{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T05:28:39Z","timestamp":1744954119510,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T00:00:00Z","timestamp":1728259200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T00:00:00Z","timestamp":1728259200000},"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":["61972361"],"award-info":[{"award-number":["61972361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00530-024-01460-3","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T13:02:24Z","timestamp":1728306144000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["3D human pose estimation with multi-hypotheses gated transformer"],"prefix":"10.1007","volume":"30","author":[{"given":"Xiena","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,7]]},"reference":[{"key":"1460_CR1","unstructured":"Angelini, F., Fu, Z., Long, Y., et al.: Actionxpose: a novel 2d multi-view pose-based algorithm for real-time human action recognition[J]. arXiv preprint arXiv:1810.12126, (2018)"},{"key":"1460_CR2","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition[C]. In Thirty-second AAAI Conference on Artificial Intelligence. (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1460_CR3","doi-asserted-by":"crossref","unstructured":"Lu, M., Poston, K., Pfefferbaum, A., et al.: Vision-based estimation of MDS-UPDRS gait scores for assessing Parkinson\u2019s disease motor severity[C]. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 637\u2013647 (2020)","DOI":"10.1007\/978-3-030-59716-0_61"},{"key":"1460_CR4","doi-asserted-by":"crossref","unstructured":"Gu, Y., Pandit, S., Saraee, E., et al.: Home-based physical therapy with an interactive computer vision system[C]. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops. (2019)","DOI":"10.1109\/ICCVW.2019.00320"},{"key":"1460_CR5","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., et al.: 3d human pose estimation in video with temporal convolutions and semi-supervised training[C]. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1460_CR6","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Liu, J., et al.: Exploiting spatial-temporal relationships for 3d pose estimation via graph convolutional networks[C]. Proceedings of the IEEE\/CVF international conference on computer vision. 2272\u20132281 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"1460_CR7","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., et al.: 3d human pose estimation with spatial and temporal transformers[C]. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"1460_CR8","doi-asserted-by":"crossref","unstructured":"Jahangiri, E., Yuille, A.L.: Generating multiple diverse hypotheses for human 3d pose consistent with 2d joint detections[C]. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops. 805\u2013814 (2017)","DOI":"10.1109\/ICCVW.2017.100"},{"key":"1460_CR9","doi-asserted-by":"crossref","unstructured":"Oikarinen, T., Hannah, D., Kazerounian, S.: GraphMDN: Leveraging graph structure and deep learning to solve inverse problems[C]. In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 1\u20139 (2021)","DOI":"10.1109\/IJCNN52387.2021.9534301"},{"key":"1460_CR10","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., et al.: Mhformer: multi-hypothesis transformer for 3d human pose estimation[C]. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13147\u201313156 (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"issue":"7","key":"1460_CR11","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., et al.: Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments[J]. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1460_CR12","doi-asserted-by":"crossref","unstructured":"Hu, W., Zhang, C., Zhan, F., Zhang, L., Wong, T.-T.: Conditional directed graph convolution for 3D human pose estimation. In Proceedings of the ACM International Conference on Multimedia (ACM), 602\u2013611 (2021)","DOI":"10.1145\/3474085.3475219"},{"key":"1460_CR13","unstructured":"Li, C., Lee, G.H.: Weakly supervised generative network for multiple 3D human pose hypotheses. In Proceedings of the British Machine Vision Conference (BMVC), (2020)"},{"key":"1460_CR14","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., et al.: A simple yet effective baseline for 3d human pose estimation[C]. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"1460_CR15","doi-asserted-by":"crossref","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3d human pose estimation[C]. In: Proceedings of the European Conference on Computer Vision (ECCV). 68\u201384 (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"issue":"1","key":"1460_CR16","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","volume":"32","author":"T Chen","year":"2021","unstructured":"Chen, T., Fang, C., Shen, X., et al.: Anatomy-aware 3d human pose estimation with bone-based pose decomposition[J]. IEEE Trans. Circ. Syst. Video Technol. 32(1), 198\u2013209 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"1460_CR17","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., et al.: Realtime multi-person 2d pose estimation using part affinity fields[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"1460_CR18","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., et al.: Cascaded pyramid network for multi-person pose estimation[C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"1460_CR19","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., et al.: Deep high-resolution representation learning for human pose estimation[C]. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1460_CR20","doi-asserted-by":"crossref","unstructured":"Li, C., Lee, G.H.: Generating multiple hypotheses for 3d human pose estimation with mixture density network[C]. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9887\u20139895 (2019)","DOI":"10.1109\/CVPR.2019.01012"},{"key":"1460_CR21","doi-asserted-by":"crossref","unstructured":"Sharma, S., Varigonda, P.T., Bindal, P., et al.: Monocular 3d human pose estimation by generation and ordinal ranking[C]. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2325\u20132334 (2019)","DOI":"10.1109\/ICCV.2019.00241"},{"key":"1460_CR22","doi-asserted-by":"crossref","unstructured":"Wehrbein, T., Rudolph, M., Rosenhahn, B., et al.: Probabilistic monocular 3d human pose estimation with normalizing flows[C]. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 11199\u201311208 (2021)","DOI":"10.1109\/ICCV48922.2021.01101"},{"key":"1460_CR23","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale[J]. In International Conference on Learning Representations. (2021)"},{"key":"1460_CR24","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Ding, R., et al.: Exploiting temporal contexts with strided transformer for 3d human pose estimation[J]. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3141231"},{"key":"1460_CR25","unstructured":"Parisotto, E., Song, F., Rae, J., et al.: Stabilizing transformers for reinforcement learning[C]. In International Conference on Machine Learning. PMLR, 7487\u20137498 (2020)"},{"key":"1460_CR26","doi-asserted-by":"crossref","unstructured":"Dhingra, B., Liu, H., Yang, Z., et al.: Gated-attention readers for text comprehension[C]. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. (2017)","DOI":"10.18653\/v1\/P17-1168"},{"key":"1460_CR27","unstructured":"Yeh, R., Hu, Y.T., Schwing, A.: Chirality nets for human pose regression[J]. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"1460_CR28","unstructured":"Lin, J., Lee, G.H.: Trajectory space factorization for deep video-based 3d human pose estimation[J]. In BMVC, (2019)"},{"key":"1460_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., et al.: Motion guided 3d pose estimation from videos[C]. In European Conference on Computer Vision. Springer, Cham, 764\u2013780 (2020)","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"1460_CR30","doi-asserted-by":"crossref","unstructured":"Liu, R., Shen, J., Wang, H., et al.: Attention mechanism exploits temporal contexts: real-time 3d human pose reconstruction[C]. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5064\u20135073 (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"1460_CR31","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Yang, L., et al.: Learning skeletal graph neural networks for hard 3d pose estimation[C]. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 11436\u201311445 (2021)","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"1460_CR32","doi-asserted-by":"crossref","unstructured":"Xu, J., Yu, Z., Ni, B., et al.: Deep kinematics analysis for monocular 3d human pose estimation[C]. In Proceedings of the IEEE\/CVF Conference on computer vision and Pattern recognition. 899\u2013908 (2020)","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"1460_CR33","doi-asserted-by":"crossref","unstructured":"Xu, T., Takano, W.: Graph stacked hourglass networks for 3d human pose estimation[C]. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16105\u201316114 (2021)","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"1460_CR34","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[C]. In European Conference on Computer Vision. Springer, Cham, 507\u2013523 (2020)","DOI":"10.1007\/978-3-030-58568-6_30"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01460-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01460-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01460-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T09:05:17Z","timestamp":1734339917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01460-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,7]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1460"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01460-3","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2024,10,7]]},"assertion":[{"value":"15 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2024","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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"309"}}