"10.1109\/IACIS60239.2024.10451234"},{"key":"492_CR19","doi-asserted-by":"publisher","unstructured":"Gudivaka RK, Hussein L, Aruna TM, Bharattej RRVSS, Kumar PM. Cloud based early acute lymphoblastic Leukemia detection using deep learning based improved YOLOv4. 2024 second international conference on data science and information system (ICDSIS). IEEE; 2024. pp. 1\u20134. https:\/\/doi.org\/10.1109\/ICDSIS60322.2024.10458391.","DOI":"10.1109\/ICDSIS60322.2024.10458391"},{"issue":"3","key":"492_CR20","doi-asserted-by":"publisher","first-page":"912","DOI":"10.5281\/zenodo.10876543","volume":"12","author":"DKR Basani","year":"2024","unstructured":"Basani DKR. Robotic process automation in IoT: enhancing object localization using YOLOv3-based class algorithms. Int J Inf Technol Comput Eng. 2024;12(3):912\u201327. https:\/\/doi.org\/10.5281\/zenodo.10876543.","journal-title":"Int J Inf Technol Comput Eng"},{"key":"492_CR21","doi-asserted-by":"publisher","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B. High-resolution image synthesis with latent diffusion models. Ludwig Maximilian University of Munich & IWR, Heidelberg University, Germany. 2021. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2112.10752","DOI":"10.48550\/arXiv.2112.10752"},{"key":"492_CR22","doi-asserted-by":"publisher","unstructured":"Kim Y. Convolutional neural networks for sentence classification. 2014. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1408.5882","DOI":"10.48550\/arXiv.1408.5882"},{"key":"492_CR23","doi-asserted-by":"publisher","unstructured":"Khanam R, Hussain M. YOLOv11: an overview of the key architectural enhancements. 2024. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2410.17725","DOI":"10.48550\/arXiv.2410.17725"},{"key":"492_CR24","doi-asserted-by":"publisher","unstructured":"Wang C-Y, Liao H-YM, Yeh I-H, Wu Y-H, Chen P-Y, Hsieh J-W. CSPNet: a new backbone that can enhance the learning capability of CNN. 2019. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1911.11929","DOI":"10.48550\/arXiv.1911.11929"},{"key":"492_CR25","doi-asserted-by":"publisher","unstructured":"Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design. 2021. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2103.02907","DOI":"10.48550\/arXiv.2103.02907"},{"key":"492_CR26","doi-asserted-by":"publisher","unstructured":"Sun Y, Chen G, Zhou T, Zhang Y, Liu N. Context-aware cross-level fusion network for camouflaged object detection. 2021. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2105.12555","DOI":"10.48550\/arXiv.2105.12555"},{"key":"492_CR27","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I. Attention is all you need. In: Advances in neural information processing systems, vol 30. 2017. https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"492_CR28","doi-asserted-by":"publisher","unstructured":"Sun Y, Dong L, Huang S, Ma S, Xia Y, Xue J, Wei F. Retentive network: a successor to transformer for large language models. 2015. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1512.03385","DOI":"10.48550\/arXiv.1512.03385"},{"key":"492_CR29","doi-asserted-by":"publisher","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J. Path aggregation network for instance segmentation. 2018. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1803.01534","DOI":"10.48550\/arXiv.1803.01534"},{"key":"492_CR30","doi-asserted-by":"publisher","unstructured":"Chollet F. Xception: deep learning with depth wise separable convolutions. 2016. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1610.02357","DOI":"10.48550\/arXiv.1610.02357"},{"key":"492_CR31","doi-asserted-by":"publisher","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q. ECA-Net: efficient channel attention for deep convolutional neural networks. 2019. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1910.03151","DOI":"10.48550\/arXiv.1910.03151"},{"key":"492_CR32","doi-asserted-by":"publisher","unstructured":"Jaderberg M, Simonyan K, Zisserman A. Spatial transformer networks. 2015. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1506.02025","DOI":"10.48550\/arXiv.1506.02025"},{"key":"492_CR33","doi-asserted-by":"publisher","first-page":"24261","DOI":"10.48550\/arXiv.2105.01601","volume":"34","author":"I Tolstikhin","year":"2021","unstructured":"Tolstikhin I, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T, Dosovitskiy A. MLP-Mixer: an all-MLP architecture for vision. Adv Neural Inf Process Syst. 2021;34:24261\u201372. https:\/\/doi.org\/10.48550\/arXiv.2105.01601.","journal-title":"Adv Neural Inf Process Syst"},{"key":"492_CR34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.48550\/arXiv.1702.03118","volume":"107","author":"S Elfwing","year":"2017","unstructured":"Elfwing S, Uchibe E, Doya K. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 2017;107:3\u201311. https:\/\/doi.org\/10.48550\/arXiv.1702.03118.","journal-title":"Neural Netw"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00492-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-025-00492-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00492-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T03:26:42Z","timestamp":1756524402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-025-00492-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,30]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["492"],"URL":"https:\/\/doi.org\/10.1007\/s44163-025-00492-6","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,30]]},"assertion":[{"value":"25 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"232"}}