{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:49:33Z","timestamp":1782863373532,"version":"3.54.5"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:00:00Z","timestamp":1780358400000},"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":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00138-026-01852-7","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:22:04Z","timestamp":1780424524000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SBAHGNet:3D human pose estimation via skeleton-biased attention and high-frequency enhanced graph convolution"],"prefix":"10.1007","volume":"37","author":[{"given":"Yu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqiu","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"issue":"8","key":"1852_CR1","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.3390\/s25082409","volume":"25","author":"Y Guo","year":"2025","unstructured":"Guo, Y., Gao, T., Dong, A., Jiang, X., Zhu, Z., Wang, F.: A survey of the state of the art in monocular 3D human pose estimation: methods, benchmarks, and challenges. Sensors. 25(8), 2409 (2025). https:\/\/doi.org\/10.3390\/s25082409","journal-title":"Sensors"},{"key":"1852_CR2","doi-asserted-by":"publisher","first-page":"104282","DOI":"10.1016\/j.imavis.2021.104282","volume":"114","author":"M Ben Gamra","year":"2021","unstructured":"Ben Gamra, M., Akhloufi, M.A.: A review of deep learning tec-hniques for 2D and 3D human pose estimation. Image Vis. Co- mput. 114, 104282 (2021). https:\/\/doi.org\/10.1016\/j.imavis.2021.104282","journal-title":"Image Vis. Co- mput"},{"key":"1852_CR3","doi-asserted-by":"publisher","first-page":"112239","DOI":"10.1016\/j.patcog.2025.112239","volume":"171","author":"K Peng","year":"2026","unstructured":"Peng, K., Yin, C., Zheng, J., Liu, R., Schneider, D., Zhang, J., Yang, K., Sarfraz, M.S., Stiefelhagen, R., Roitberg, A.: Navigatin-. 171, 112239 (2026). https:\/\/doi.org\/10.1016\/j.patcog.2025.112239","journal-title":"Navigatin"},{"key":"1852_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03399-z","author":"A Yang","year":"2021","unstructured":"Yang, A., Lu, W., Naeem, W., Chen, L., Fei, M.: A sequence models-based real-time multi-person action recognition method with monocular vision. J. Ambient Intell. Humaniz. Comput. (2021). https:\/\/doi.org\/10.1007\/s12652-021-03399-z","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"1852_CR5","doi-asserted-by":"publisher","unstructured":"Cheng, Y., Yi, P., Liu, R., Dong, J., Zhou, D., Zhang, Q.: Hu-man-robot interaction method combining human pose estimati-on and motion intention recognition. In: 2021 IEEE 24th Inter-national Conference on Computer Supported Cooperative Wo-rk in Design (CSCWD), pp. 958\u2013963 (2021). https:\/\/doi.org\/10.1109\/CSCWD49262.2021.9437772","DOI":"10.1109\/CSCWD49262.2021.9437772"},{"key":"1852_CR6","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-642-17688-3_31","volume-title":"Adv-anced Concepts for Intelligent Vision Systems. ACIVS 2010","author":"H-Y Lin","year":"2010","unstructured":"Lin, H.-Y., Chen, T.-W.: Augmented reality with human body interaction based on monocular 3D pose estimation. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) Adv-anced Concepts for Intelligent Vision Systems. ACIVS 2010. Lecture Notes in Computer Science, vol. 6474, pp. 321\u2013331. Springer, Berlin (2010)"},{"issue":"4","key":"1852_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., Sridhar, S., Sotnychenko, O., Rhodin, H., Shafiei, M., Seidel, H.-P., Xu, W., Casas, D., Theobalt, C.: VNect: R-eal-time 3D human pose estimation with a single RGB came-ra. ACM Trans. Graph. 36(4), 1\u201314 (2017). https:\/\/doi.org\/10.1145\/3072959.3073596","journal-title":"ACM Trans. Graph"},{"key":"1852_CR8","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-031-72655-2_18","volume-title":"Computer Vision \u2013 ECCV 2024","author":"Z Sun","year":"2024","unstructured":"Sun, Z., Liang, Y., Ma, Z., Zhang, T., Bao, L., Li, G., He, S.: RePOSE: 3D human pose estimation via spatio-temporal depth relational consistency. In: Computer Vision\u2014ECCV 2024. Lecture Notes in Computer Science, pp. 309\u2013325. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72655-2_18"},{"key":"1852_CR9","doi-asserted-by":"publisher","first-page":"112239","DOI":"10.1016\/j.patcog.2025.112239","volume":"171","author":"Y Liu","year":"2026","unstructured":"Liu, Y., Zhang, Z.: STGFormer: spatio-temporal GraphFormer for 3D human pose estimation in video. Pattern Recogn. 171, 112239 (2026). https:\/\/doi.org\/10.1016\/j.patcog.2025.112239","journal-title":"Pattern Recogn."},{"key":"1852_CR10","doi-asserted-by":"publisher","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Patt-ern Recognition (CVPR), pp. 4929\u20134938 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00794","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1852_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zheng, C., Liu, M., Chen, C.: A single 2D pose with c-ontext is worth hundreds for 3D human pose estimation. In: Advances in Neural Information Processing Systems 36NeurIPS, pp. 27394\u201327413 (2023) (2023)","DOI":"10.52202\/075280-1193"},{"key":"1852_CR12","doi-asserted-by":"publisher","unstructured":"Lee, S., Hwang, Y., Lee, J.T.: Learning 2D human poses for better 3D lifting via multi-model 3D-guidance. In: Proceedings of the Asian Conference on Computer Vision (ACCV) 2024. Lecture Notes in Computer Science, vol. 15472, pp. 185\u2013202. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-981-96-0885-0_11","DOI":"10.1007\/978-981-96-0885-0_11"},{"key":"1852_CR13","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Zhang, Z., Liu, Y., Zhong, S., 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, pp. 8818\u20138829 (2023)","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"1852_CR14","unstructured":"Mehraban, S., Adeli, V., Taati, B.: Motionagformer: enhancing 3d human pose estimation with a transformer-gcnformer net-work. Mehraban, Adeli, S., Taati, V.: B.: Motionagformer: Enhancing 3d human pose estimation with a transformer-gcnformer network"},{"key":"1852_CR15","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M.: Semantic graph co-nvolutional networks for 3d human pose regression. In: Proceedings of the IEEE\/CVF conference on computer vision and p-attern recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"1852_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, J., Tu, Z., Yang, J., Yang, J., Chen, Y., Yuan, J.: MixS-TE: 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, pp. 13232\u201313242 (2022)","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"1852_CR17","doi-asserted-by":"publisher","unstructured":"Chen, Z., Dai, J., Bai, J., Pan, J.: (or the published author list as in the journal): DGFormer: dynamic graph transformer for 3D human pose estimation. Pattern Recognit (2024). https:\/\/doi.org\/10.1016\/j.patcog.2024.110446","DOI":"10.1016\/j.patcog.2024.110446"},{"key":"1852_CR18","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the Interna-tional Conference on Learning Representations (ICLR) (Poster) (2017). https:\/\/arxiv.org\/abs\/1609.02907"},{"key":"1852_CR19","unstructured":"Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 3844\u20133852 (2016)"},{"key":"1852_CR20","unstructured":"Wu, F., de Souza, A.H. Jr., Zhang, T., Fifty, C., Yu, T., Wein-berger, K.Q.: Simplifying graph convolutional networks. In: Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, pp. 6861\u20136871 (2019). https:\/\/proceedings.mlr.press\/v97\/wu19e.html"},{"key":"1852_CR21","doi-asserted-by":"publisher","unstructured":"Li, M., Chen, S., Zhang, Z., Xie, L., Tian, Q., Zhang, Y.: Skeleton-parted graph scattering networks for 3D human motion p-rediction. In: Computer Vision\u2014ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part VI, Lecture Notes in Computer Science, pp. 18\u201336. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_2","DOI":"10.1007\/978-3-031-20068-7_2"},{"key":"1852_CR22","doi-asserted-by":"publisher","unstructured":"Dong, Y., Ding, K., Jalaian, B., Ji, S., Li, J.: AdaGNN: graph neural networks with adaptive frequency response filter. In: Proceedings of the 30th ACM International Conference on I-nformation and Knowledge Management (CIKM), pp. 392\u2013401 (2021). https:\/\/doi.org\/10.1145\/3459637.3482226","DOI":"10.1145\/3459637.3482226"},{"key":"1852_CR23","doi-asserted-by":"publisher","unstructured":"Plizzari, C., Cannici, M., Matteucci, M.: Skeleton-based action recognition via spatial and temporal transformer networks. Computer Vision and Image Understanding 208\u2013209, 103219 (2021). https:\/\/doi.org\/10.1016\/j.cviu.2021.103219","DOI":"10.1016\/j.cviu.2021.103219"},{"key":"1852_CR24","doi-asserted-by":"publisher","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Decoupled spatial-tempor-al attention network for skeleton-based action-gesture recogniti-on. In: Computer Vision\u2014ACCV 2020 (Asian Conference on Computer Vision), Lecture Notes in Computer Science, vol. 12626, pp. 38\u201353. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-69541-5_3","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"1852_CR25","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.neucom.2023.03.001","volume":"537","author":"W Xin","year":"2023","unstructured":"Xin, W., Liu, R., Liu, Y., Chen, Y., Yu, W., Miao, Q.: Transf-ormer for skeleton-based action recognition: a review of recent advances. Neurocomputing. 537, 164\u2013186 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.03.001","journal-title":"Neurocomputing"},{"key":"1852_CR26","doi-asserted-by":"publisher","unstructured":"Gao, Z., Wang, P., Lv, P., Jiang, X., Liu, Q., Wang, P., Xu, M., Li, W.: Focal and global spatial-temporal transformer for skeleton-based action recognition (FG-STFormer). In: Proceedings of the Asian Conference on Computer Vision (ACCV), pp. 382\u2013398 (2022). https:\/\/doi.org\/10.1007\/978-3-031-26316-3_10","DOI":"10.1007\/978-3-031-26316-3_10"},{"key":"1852_CR27","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, pp. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"1852_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zheng, C., Liu, M., Wang, P., Chen, C.: Poseformerv2: exploring frequency domain for efficient and robust 3d hu-man pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8877\u20138886 (2023)","DOI":"10.1109\/CVPR52729.2023.00857"},{"issue":"8","key":"1852_CR29","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.3390\/sym14081547","volume":"14","author":"Y Jiang","year":"2022","unstructured":"Jiang, Y., Sun, Z., Yu, S., Wang, S., Song, Y.: A graph skeleton transformer network for action recognition. Symmetry. 14(8), 1547 (2022). https:\/\/doi.org\/10.3390\/sym14081547","journal-title":"Symmetry"},{"key":"1852_CR30","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.neucom.2023.03.001","volume":"537","author":"W Xin","year":"2023","unstructured":"Xin, W., Liu, R., Liu, Y., Chen, Y., Yu, W., Miao, Q.: Transformer for skeleton-based action recognition: a review of recent advances. Neurocomputing. 537, 164\u2013186 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.03.001","journal-title":"Neurocomputing"},{"key":"1852_CR31","doi-asserted-by":"crossref","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 68\u201384 (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"1852_CR32","doi-asserted-by":"publisher","unstructured":"Mehta, D., Sridhar, S., Sotnychenko, O., Rhodin, H., Shafiei, M., Seidel, H.-P., Xu, W., Casas, D., Theobalt, C.: VNect: real-time 3D human pose estimation with a single RGB came-ra. ACM Trans. Graph. 36(4) (2017). https:\/\/doi.org\/10.1145\/3072959.3073596","DOI":"10.1145\/3072959.3073596"},{"key":"1852_CR33","doi-asserted-by":"publisher","unstructured":"You, Y., Liu, H., Wang, T., Li, W., Ding, R., Li, X.: Co-evolution of pose and mesh for 3D human body estimation from video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14963\u201314973 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01374","DOI":"10.1109\/ICCV51070.2023.01374"},{"key":"1852_CR34","doi-asserted-by":"publisher","unstructured":"Zheng, K., et al.: 3D Human pose estimation via non-causal retentive networks. In: Proceedings of the European Conference on Computer Vision (ECCV) (2024). https:\/\/doi.org\/10.1007\/978-3-031-73414-4_7","DOI":"10.1007\/978-3-031-73414-4_7"},{"key":"1852_CR35","doi-asserted-by":"publisher","unstructured":"Hsu, C.-H., Jang, J.-S.R.: Enhancing 3D human pose estimation with bone length adjustment. In: Proceedings of the Asian Conference on Computer Vision (ACCV), Lecture Notes in Computer Science (LNCS), Springer (2024). https:\/\/doi.org\/10.1007\/978-981-96-0885-0_14","DOI":"10.1007\/978-981-96-0885-0_14"},{"key":"1852_CR36","doi-asserted-by":"publisher","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 7444\u20137452 (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.12328","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1852_CR37","doi-asserted-by":"publisher","unstructured":"Azizi, N., Possegger, H., Rodol\u00e0, E., Bischof, H.: 3D Human pose estimation using m\u00f6bius graph convolutional networks. In: Computer Vision\u2014ECCV 2022, Proceedings, Part I, Lecture Notes in Computer Science, pp. 160\u2013178. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_10","DOI":"10.1007\/978-3-031-19769-7_10"},{"key":"1852_CR38","unstructured":"Zhang, Z.: Group Graph convolutional networks for 3D human pose estimation. In: Proceedings of the 33rd British Ma-chine Vision Conference (BMVC 2022). BMVA Press (2022)"},{"key":"1852_CR39","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, pp. 13147\u201313156 (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"1852_CR40","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, pp. 4790\u20134799 (2023)","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"1852_CR41","doi-asserted-by":"publisher","unstructured":"Liu, J., Rojas, J., Li, Y., Liang, Z., Guan, Y., Xi, N., Zhu, H.: GAST-Net: graph attention spatio-temporal convolutional networks for 3D human pose estimation in video. In: Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 3374\u20133380 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561605","DOI":"10.1109\/ICRA48506.2021.9561605"},{"key":"1852_CR42","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.neucom.2022.06.033","volume":"501","author":"T Wang","year":"2022","unstructured":"Wang, T., Zhang, X.: Simplified-attention enhanced graph convolutional network for 3D human pose estimation (SaEGC-Net). Neurocomputing. 501, 231\u2013243 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.06.033","journal-title":"Neurocomputing"},{"key":"1852_CR43","doi-asserted-by":"crossref","unstructured":"Lin, H., Chiu, Y.-W., Wu, P.-Y.: AMPose: alternately mixed global-local attention model for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095351"},{"key":"1852_CR44","doi-asserted-by":"publisher","unstructured":"Zhai, K., Nie, Q., Ouyang, B., Li, X., Yang, S.: HopFIR: Hop-w-ise GraphFormer with intragroup joint refinement for 3D human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14985\u201314995 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01376","DOI":"10.1109\/ICCV51070.2023.01376"},{"issue":"5","key":"1852_CR45","first-page":"214313","volume":"60","author":"J Ai","year":"2022","unstructured":"Ai, J., Mao, Y., Luo, Q., Jia, L., Xing, M.: SAR target classification using the multi-kernel-size feature fusion based convolutional neural network. IEEE Trans. Geosci. Remote Sens. 60(5), 214313 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"4","key":"1852_CR46","first-page":"4018705","volume":"19","author":"J Ai","year":"2022","unstructured":"Ai, J., Fan, G., Mao, Y., Jin, J., Xing, M., Yan, H.: An improved SRGAN based ambiguity suppression algorithm for SAR ship target contrast enhancement. IEEE Geosci. Remote Sens. Lett. 19(4), 4018705 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1852_CR47","doi-asserted-by":"publisher","unstructured":"Huang, J., Feng, Y., Cui, F.-Q., Zhang, X., Liu, Z., Liu, X., Liu, J., Zhang, F., Li, M.: Identifying who you are no matter what you write through abstracting handwriting style. IEEE Trans. Depend. Secur. Comput. 1\u201315 (2026). https:\/\/doi.org\/10.1109\/TDSC.2026.3668275","DOI":"10.1109\/TDSC.2026.3668275"},{"key":"1852_CR48","doi-asserted-by":"crossref","unstructured":"Xue, W., Ai, J., Zhu, Y., Sun, X., Zhang, Y., Gao, G.: LMCNet: light-weight modality compensation network for salient ship detection under missing modality conditions. IEEE Trans. Aerosp. Electron. Syst., pp. 1\u201314 (2026)","DOI":"10.1109\/TAES.2026.3664356"},{"issue":"7","key":"1852_CR49","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1852_CR50","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3d human pose estimation in the wild using improved cnn supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516 IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"1852_CR51","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 (CVPR), pp. 8877\u20138886. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"1852_CR52","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 (ICCV), pp. 15085\u201315099. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.01385"},{"key":"1852_CR53","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv:1711.05101 (2017)"},{"key":"1852_CR54","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VIII 14, pp. 483\u2013499. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"1852_CR55","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, pp. 461\u2013478. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"1852_CR56","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, pp. 15085\u201315099 (2023)","DOI":"10.1109\/ICCV51070.2023.01385"},{"key":"1852_CR57","doi-asserted-by":"crossref","unstructured":"Chen, H., He, J.Y., Xiang, W., et al.: Hdformer: high-order directed transformer for 3d human pose Estimation. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 581\u2013589 (2023)","DOI":"10.24963\/ijcai.2023\/65"},{"key":"1852_CR58","doi-asserted-by":"publisher","unstructured":"Qian, X., Tang, Y., Zhang, N., Han, M., Xiao, J., Huang, M., Lin, R.: Hstformer: hierarchical spatial-temporal transformers for 3d human pose estimation. (2023). https:\/\/doi.org\/10.48550\/arXiv.2301.07322","DOI":"10.48550\/arXiv.2301.07322"},{"key":"1852_CR59","doi-asserted-by":"publisher","unstructured":"Liu, J., Liu, M., Liu, H., Li, W.: TCPFormer: learning temporal correlation with implicit pose proxy for 3D human pose estimation. In: Proceedings of the AAAI Conference on Artificial Inte-lligence (AAAI) (vol. 39) (2025). https:\/\/doi.org\/10.1609\/aaai.v39i5.32583","DOI":"10.1609\/aaai.v39i5.32583"},{"key":"1852_CR60","doi-asserted-by":"publisher","unstructured":"Foo, L.G., Li, T., Rahmani, H., Ke, Q., Liu, J.: Unified pose sequence modeling. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 13019\u201313030 (2023). https:\/\/doi.org\/10.1109\/-CVPR52729.2023.01251","DOI":"10.1109\/-CVPR52729.2023.01251"},{"key":"1852_CR61","first-page":"1","volume-title":"Computer Vision and Pattern Recognition","author":"A Farhadi","year":"2018","unstructured":"Farhadi, A., Redmon, J.: Yolov3: an incremental improvement. In: Computer Vision and Pattern Recognition, vol. 1804, pp. 1\u20136. Springer, Berlin\/Heidelberg, Germany (2018)"},{"key":"1852_CR62","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1852_CR63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.13715","author":"A Zeng","year":"2021","unstructured":"Zeng, A., et al.: SmoothNet: A plug-and-play network for refining human poses in videos. (2021). https:\/\/doi.org\/10.48550\/arXiv.2112.13715 :2112.13715","journal-title":"arXiv preprint arXiv"},{"key":"1852_CR64","doi-asserted-by":"publisher","unstructured":"Martini, E., et al.: COMETH: convex optimization for multiview estimation and tracking of humans. Expert Syst Appl, 210, 131728 (2026). https:\/\/doi.org\/10.1016\/j.eswa.2026.131728","DOI":"10.1016\/j.eswa.2026.131728"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01852-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-026-01852-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01852-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:55:18Z","timestamp":1782860118000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-026-01852-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,2]]},"references-count":64,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["1852"],"URL":"https:\/\/doi.org\/10.1007\/s00138-026-01852-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-8548943\/v1","asserted-by":"object"}]},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,2]]},"assertion":[{"value":"8 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"82"}}