{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:17:59Z","timestamp":1754558279561,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"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","award":["(No.61907028","No.11872036","(No.61907028","No.11872036","(No.61907028","No.11872036"],"award-info":[{"award-number":["(No.61907028","No.11872036","(No.61907028","No.11872036","(No.61907028","No.11872036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young science and technology stars in Shaanxi Province","award":["2021KJXX-91"],"award-info":[{"award-number":["2021KJXX-91"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s00530-023-01085-y","type":"journal-article","created":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T02:02:12Z","timestamp":1681783332000},"page":"2085-2097","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["HSGNet: hierarchically stacked graph network with attention mechanism for 3D human pose estimation"],"prefix":"10.1007","volume":"29","author":[{"given":"Honghong","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,18]]},"reference":[{"key":"1085_CR1","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/s00530-021-00808-3","volume":"28","author":"K Huang","year":"2022","unstructured":"Huang, K., Sui, T., Wu, H.: 3D human pose estimation with multi-scale graph convolution and hierarchical body pooling. Multimed. Syst. 28, 403\u2013412 (2022)","journal-title":"Multimed. Syst."},{"issue":"6","key":"1085_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-022-01334-6","volume":"33","author":"H-H Yang","year":"2022","unstructured":"Yang, H.-H., Guo, L.-F., Zhang, Y.-M., Wu, X.-J.: U-shaped spatial-temporal transformer network for 3D human pose estimation. Mach. Vis. Appl. 33(6), 1\u201316 (2022)","journal-title":"Mach. Vis. Appl."},{"key":"1085_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00880-9","author":"X Dong","year":"2022","unstructured":"Dong, X., Yu, J., Zhang, J.: Position constrained network for 3D human pose estimation. Multimed. Syst. (2022). https:\/\/doi.org\/10.1007\/s00530-021-00880-9","journal-title":"Multimed. Syst."},{"key":"1085_CR4","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3D human pose estimation in the wild: a weakly-supervised approach. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 398\u2013407 (2017)","DOI":"10.1109\/ICCV.2017.51"},{"key":"1085_CR5","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3D human pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"1085_CR6","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 529\u2013545 (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"1085_CR7","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"1085_CR8","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1085_CR9","unstructured":"Lin, J., Lee, G.H.: Trajectory space factorization for deep video-based 3D human pose estimation. In: BMVC (2019)"},{"key":"1085_CR10","doi-asserted-by":"crossref","unstructured":"Xu, T., Takano, W.: Graph stacked hourglass networks for 3D human pose estimation. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16105\u201316114 (2021)","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"1085_CR11","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.-J., Yuan, J., Thalmann, N.M: 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 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"1085_CR12","doi-asserted-by":"crossref","unstructured":"Bai, Z., Yan, H., Wang, L.: High-order graph convolutional network for skeleton-based human action recognition.\u00a0PRCV (1):14\u201325 (2019)","DOI":"10.1007\/978-3-030-31654-9_2"},{"issue":"12","key":"1085_CR13","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong, C., Yu, J., Wan, J., et al.: multimodal deep autoencoder for human pose recovery. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 24(12), 5659\u20135670 (2015)","journal-title":"IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc."},{"issue":"6","key":"1085_CR14","first-page":"3742","volume":"62","author":"C Hong","year":"2015","unstructured":"Hong, C., Yu, J., Tao, D., et al.: Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. IEEE Trans. Ind. Electron. 62(6), 3742\u20133751 (2015)","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"3","key":"1085_CR15","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1007\/s11063-021-10699-0","volume":"54","author":"R Wang","year":"2022","unstructured":"Wang, R., Liu, R., Li, Y., et al.: Learning enriched global context information for human pose estimation. Neural Process. Lett. 54(3), 1663\u20131678 (2022)","journal-title":"Neural Process. Lett."},{"key":"1085_CR16","first-page":"1","volume":"4","author":"X Wang","year":"2021","unstructured":"Wang, X., Tong, J., Wang, R.: Attention refined network for human pose estimation. Neural Process. Lett. 4, 1\u201320 (2021)","journal-title":"Neural Process. Lett."},{"key":"1085_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3D human pose regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"1085_CR18","doi-asserted-by":"crossref","unstructured":"Ci, H., Wang, C., Ma, X., Wang, Y.: Optimizing network structure for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2262\u20132271 (2019)","DOI":"10.1109\/ICCV.2019.00235"},{"key":"1085_CR19","doi-asserted-by":"crossref","unstructured":"Liu, K., Ding, R., Zou, Z., Wang, L., Tang, W.: A comprehensive study of weight sharing in graph networks for 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58607-2_19"},{"key":"1085_CR20","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Huang, F., et al. SRNet: improving generalization in 3D human pose estimation with a split-and-recombine approach. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 507\u2013523 (2020)","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"1085_CR21","unstructured":"Bruna, J., Zaremba, W., Szlam, A., LeCun, Y. Spectral networks and locally connected networks on graphs. Comput. Sci. (2013)"},{"key":"1085_CR22","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70. pp. 1263\u20131272. JMLR.org (2017)"},{"key":"1085_CR23","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations (2016)"},{"issue":"44","key":"1085_CR24","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","volume":"2","author":"J Yu","year":"2022","unstructured":"Yu, J., Tan, M., Zhang, H., et al.: Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2(44), 563\u2013577 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1085_CR25","doi-asserted-by":"crossref","unstructured":"Zou, Z., Liu, K., Wang, L., Tang, W. High-order graph convolutional networks for 3D human pose estimation. In: British Machine Vision Conference (2020)","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"1085_CR26","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3D pose estimation from videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 764\u2013780 (2020)","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"1085_CR27","unstructured":"Ying, R., You, J., Morris, C., et al.: Hierarchical graph representation learning with differentiable pooling. In: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montr\u00e9al, Canada. pp. 1\u201311"},{"key":"1085_CR28","unstructured":"Velikovi, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. In: Proceedings of the International Conference on Learning Representations, pp. 1\u201312 (2018)"},{"issue":"7","key":"1085_CR29","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":"1085_CR30","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: 3D Vision (3DV), 2017 Fifth International Conference on. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"1085_CR31","doi-asserted-by":"crossref","unstructured":"Chen, T., Fang, C., Shen, X., Zhu, Y., Chen, Z., Luo, J.: Anatomy-aware 3D human pose estimation with bone-based pose decomposition. IEEE Trans. Circuits Syst. Video Technol. (2021)","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"1085_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 2nd International Conference on Learning Representations (2014)"},{"key":"1085_CR33","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: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"1085_CR34","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 International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"1085_CR35","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3D human pose estimation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7307\u20137316 (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"1085_CR36","doi-asserted-by":"crossref","unstructured":"HaoShu, F., Yuanlu, X., Wenguan, W., Xiaobai, L., SongChun, Z.: Learning pose grammar to encode human body configuration for 3D pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, pp. 6821\u20136828 (2018)","DOI":"10.1609\/aaai.v32i1.12270"},{"key":"1085_CR37","doi-asserted-by":"crossref","unstructured":"Sharma, S., Varigonda, P.T., Bindal, P., Sharma, A., Jain, A.: Monocular 3D human pose estimation by generation and ordinal ranking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2325\u20132334 (2019)","DOI":"10.1109\/ICCV.2019.00241"},{"key":"1085_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, W., Tian, Y., Ye, Q., et al. GraFormer: graph convolution transformer for 3D pose estimation. 1\u20139 (2021). http:\/\/arxiv.org\/abs\/2109.08364","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"1085_CR39","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"},{"issue":"4","key":"1085_CR40","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., Weipeng, Xu., Casas, D., Theobalt, C.: Vnect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. (TOG) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1085_CR41","doi-asserted-by":"crossref","unstructured":"Li, S., Ke, L., Pratama, K., Tai, Y.-W., Tang, C.-K., Cheng, K.-T.: Cascaded deep monocular 3D human pose estimation with evolutionary training data. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.00621"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01085-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01085-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01085-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T10:26:11Z","timestamp":1689330371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01085-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,18]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["1085"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01085-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2023,4,18]]},"assertion":[{"value":"29 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2023","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}