{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T22:20:51Z","timestamp":1769984451679,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"The science and technology innovation Program of Hunan Province","award":["2022RC3013"],"award-info":[{"award-number":["2022RC3013"]}]},{"name":"National Key Research and Development Program of China","award":["2025YFC2511600"],"award-info":[{"award-number":["2025YFC2511600"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Health Inf Sci Syst"],"DOI":"10.1007\/s13755-025-00422-x","type":"journal-article","created":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T09:01:57Z","timestamp":1769936517000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pose2met: a unified spatiotemporal framework for 3D human pose estimation and energy expenditure estimation"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9427-1126","authenticated-orcid":false,"given":"Zhongteng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2471-6147","authenticated-orcid":false,"given":"Liu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9767-1671","authenticated-orcid":false,"given":"Qing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7168-4943","authenticated-orcid":false,"given":"Weihong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,1]]},"reference":[{"issue":"10","key":"422_CR1","doi-asserted-by":"publisher","first-page":"575","DOI":"10.4330\/wjc.v8.i10.575","volume":"8","author":"AJ Alves","year":"2016","unstructured":"Alves AJ, Viana JL, Cavalcante SL, Oliveira NL, Duarte JA, Mota J, et al. Physical activity in primary and secondary prevention of cardiovascular disease: Overview updated. World J Cardiol. 2016;8(10):575.","journal-title":"World J Cardiol."},{"key":"422_CR2","doi-asserted-by":"crossref","unstructured":"Cai Y, G, L, Liu J, Cai J, Cham TJ, Yuan J, Thalmann NM. Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). pp 2272\u20132281 (Oct 2019). DOI: https:\/\/doi.org\/10\/ghfh88, iSSN: 2380-7504.","DOI":"10.1109\/ICCV.2019.00236"},{"key":"422_CR3","doi-asserted-by":"crossref","unstructured":"Ci H, Wang C, Ma X, Wang Y. Optimizing Network Structure for 3D Human Pose Estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). pp 2262\u20132271 (Oct 2019). DOI: https:\/\/doi.org\/10\/ghfjcs, iSSN: 2380-7504.","DOI":"10.1109\/ICCV.2019.00235"},{"key":"422_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105381","volume":"87","author":"VMP Cortes","year":"2024","unstructured":"Cortes VMP, Chatterjee A, Khovalyg D. Dynamic personalized human body energy expenditure: prediction using time series forecasting LSTM models. Biomed Signal Process Control. 2024;87:105381.","journal-title":"Biomed Signal Process Control."},{"key":"422_CR5","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s00421-020-04514-2","volume":"121","author":"JP DeBlois","year":"2021","unstructured":"DeBlois JP, White LE, Barreira TV. Reliability and validity of the COSMED K5 portable metabolic system during walking. Eur J Appl Physiol. 2021;121:209\u201317.","journal-title":"Eur J Appl Physiol."},{"key":"422_CR6","doi-asserted-by":"crossref","unstructured":"Gong J, Foo LG, Fan Z, Ke Q, Rahmani H, Liu J. DiffPose: toward More Reliable 3D Pose Estimation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp 13041\u201313051 (2023). DOI: https:\/\/doi.org\/10\/gtx6kr. https:\/\/ieeexplore.ieee.org\/document\/10203375, iSSN: 2575-7075.","DOI":"10.1109\/CVPR52729.2023.01253"},{"issue":"12","key":"422_CR7","doi-asserted-by":"publisher","first-page":"243","DOI":"10.4239\/wjd.v7.i12.243","volume":"7","author":"H Hamasaki","year":"2016","unstructured":"Hamasaki H. Daily physical activity and type 2 diabetes: a review. World J Diabet. 2016;7(12):243.","journal-title":"World J Diabet"},{"key":"422_CR8","doi-asserted-by":"crossref","unstructured":"Hu W, Zhang C, Zhan F, Zhang L, Wong TT. Conditional Directed Graph Convolution for 3D Human Pose Estimation. In: Proceedings of the 29th ACM International Conference on Multimedia. pp 602\u2013611. ACM, Virtual Event China (2021). DOI: https:\/\/doi.org\/10\/grw552. https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475219.","DOI":"10.1145\/3474085.3475219"},{"issue":"3","key":"422_CR9","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.cbpa.2010.04.013","volume":"158","author":"KJ Kaiyala","year":"2011","unstructured":"Kaiyala KJ, Ramsay DS. Direct animal calorimetry, the underused gold standard for quantifying the fire of life. Comp Biochem Physiol A Mol Integr Physiol. 2011;158(3):252\u201364.","journal-title":"Comp Biochem Physiol A Mol Integr Physiol."},{"key":"422_CR10","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1007\/s00421-017-3670-5","volume":"117","author":"GP Kenny","year":"2017","unstructured":"Kenny GP, Notley SR, Gagnon D. Direct calorimetry: a brief historical review of its use in the study of human metabolism and thermoregulation. Eur J Appl Physiol. 2017;117:1765\u201385.","journal-title":"Eur J Appl Physiol."},{"key":"422_CR11","doi-asserted-by":"crossref","unstructured":"Li W, Liu H, Ding R, Liu M, Wang P, Yang W. Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation. IEEE Transactions on Multimedia 2022:pp 1\u20131. DOI: https:\/\/doi.org\/10\/gpvwhc, conference Name: IEEE Transactions on Multimedia.","DOI":"10.1109\/TMM.2022.3141231"},{"key":"422_CR12","doi-asserted-by":"crossref","unstructured":"Li W, Liu H, Tang H, Wang P, Van Gool L. Mhformer: multi-hypothesis transformer for 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2022:13147\u201356.","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"422_CR13","doi-asserted-by":"crossref","unstructured":"Liu K, Zou Z, Tang W. Learning global pose features in graph convolutional networks for 3d human pose estimation. In: Proceedings of the Asian conference on computer vision; 2020.","DOI":"10.1007\/978-3-030-69525-5_6"},{"issue":"3","key":"422_CR14","doi-asserted-by":"publisher","first-page":"787","DOI":"10.5114\/biolsport.2023.119986","volume":"40","author":"D Martinho","year":"2023","unstructured":"Martinho D, Naughton R, Faria A, Rebelo A, Sarmento H. Predicting resting energy expenditure among athletes: a systematic review. Biol Sport. 2023;40(3):787\u2013804.","journal-title":"Biol Sport"},{"key":"422_CR15","doi-asserted-by":"crossref","unstructured":"Mehraban S, Adeli V, Taati, B. Motionagformer: enhancing 3d human pose estimation with a transformer-gcnformer network. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision 2024:6920\u201330.","DOI":"10.1109\/WACV57701.2024.00677"},{"key":"422_CR16","doi-asserted-by":"crossref","unstructured":"Nakamura K, Yeung S, Alahi A, Fei-Fei L. Jointly learning energy expenditures and activities using egocentric multimodal signals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017:1868\u201377.","DOI":"10.1109\/CVPR.2017.721"},{"issue":"5","key":"422_CR17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0127113","volume":"10","author":"D Nathan","year":"2015","unstructured":"Nathan D, Huynh DQ, Rubenson J, Rosenberg M. Estimating physical activity energy expenditure with the kinect sensor in an exergaming environment. PLoS ONE. 2015;10(5):e0127113.","journal-title":"PLoS ONE"},{"key":"422_CR18","doi-asserted-by":"crossref","unstructured":"Peng J, Zhou Y, Mok, P. Ktpformer: Kinematics and trajectory prior knowledge-enhanced transformer for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2024:1123\u201332.","DOI":"10.1109\/CVPR52733.2024.00113"},{"key":"422_CR19","doi-asserted-by":"crossref","unstructured":"Peng K, Roitberg A, Yang K, Zhang J, Stiefelhagen R. Should I take a walk? Estimating energy expenditure from video data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2022:2075\u201385.","DOI":"10.1109\/CVPRW56347.2022.00225"},{"key":"422_CR20","doi-asserted-by":"crossref","unstructured":"Shan W, Liu Z, Zhang X, Wang S, Ma S, Gao W. P-stmo: pre-trained spatial temporal many-to-one model for 3d human pose estimation. In: European Conference on Computer Vision, Springer 2022:461\u201378.","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"422_CR21","doi-asserted-by":"crossref","unstructured":"Shan W, Liu Z, Zhang X, Wang Z, Han K, Wang S, Ma S, Gao W. Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation. 2023:14761\u201371.","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"422_CR22","first-page":"108705","volume":"27","author":"YY Shen","year":"2024","unstructured":"Shen YY, Xing QJ, Shen YF. Markerless vision-based functional movement screening movements evaluation with deep neural networks. ISCI. 2024;27:108705.","journal-title":"ISCI."},{"key":"422_CR23","doi-asserted-by":"crossref","unstructured":"Tang Z, Qiu Z, Hao Y, Hong R, Yao T. 3d human pose estimation with spatio-temporal criss-cross attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2023:4790\u20139.","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"422_CR24","doi-asserted-by":"crossref","unstructured":"Tao L, Burghardt T, Mirmehdi M, Damen D, Cooper A, Hannuna S, Camplani M, Paiement A, Craddock I. Calorie counter: RGB-depth visual estimation of energy expenditure at home. In: Computer Vision\u2013ACCV 2016 Workshops: ACCV 2016 International Workshops, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I 13. 2017:239\u2013251. Springer.","DOI":"10.1007\/978-3-319-54407-6_16"},{"issue":"2","key":"422_CR25","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.jsams.2015.01.013","volume":"19","author":"EJ Walker","year":"2016","unstructured":"Walker EJ, McAinch AJ, Sweeting A, Aughey RJ. Inertial sensors to estimate the energy expenditure of team-sport athletes. J Sci Med Sport. 2016;19(2):177\u201381.","journal-title":"J Sci Med Sport."},{"key":"422_CR26","doi-asserted-by":"crossref","unstructured":"Wang J, Yan S, Xiong Y, Lin D. Motion Guided 3D Pose Estimation from Videos. In: Vedaldi A, Bischof H, Brox T, Frahm JM. (eds.) Computer Vision \u2013 ECCV 2020. 2020:764\u2013780. Lecture Notes in Computer Science, Springer International Publishing, Cham. DOI: https:\/\/doi.org\/10\/grw53c.","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"422_CR27","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1007\/s00421-017-3641-x","volume":"117","author":"KR Westerterp","year":"2017","unstructured":"Westerterp KR. Doubly labelled water assessment of energy expenditure: principle, practice, and promise. Eur J Appl Physiol. 2017;117:1277\u201385.","journal-title":"Eur J Appl Physiol."},{"key":"422_CR28","doi-asserted-by":"crossref","unstructured":"Xu J, Guo Y, Peng, Y. Finepose: fine-grained prompt-driven 3d human pose estimation via diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2024:561\u201370.","DOI":"10.1109\/CVPR52733.2024.00060"},{"key":"422_CR29","doi-asserted-by":"crossref","unstructured":"Xu T, Takano W. Graph stacked hourglass networks for 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2021:16105\u201314.","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"422_CR30","doi-asserted-by":"publisher","first-page":"4278","DOI":"10.1109\/TIP.2022.3182269","volume":"31","author":"Y Xue","year":"2022","unstructured":"Xue Y, Chen J, Gu X, Ma H, Ma H. Boosting monocular 3D human pose estimation with part aware attention. IEEE Trans Image Process. 2022;31:4278\u201391.","journal-title":"IEEE Trans Image Process."},{"key":"422_CR31","doi-asserted-by":"crossref","unstructured":"Yu BX, Zhang Z, Liu Y, Zhong, S.h., Liu, Y., Chen, C.W. Gla-gcn: Global-local adaptive graph convolutional network for 3d human pose estimation from monocular video. In: Proceedings of the IEEE\/CVF international conference on computer vision 2023:8818\u201329.","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"422_CR32","doi-asserted-by":"crossref","unstructured":"Zeng A, Sun X, Yang L, Zhao N, Liu M, Xu Q. Learning skeletal graph neural networks for hard 3d pose estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision 2021:11436\u201345.","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"422_CR33","doi-asserted-by":"crossref","unstructured":"Zhang J, Tu Z, Yang J, Chen Y, Yuan, J. 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 2022:13232\u201342.","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"422_CR34","doi-asserted-by":"publisher","first-page":"7914","DOI":"10.1109\/TIP.2021.3109517","volume":"30","author":"J Zhang","year":"2021","unstructured":"Zhang J, Wang Y, Zhou Z, Luan T, Wang Z, Qiao Y. Learning dynamical human-joint affinity for 3d pose estimation in videos. IEEE Trans Image Process. 2021;30:7914\u201325.","journal-title":"IEEE Trans Image Process"},{"key":"422_CR35","doi-asserted-by":"crossref","unstructured":"Zhang S, Jin L, Wang Y, Wang X, Wen X, Feng Z, et al. E3V\u2013K5: an Authentic Benchmark for Redefining Video-Based Energy Expenditure Estimation. In: European Conference on Computer Vision Springer 2024:421\u201340.","DOI":"10.1007\/978-3-031-72761-0_24"},{"key":"422_CR36","doi-asserted-by":"crossref","unstructured":"Zhao L, Peng X, Tian Y, Kapadia M, Metaxas DN. Semantic Graph Convolutional Networks for 3D Human Pose Regression. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3420\u20133430 (2019). DOI: https:\/\/doi.org\/10\/gg2d9s, iSSN: 2575-7075","DOI":"10.1109\/CVPR.2019.00354"},{"key":"422_CR37","doi-asserted-by":"crossref","unstructured":"Zhao Q, Zheng C, Liu M, Wang P, Chen C. Poseformerv2: exploring frequency domain for efficient and robust 3d human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2023:8877\u201386.","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"422_CR38","doi-asserted-by":"crossref","unstructured":"Zhao W, Wang W, Tian, Y. Graformer: graph-oriented transformer for 3d pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2022:20438\u201347.","DOI":"10.1109\/CVPR52688.2022.01979"},{"issue":"1","key":"422_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3603618","volume":"56","author":"C Zheng","year":"2023","unstructured":"Zheng C, Wu W, Chen C, Yang T, Zhu S, Shen J, et al. Deep Learning-based Human Pose Estimation: a Survey. ACM Comput Surv. 2023;56(1):1\u201337.","journal-title":"ACM Comput Surv"},{"key":"422_CR40","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: Proceedings of the IEEE\/CVF international conference on computer vision 2021:11656\u201365.","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"422_CR41","doi-asserted-by":"crossref","unstructured":"Zhu W, Ma X, Liu Z, Liu L, Wu W, Wang, Y. Motionbert: a unified perspective on learning human motion representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision 2023:15085\u201399.","DOI":"10.1109\/ICCV51070.2023.01385"}],"container-title":["Health Information Science and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13755-025-00422-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13755-025-00422-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13755-025-00422-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T09:02:03Z","timestamp":1769936523000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13755-025-00422-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["422"],"URL":"https:\/\/doi.org\/10.1007\/s13755-025-00422-x","relation":{},"ISSN":["2047-2501"],"issn-type":[{"value":"2047-2501","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]},"assertion":[{"value":"2 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"36"}}