{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:11:39Z","timestamp":1758892299776,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:00:00Z","timestamp":1622160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:00:00Z","timestamp":1622160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004829","name":"Department of Science and Technology of Sichuan Province","doi-asserted-by":"publisher","award":["2020YFS0057"],"award-info":[{"award-number":["2020YFS0057"]}],"id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZYGX2019Z015"],"award-info":[{"award-number":["ZYGX2019Z015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00530-021-00808-3","type":"journal-article","created":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T03:51:26Z","timestamp":1622173886000},"page":"403-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["3D human pose estimation with multi-scale graph convolution and hierarchical body pooling"],"prefix":"10.1007","volume":"28","author":[{"given":"Ke","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"TianQi","family":"Sui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7019-8046","authenticated-orcid":false,"given":"Hong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,28]]},"reference":[{"key":"808_CR1","first-page":"21","volume":"97","author":"S Abu-El-Haija","year":"2019","unstructured":"Abu-El-Haija, S., Perozzi, B., Kapoor, A., Harutyunyan, H., Alipourfard, N., Lerman, K., Steeg, G.V., Galstyan, A.: Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. ICML 97, 21\u201329 (2019)","journal-title":"ICML"},{"issue":"1","key":"808_CR2","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TPAMI.2006.21","volume":"28","author":"A Agarwal","year":"2006","unstructured":"Agarwal, A., Triggs, B.: Recovering 3d human pose from monocular images. IEEE Trans. Pattern Anal. Mach. Intell. 28(1), 44\u201358 (2006). https:\/\/doi.org\/10.1109\/TPAMI.2006.21","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"808_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471","author":"M Andriluka","year":"2014","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: New benchmark and state of the art analysis. CVPR (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.471","journal-title":"CVPR"},{"key":"808_CR4","unstructured":"Bruna, J., Zaremba, W., Szlam, A.D., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: ICLR (2014)"},{"key":"808_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236","author":"Y Cai","year":"2019","unstructured":"Cai, Y., Ge, L., Liu, J., Cai, J., Cham, T.J., Yuan, J., Magnenat-Thalmann, N.: Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks. ICCV (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00236","journal-title":"ICCV"},{"key":"808_CR6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. CVPR (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00742","journal-title":"CVPR"},{"key":"808_CR7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00235","author":"H Ci","year":"2019","unstructured":"Ci, H., Wang, C., Ma, X., Wang, Y.: Optimizing network structure for 3d human pose estimation. ICCV (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00235","journal-title":"ICCV"},{"key":"808_CR8","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-030-11018-5_7","volume":"11132","author":"D Drover","year":"2018","unstructured":"Drover, D., Chen, C.H., Agrawal, A., Tyagi, A., Phuoc Huynh, C.: Can 3d pose be learned from 2d projections alone? ECCV 11132, 78\u201394 (2018). https:\/\/doi.org\/10.1007\/978-3-030-11018-5_7","journal-title":"ECCV"},{"key":"808_CR9","unstructured":"Duvenaud, D., Maclaurin, D., Aguilera-Iparraguirre, J., G\u00f3mez-Bombarelli, R., Hirzel, T., Aspuru-Guzik, A., Adams, R.P.: Convolutional networks on graphs for learning molecular fingerprints. In: NIPS, pp. 2224\u20132232. (2015)"},{"key":"808_CR10","unstructured":"Fang, H., Xu, Y., Wang, W., Liu, X., Zhu, S.C.: Learning knowledge-guided pose grammar machine for 3d human pose estimation. (2017)"},{"key":"808_CR11","doi-asserted-by":"publisher","unstructured":"Grinciunaite, A., Gudi, A., Tasli, E., Den Uyl, M.: Human pose estimation in space and time using 3d cnn. ECCV Worksh. 9915, 32\u201339 (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_5","DOI":"10.1007\/978-3-319-49409-8_5"},{"key":"808_CR12","unstructured":"Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS, pp. 1024\u20131034 (2017)"},{"key":"808_CR13","unstructured":"Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. (2015)"},{"key":"808_CR14","doi-asserted-by":"publisher","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3d human pose estimation. ECCV 11214, 68\u201384 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_5","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"808_CR15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126500","author":"C Ionescu","year":"2011","unstructured":"Ionescu, C., Li, F., Sminchisescu, C.: Latent structured models for human pose estimation. ICCV (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126500","journal-title":"ICCV"},{"issue":"7","key":"808_CR16","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.: Human 3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2013.248","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"808_CR17","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-030-20351-1\\_6","volume":"11492","author":"A Kazi","year":"2019","unstructured":"Kazi, A., Shekarforoush, S., Krishna, S.A., Burwinkel, H., Vivar, G., Kort\u00fcm, K., Ahmadi, S.A., Albarqouni, S., Navab, N.: Inceptiongcn: Receptive field aware graph convolutional network for disease prediction. IPMI 11492, 73\u201385 (2019). https:\/\/doi.org\/10.1007\/978-3-030-20351-1_6","journal-title":"IPMI"},{"key":"808_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: ICLR (2015)"},{"key":"808_CR19","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)"},{"key":"808_CR20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00117","author":"M Kocabas","year":"2019","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: Self-supervised learning of 3d human pose using multi-view geometry. CVPR (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00117","journal-title":"CVPR"},{"key":"808_CR21","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: AAAI, pp. 3538\u20133545 (2018)","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"808_CR22","first-page":"332","volume":"9004","author":"S Li","year":"2014","unstructured":"Li, S., Chan, A.B.: 3d human pose estimation from monocular images with deep convolutional neural network. ACCV 9004, 332\u2013347 (2014)","journal-title":"ACCV"},{"key":"808_CR23","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. In: ICLR (2016)"},{"key":"808_CR24","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1\\_48","volume":"8693","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. ECCV 8693, 740\u2013755 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","journal-title":"ECCV"},{"key":"808_CR25","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-58607-2\\_19","volume":"12355","author":"K Liu","year":"2020","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. ECCV 12355, 318\u2013334 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_19","journal-title":"ECCV"},{"key":"808_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288","author":"J Martinez","year":"2017","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3d human pose estimation. ICCV (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.288","journal-title":"ICCV"},{"key":"808_CR27","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064","author":"D Mehta","year":"2017","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. 3D Vis. (2017). https:\/\/doi.org\/10.1109\/3DV.2017.00064","journal-title":"3D Vis."},{"issue":"4","key":"808_CR28","doi-asserted-by":"publisher","first-page":"4411","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: Real-time 3d human pose estimation with a single rgb camera. ACM Trans. Graph. 36(4), 4411\u20134414 (2017). https:\/\/doi.org\/10.1145\/3072959.3073596","journal-title":"ACM Trans. Graph."},{"key":"808_CR29","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8\\_29","volume":"9912","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. ECCV 9912, 483\u2013499 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","journal-title":"ECCV"},{"key":"808_CR30","first-page":"2014","volume":"48","author":"M Niepert","year":"2016","unstructured":"Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. ICML 48, 2014\u20132023 (2016)","journal-title":"ICML"},{"key":"808_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4761608","author":"K Onishi","year":"2008","unstructured":"Onishi, K., Takiguchi, T., Ariki, Y.: 3d human posture estimation using the hog features from monocular image. ICPR (2008). https:\/\/doi.org\/10.1109\/ICPR.2008.4761608","journal-title":"ICPR"},{"key":"808_CR32","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-319-49409-8\\_15","volume":"9915","author":"S Park","year":"2016","unstructured":"Park, S., Hwang, J., Kwak, N.: 3d human pose estimation using convolutional neural networks with 2d pose information. ECCV Worksh. 9915, 156\u2013169 (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_15","journal-title":"ECCV Worksh."},{"key":"808_CR33","unstructured":"Park, S., Kwak, N.: 3d human pose estimation with relational networks. In: BMVC, p. 129 (2018)"},{"key":"808_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763","author":"G Pavlakos","year":"2018","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3d human pose estimation. CVPR (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00763","journal-title":"CVPR"},{"key":"808_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.139","author":"G Pavlakos","year":"2017","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-fine volumetric prediction for single-image 3d human pose. CVPR (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.139","journal-title":"CVPR"},{"key":"808_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794","author":"D Pavllo","year":"2019","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3d human pose estimation in video with temporal convolutions and semi-supervised training. CVPR (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00794","journal-title":"CVPR"},{"key":"808_CR37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00241","author":"S Sharma","year":"2019","unstructured":"Sharma, S., Varigonda, P.T., Bindal, P., Sharma, A., Jain, A.: Monocular 3d human pose estimation by generation and ordinal ranking. ICCV (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00241","journal-title":"ICCV"},{"key":"808_CR38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.284","author":"X Sun","year":"2017","unstructured":"Sun, X., Shang, J., Liang, S., Wei, Y.: Compositional human pose regression. ICCV (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.284","journal-title":"ICCV"},{"key":"808_CR39","doi-asserted-by":"crossref","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P.: Learning to fuse 2d and 3d image cues for monocular body pose estimation. In: ICCV, pp. 3941\u20133950 (2017)","DOI":"10.1109\/ICCV.2017.425"},{"key":"808_CR40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.603","author":"D Tome","year":"2017","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: Convolutional 3d pose estimation from a single image. CVPR (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.603","journal-title":"CVPR"},{"key":"808_CR41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/136","author":"M Wang","year":"2018","unstructured":"Wang, M., Chen, X., Liu, W., Qian, C., Lin, L., Ma, L.: Drpose3d: Depth ranking in 3d human pose estimation. IJCAI (2018). https:\/\/doi.org\/10.24963\/ijcai.2018\/136","journal-title":"IJCAI"},{"key":"808_CR42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00551","author":"W Yang","year":"2018","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., Wang, X.: 3d human pose estimation in the wild by adversarial learning. CVPR (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00551","journal-title":"CVPR"},{"key":"808_CR43","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/978-3-030-58568-6\\_30","volume":"12359","author":"A Zeng","year":"2020","unstructured":"Zeng, A., Sun, X., Huang, F., Liu, M., Xu, Q., Lin, S.: Srnet: Improving generalization in 3d human pose estimation with a split-and-recombine approach. ECCV 12359, 507\u2013523 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_30","journal-title":"ECCV"},{"key":"808_CR44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00354","author":"L Zhao","year":"2019","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3d human pose regression. CVPR (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00354","journal-title":"CVPR"},{"key":"808_CR45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.51","author":"X Zhou","year":"2017","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3d human pose estimation in the wild: A weakly-supervised approach. ICCV (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.51","journal-title":"ICCV"},{"key":"808_CR46","unstructured":"Zhu, Q., Du, B., Yan, P.: Multi-hop convolutions on weighted graphs. (2019)"},{"key":"808_CR47","doi-asserted-by":"crossref","unstructured":"Zou, Z., Liu, K., Wang, L., Tang, W.: High-order graph convolutional networks for 3d human pose estimation. In: BMVC (2020)","DOI":"10.1109\/ICCV48922.2021.01128"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00808-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00808-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00808-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T21:57:28Z","timestamp":1672264648000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00808-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,28]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["808"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00808-3","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2021,5,28]]},"assertion":[{"value":"15 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}