{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:33:27Z","timestamp":1772120007826,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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":["71971002"],"award-info":[{"award-number":["71971002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11760-024-03589-0","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:18:49Z","timestamp":1733393929000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A multi-granular joint tracing transformer for video-based 3D human pose estimation"],"prefix":"10.1007","volume":"19","author":[{"given":"Yingying","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"3589_CR1","unstructured":"Zheng, C., Wu, W., Chen, C., Yang, T., Zhu, S., Shen, J., Kehtarnavaz, N., Shah, M.: Deep learning-based human pose estimation: a survey. arXiv preprint arXiv:2012.13392 (2020)"},{"key":"3589_CR2","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2272\u20132281 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"3589_CR3","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"3589_CR4","unstructured":"Lin, J., Lee, G.H.: Trajectory space factorization for deep video-based 3d human pose estimation. arXiv preprint arXiv:1908.08289 (2019)"},{"key":"3589_CR5","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3d pose estimation from videos. In: European Conference on Computer Vision, pp. 764\u2013780. Springer (2020)","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"3589_CR6","doi-asserted-by":"crossref","unstructured":"Xu, J., Yu, Z., Ni, B., Yang, J., Yang, X., Zhang, W.: Deep kinematics analysis for monocular 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 899\u2013908 (2020)","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"3589_CR7","doi-asserted-by":"crossref","unstructured":"Liu, R., Shen, J., Wang, H., Chen, C., Cheung, S.-c., Asari, V.: Attention mechanism exploits temporal contexts: Real-time 3d human pose reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5064\u20135073 (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"3589_CR8","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":"3589_CR9","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., Wang, P., Van\u00a0Gool, 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":"3589_CR10","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Ding, R., Liu, M., Wang, P., Yang, W.: Exploiting temporal contexts with strided transformer for 3d human pose estimation. IEEE Trans. Multimedia 25, 1282\u20131293 (2022)","DOI":"10.1109\/TMM.2022.3141231"},{"key":"3589_CR11","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. arXiv preprint arXiv:2203.07628 (2022)","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"3589_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, J., Tu, Z., Yang, J., Chen, Y., Yuan, J.: Mixste: 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":"3589_CR13","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":"3589_CR14","doi-asserted-by":"crossref","unstructured":"Fang, H.-S., Xu, Y., Wang, W., Liu, X., Zhu, S.-C.: Learning pose grammar to encode human body configuration for 3d pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12270"},{"key":"3589_CR15","doi-asserted-by":"crossref","unstructured":"Lee, K., Lee, I., Lee, S.: Propagating lstm: 3d pose estimation based on joint interdependency. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 119\u2013135 (2018)","DOI":"10.1007\/978-3-030-01234-2_8"},{"key":"3589_CR16","doi-asserted-by":"crossref","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. In: European Conference on Computer Vision, pp. 507\u2013523 (2020). Springer","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"3589_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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"3589_CR18","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3d human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7307\u20137316 (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"3589_CR19","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, W., Zhao, W.: Pva-gcn: point-voxel absorbing graph convolutional network for 3d human pose estimation from monocular video. Signal Image Video Process. 18.4, 3627\u20133641 (2024)","DOI":"10.1007\/s11760-024-03028-0"},{"key":"3589_CR20","doi-asserted-by":"crossref","unstructured":"Panda, A., Mukherjee, D.P.: Monocular 3d human pose estimation by multiple hypothesis prediction and joint angle supervision. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3243\u20133247. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506722"},{"key":"3589_CR21","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":"3589_CR22","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) (2017)","DOI":"10.1109\/ICCV.2017.284"},{"key":"3589_CR23","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3d human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"3589_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, W., Tian, Y., Ye, Q., Jiao, J., Wang, W.: Graformer: graph convolution transformer for 3d pose estimation. arXiv preprint arXiv:2109.08364 (2021)","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"3589_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3589_CR26","doi-asserted-by":"crossref","unstructured":"Ma, H., Lu, K., Xue, J., Niu, Z., Gao, P.: Local to global transformer for video based 3d human pose estimation. In: 2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICMEW56448.2022.9859482"},{"key":"3589_CR27","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) (2018)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"3589_CR28","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3589_CR29","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., Jain, A.: Learning 3d human pose from structure and motion. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 668\u2013683 (2018)","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"3589_CR30","unstructured":"Ma, H., Chen, L., Kong, D., Wang, Z., Liu, X., Tang, H., Yan, X., Xie, Y., Lin, S.-Y., Xie, X.: Transfusion: Cross-view fusion with transformer for 3d human pose estimation. arXiv preprint arXiv:2110.09554 (2021)"},{"key":"3589_CR31","doi-asserted-by":"crossref","unstructured":"Shuai, H., Wu, L., Liu, Q.: Adaptive multi-view and temporal fusing transformer for 3d human pose estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/TPAMI.2022.3188716"},{"issue":"7","key":"3589_CR32","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":"3589_CR33","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"},{"issue":"1","key":"3589_CR34","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., Zhu, Y., Chen, Z., Luo, J.: Anatomy-aware 3d human pose estimation with bone-based pose decomposition. IEEE Trans. Circuits Syst. Video Technol. 32(1), 198\u2013209 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3589_CR35","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Zhang, Z., Liu, Y., Zhong, S.-h., 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":"3589_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, K., Luan, X., Syed, T.H.S., Xiang, X.: Icrformer: An improving cos-reweighting transformer for 3d human pose estimation in video. In: 2023 35th Chinese Control and Decision Conference (CCDC), pp. 436\u2013441. IEEE (2023)","DOI":"10.1109\/CCDC58219.2023.10326602"},{"key":"3589_CR37","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, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"issue":"4","key":"3589_CR38","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: real-time 3d human pose estimation with a single rgb camera. ACM Trans. Graphics (TOG) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graphics (TOG)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03589-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03589-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03589-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T12:49:52Z","timestamp":1738068592000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03589-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3589"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03589-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4154859\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"23 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2024","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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"72"}}