{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T12:03:44Z","timestamp":1784894624290,"version":"3.55.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61503005"],"award-info":[{"award-number":["61503005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Humanities and Social Sciences of the Ministry of Education in China","award":["22YJAZH002"],"award-info":[{"award-number":["22YJAZH002"]}]},{"name":"Beijing Natural Science Foundation","award":["L253018"],"award-info":[{"award-number":["L253018"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00371-026-04597-6","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T11:28:55Z","timestamp":1782559735000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["JC-STNet: a physics-inspired joint-centric spatiotemporal network for real-time 2D pose estimation"],"prefix":"10.1007","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5996-2728","authenticated-orcid":false,"given":"Xingquan","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6351-6674","authenticated-orcid":false,"given":"Kaijie","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2492-1616","authenticated-orcid":false,"given":"Chuansheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1849-9052","authenticated-orcid":false,"given":"Xinzhu","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6972-3813","authenticated-orcid":false,"given":"Liang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"4597_CR1","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1609\/aaai.v38i2.27826","volume":"38","author":"X An","year":"2024","unstructured":"An, X., Zhao, L., Gong, C., Wang, N., Wang, D., Yang, J.: Sharpose: Sparse high-resolution representation for human pose estimation. In Proceedings of the AAAI Conference on Artificial Intelligence 38, 691\u2013699 (2024)","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"13","key":"4597_CR2","doi-asserted-by":"publisher","first-page":"10751","DOI":"10.1007\/s00371-025-04066-6","volume":"41","author":"H Liu","year":"2025","unstructured":"Liu, H., Wen, X., Ye, X., Zhang, W.: Progressive dual-branch transformer-based diffusion model: a novel approach for robust 2D human pose estimation. Vis. Comput. 41(13), 10751\u201310766 (2025)","journal-title":"Vis. Comput."},{"key":"4597_CR3","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/TMM.2020.2999181","volume":"23","author":"A Kamel","year":"2020","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Hybrid refinement-correction heatmaps for human pose estimation. IEEE Trans. Multimedia 23, 1330\u20131342 (2020)","journal-title":"IEEE Trans. Multimedia"},{"issue":"9","key":"4597_CR4","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMC.2018.2850149","volume":"49","author":"A Kamel","year":"2018","unstructured":"Kamel, A., Sheng, B., Yang, P., Li, P., Shen, R., Feng, D.D.: Deep convolutional neural networks for human action recognition using depth maps and postures. IEEE Trans. Syst. Man Cybernet. Syst. 49(9), 1806\u20131819 (2018)","journal-title":"IEEE Trans. Syst. Man Cybernet. Syst."},{"key":"4597_CR5","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/LSP.2024.3517418","volume":"32","author":"R Zhang","year":"2024","unstructured":"Zhang, R., Feng, J., Feng, C., Wang, Y., Guo, L.: Part2Pose: Inferring Human Pose From Parts in Complex Scenes. IEEE Signal Process. Lett. 32, 441\u2013445 (2024)","journal-title":"IEEE Signal Process. Lett."},{"issue":"2","key":"4597_CR6","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s00371-025-04313-w","volume":"42","author":"SB Bian","year":"2026","unstructured":"Bian, S.B., Wang, J., You, Y., Yu, Z., Sun, Y., Wu, W.C.: Enhancing human pose estimation accuracy with pyramid fusion Vision Transformers. Vis. Comput. 42(2), 143 (2026)","journal-title":"Vis. Comput."},{"key":"4597_CR7","doi-asserted-by":"crossref","unstructured":"George, C., Eiband, M., Hufnagel, M., Hussmann, H.: Trusting strangers in immersive virtual reality. In Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces, 1\u20132, 2018","DOI":"10.1145\/3180308.3180355"},{"key":"4597_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2025.110821","volume":"138","author":"J Li","year":"2025","unstructured":"Li, J., Zhao, Y., Fan, Y., Chen, J., Gong, J., Li, W.J.: Flexible wearable electronics for enhanced human-computer interaction and virtual reality applications. Nano Energy 138, 110821 (2025)","journal-title":"Nano Energy"},{"key":"4597_CR9","doi-asserted-by":"publisher","DOI":"10.3389\/frvir.2021.750729","volume":"2","author":"SL Rogers","year":"2022","unstructured":"Rogers, S.L., Broadbent, R., Brown, J., Fraser, A., Speelman, C.P.: Realistic motion avatars are the future for social interaction in virtual reality. Front, Virt. Reality 2, 750729 (2022)","journal-title":"Front, Virt. Reality"},{"key":"4597_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2025.103488","volume":"199","author":"G Son","year":"2025","unstructured":"Son, G., Rubo, M.: Social virtual reality elicits natural interaction behavior with self-similar and generic avatars. Int. J. Hum Comput Stud. 199, 103488 (2025)","journal-title":"Int. J. Hum Comput Stud."},{"key":"4597_CR11","doi-asserted-by":"crossref","unstructured":"Jeong, U., Freer, J., Baek, S., Chang, H.J., Kim, K.I.: PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation. In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 12278\u201312288, 2025","DOI":"10.1109\/CVPR52734.2025.01146"},{"issue":"5","key":"4597_CR12","doi-asserted-by":"publisher","first-page":"3309","DOI":"10.1007\/s00371-024-03604-y","volume":"41","author":"X Cai","year":"2025","unstructured":"Cai, X., Zhang, H., Chen, L.Z., Wu, Y.J., Sun, H.: 3D human pose estimation using spatiotemporal hypergraphs and its public benchmark on opera videos. Vis. Comput. 41(5), 3309\u20133327 (2025)","journal-title":"Vis. Comput."},{"issue":"10","key":"4597_CR13","doi-asserted-by":"publisher","first-page":"2355012","DOI":"10.1142\/S0218001423550121","volume":"37","author":"X Cai","year":"2023","unstructured":"Cai, X., Lu, R., Cheng, P., Yao, J., Hu, Y.: An extended labanotation generation method based on 3d human pose estimation for intangible cultural heritage dance videos. Int. J. Pattern Recognit Artif Intell. 37(10), 2355012 (2023)","journal-title":"Int. J. Pattern Recognit Artif Intell."},{"key":"4597_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Ye, M. Y.: Fast human pose estimation. In Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition (CVPR), 3517\u20133526, 2019","DOI":"10.1109\/CVPR.2019.00363"},{"key":"4597_CR15","doi-asserted-by":"crossref","unstructured":"Maloney, D.: Mitigating negative effects of immersive virtual avatars on racial bias. In Proceedings of the 2018 Annual Symposium on Computer-Human Interaction in Play Companion Extended Abstracts, 39\u201343, 2018","DOI":"10.1145\/3270316.3270599"},{"key":"4597_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, J., Shi, Y., Gao, F., Xu, L., Yu, J.: Mutual adaptive reasoning for monocular 3d multi-person pose estimation. In Proceedings of the 30th ACM international conference on multimedia, 1788\u20131796, 2022","DOI":"10.1145\/3503161.3548148"},{"key":"4597_CR17","unstructured":"Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., Grundmann, M.: Blazepose: On-device real-time body pose tracking. arXiv preprint, arXiv:2006.10204, 2020"},{"key":"4597_CR18","doi-asserted-by":"crossref","unstructured":"Yu, C., Xiao, B., Gao, C., Yuan, L., Zhang, L., Sang, N., Wang, J.: Lite-hrnet: A lightweight high-resolution network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 10440\u201310450, 2021","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"4597_CR19","unstructured":"Jiang, T., Lu, P., Zhang, L., Ma, N., Han, R., Lyu, C., Li, Y., Chen, K.: Rtmpose: Real-time multi-person pose estimation based on mmpose. arXiv preprint, arXiv:2303.07399, 2023"},{"key":"4597_CR20","doi-asserted-by":"publisher","first-page":"24327","DOI":"10.52202\/068431-1766","volume":"35","author":"H Qu","year":"2022","unstructured":"Qu, H., Xu, L., Cai, Y., Foo, L.G., Liu, J.: Heatmap distribution matching for human pose estimation. Adv. Neural. Inf. Process. Syst. 35, 24327\u201324339 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4597_CR21","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In European Conference on Computer Vision (ECCV), 717\u2013732, 2016","DOI":"10.1007\/978-3-319-46478-7_44"},{"issue":"5","key":"4597_CR22","doi-asserted-by":"publisher","first-page":"3115","DOI":"10.1007\/s00530-022-01019-0","volume":"29","author":"H Chen","year":"2023","unstructured":"Chen, H., Feng, R., Wu, S., Xu, H., Zhou, F., Liu, Z.: 2D Human pose estimation: A survey. Multimedia Syst. 29(5), 3115\u20133138 (2023)","journal-title":"Multimedia Syst."},{"key":"4597_CR23","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2602\u20132611, 2017","DOI":"10.1109\/ICCV.2017.284"},{"key":"4597_CR24","doi-asserted-by":"crossref","unstructured":"Mao, W., Ge, Y., Shen, C., Tian, Z., Wang, X., Wang, Z., van den Hengel, A.: Poseur: Direct human pose regression with transformers. In European Conference on Computer Vision (ECCV), 72\u201388, 2022","DOI":"10.1007\/978-3-031-20068-7_5"},{"key":"4597_CR25","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: Human pose estimation via deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1653\u20131660, 2014","DOI":"10.1109\/CVPR.2014.214"},{"key":"4597_CR26","doi-asserted-by":"crossref","unstructured":"Bin, Y., Cao, X., Chen, X., Ge, Y., Tai, Y., Wang, C., Li, J., Huang, F., Gao, C., Sang, N.: Adversarial semantic data augmentation for human pose estimation. In European Conference on Computer Vision (ECCV), 606\u2013622, 2020","DOI":"10.1007\/978-3-030-58529-7_36"},{"key":"4597_CR27","unstructured":"Tian, Z., Chen, H., Shen, C.: Directpose: Direct end-to-end multi-person pose estimation, (2019). arXiv preprint arXiv:1911.07451"},{"key":"4597_CR28","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J. Stacked hourglass networks for human pose estimation. In European Conference on Computer Vision (ECCV), 483\u2013499, 2016","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"4597_CR29","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7103\u20137112, 2018","DOI":"10.1109\/CVPR.2018.00742"},{"key":"4597_CR30","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: Transpose: Keypoint localization via transformer. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 11802\u201311812, 2021","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"4597_CR31","doi-asserted-by":"publisher","first-page":"38571","DOI":"10.52202\/068431-2795","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose: Simple vision transformer baselines for human pose estimation. Adv. Neural. Inf. Process. Syst. 35, 38571\u201338584 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4597_CR32","doi-asserted-by":"crossref","unstructured":"Peng, Q., Zheng, C., Chen, C.: Source-free domain adaptive human pose estimation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 4826\u20134836, 2023","DOI":"10.1109\/ICCV51070.2023.00445"},{"key":"4597_CR33","doi-asserted-by":"crossref","unstructured":"Feng, R., Gao, Y., Tse, T. H. E., Ma, X., Chang, H. J.: Diffpose: Spatiotemporal diffusion model for video-based human pose estimation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 14861\u201314872, 2023","DOI":"10.1109\/ICCV51070.2023.01365"},{"key":"4597_CR34","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., Poddar, D.: Yolo-pose: Enhancing yolo for multi person pose estimation using object keypoint similarity loss. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 2637\u20132646, 2022","DOI":"10.1109\/CVPRW56347.2022.00297"},{"issue":"2","key":"4597_CR35","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10044-025-01431-y","volume":"28","author":"Z Tian","year":"2025","unstructured":"Tian, Z., Fu, W., Wo\u017aniak, M., Liu, S.: PCDPose: enhancing the lightweight 2D human pose estimation model with pose-enhancing attention and context broadcasting. Pattern Anal. Appl. 28(2), 59 (2025)","journal-title":"Pattern Anal. Appl."},{"issue":"1","key":"4597_CR36","doi-asserted-by":"publisher","first-page":"15284","DOI":"10.1038\/s41598-025-00259-0","volume":"15","author":"S Cai","year":"2025","unstructured":"Cai, S., Xu, H., Cai, W., Mo, Y., Wei, L.: A human pose estimation network based on yolov8 framework with efficient multi-scale receptive field and expanded feature pyramid network. Sci. Rep. 15(1), 15284 (2025)","journal-title":"Sci. Rep."},{"key":"4597_CR37","doi-asserted-by":"crossref","unstructured":"Geng, Z., Wang, C., Wei, Y., Liu, Z., Li, H., Hu, H.: Human pose as compositional tokens. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 660\u2013671, 2023","DOI":"10.1109\/CVPR52729.2023.00071"},{"issue":"1","key":"4597_CR38","doi-asserted-by":"publisher","first-page":"5637","DOI":"10.1038\/s41598-026-35859-x","volume":"16","author":"C Wu","year":"2026","unstructured":"Wu, C., Chen, Z., Ying, B., Tan, G., Hu, B., Li, C., Chen, H.: HEViTPose: towards high-accuracy and efficient 2D human pose estimation with cascaded group spatial reduction attention. Sci. Rep. 16(1), 5637 (2026)","journal-title":"Sci. Rep."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04597-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04597-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04597-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T11:37:45Z","timestamp":1784893065000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04597-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,27]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["4597"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04597-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,27]]},"assertion":[{"value":"27 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no Conflict of interests.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study does not involve human participants or animal subjects; therefore, ethics approval and consent to participate are not applicable.","order":2,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"365"}}