{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T19:08:40Z","timestamp":1767035320622,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T00:00:00Z","timestamp":1630886400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T00:00:00Z","timestamp":1630886400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076183","61936014","61976159"],"award-info":[{"award-number":["62076183","61936014","61976159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["20ZR1473500","19ZR1461200"],"award-info":[{"award-number":["20ZR1473500","19ZR1461200"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Innovation Action Project of Science and Technology","award":["20511100700"],"award-info":[{"award-number":["20511100700"]}]},{"name":"National Key Research and Development Project","award":["2019YFB2102300","2019YFB2102301"],"award-info":[{"award-number":["2019YFB2102300","2019YFB2102301"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00371-021-02282-4","type":"journal-article","created":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T15:03:05Z","timestamp":1630940585000},"page":"1369-1381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Joint relation based human pose estimation"],"prefix":"10.1007","volume":"38","author":[{"given":"Shuang","family":"Liang","sequence":"first","affiliation":[]},{"given":"Gang","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Chi","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jiewen","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,6]]},"reference":[{"key":"2282_CR1","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017).","DOI":"10.1109\/CVPR.2017.143"},{"key":"2282_CR2","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"},{"key":"2282_CR3","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1831\u20131840 (2017).","DOI":"10.1109\/CVPR.2017.601"},{"key":"2282_CR4","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017).","DOI":"10.1109\/ICCV.2017.89"},{"key":"2282_CR5","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., Lu, C.: Rmpe: Regional multi-person pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2334\u20132343 (2017).","DOI":"10.1109\/ICCV.2017.256"},{"key":"2282_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00b4ar, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2282_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2282_CR8","doi-asserted-by":"crossref","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: Deepercut: A deeper, stronger, and faster multi-person pose estimation model. In: Proceedings of the European Conference on Computer Vision, pp. 34\u201350 (2016).","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"2282_CR9","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: Multiposenet: Fast multi-person pose estimation using pose residual network. In: Proceedings of the European Conference on Computer Vision, pp. 417\u2013433 (2018).","DOI":"10.1007\/978-3-030-01252-6_26"},{"key":"2282_CR10","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: Composite fields for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11,977\u201311,986 (2019).","DOI":"10.1109\/CVPR.2019.01225"},{"key":"2282_CR11","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: End-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing Systems, pp. 2277\u20132287 (2017)."},{"key":"2282_CR12","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 483\u2013499 (2016).","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2282_CR13","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6951\u20136960 (2019).","DOI":"10.1109\/ICCV.2019.00705"},{"key":"2282_CR14","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Chen, L.C., Gidaris, S., Tompson, J., Murphy, K.: Personlab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Proceedings of the European Conference on Computer Vision, pp. 269\u2013286 (2018).","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"2282_CR15","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., Toshev, A., Tompson, J., Bregler, C., Murphy, K.: Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4903\u20134911 (2017).","DOI":"10.1109\/CVPR.2017.395"},{"key":"2282_CR16","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P.V., Schiele, B.: Deepcut: Joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929\u2013 4937 (2016).","DOI":"10.1109\/CVPR.2016.533"},{"key":"2282_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)."},{"key":"2282_CR18","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 Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019).","DOI":"10.1109\/CVPR.2019.00584"},{"key":"2282_CR19","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, pp. 2602\u20132611 (2017).","DOI":"10.1109\/ICCV.2017.284"},{"key":"2282_CR20","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, pp. 529\u2013545 (2018).","DOI":"10.1109\/ICCV.2017.284"},{"key":"2282_CR21","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: Deeppose: Human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653\u20131660 (2014).","DOI":"10.1109\/CVPR.2014.214"},{"key":"2282_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Long, X., Gao, Y., Ding, E., Wen, S.: Graph-pcnn: Two stage human pose estimation with graph pose refinement. In: Proceedings of the European Conference on Computer Vision, pp. 492\u2013508 (2020).","DOI":"10.1007\/978-3-030-58621-8_29"},{"key":"2282_CR23","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016).","DOI":"10.1109\/CVPR.2016.511"},{"key":"2282_CR24","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision, pp. 466\u2013481 (2018).","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"2282_CR25","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Li, H., Wang, X.: End-to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3073\u20133082 (2016).","DOI":"10.1109\/CVPR.2016.335"},{"key":"2282_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9308\u20139316 (2019).","DOI":"10.1109\/CVPR.2019.00953"},{"issue":"4","key":"2282_CR27","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., et al.: Vnect: Real-time 3d human pose estimation with a single rgb camera. ACM Transactions on Graphics 36(4), 1\u201314 (2017)","journal-title":"ACM Transactions on Graphics"},{"key":"2282_CR28","doi-asserted-by":"crossref","unstructured":"Mehta D, Sotnychenko O, Mueller F, et al. XNect: Real-time multi-person 3D motion capture with a single RGB camera. ACM Transactions on Graphics, 2020, 39(4): 82: 1\u201382: 17.","DOI":"10.1145\/3386569.3392410"},{"issue":"1","key":"2282_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3407659","volume":"40","author":"M Shi","year":"2020","unstructured":"Shi, M., Aberman, K., Aristidou, A., et al.: MotioNet: 3D human motion reconstruction from monocular video with skeleton consistency. ACM Trans. Graph. 40(1), 1\u201315 (2020)","journal-title":"ACM Trans. Graph."},{"key":"2282_CR30","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. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 7753\u20137762.","DOI":"10.1109\/CVPR.2019.00794"},{"key":"2282_CR31","doi-asserted-by":"crossref","unstructured":"G\u00fcler R A, Neverova N, Kokkinos I. Densepose: Dense human pose estimation in the wild, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7297\u20137306","DOI":"10.1109\/CVPR.2018.00762"},{"key":"2282_CR32","unstructured":"Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv preprint http:\/\/arxiv.org\/abs\/1503.02531, 2015."},{"issue":"07","key":"2282_CR33","first-page":"11354","volume":"34","author":"J Li","year":"2020","unstructured":"Li, J., Su, W., Wang, Z.: Simple pose: rethinking and improving a bottom-up approach for multi-person pose estimation. Proc. AAAI Conf. Artif. Intell. 34(07), 11354\u201311361 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2282_CR34","unstructured":"Cao X, Ge Y, Tai Y, et al. Anti-Confusing: Region-Aware Network for Human Pose Estimation. arXiv preprint http:\/\/arxiv.org\/abs\/1905.00996, 2019."},{"key":"2282_CR35","unstructured":"Hong S, Park H, Park J, et al. HintPose. arXiv preprint http:\/\/arxiv.org\/abs\/2003.02170, 2020."},{"key":"2282_CR36","unstructured":"Liu T, Sun J J, Zhao L, et al. View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose. arXiv preprint http:\/\/arxiv.org\/abs\/2010.13321, 2020."},{"key":"2282_CR37","doi-asserted-by":"crossref","unstructured":"Qammaz A, Argyros A. Occlusion-tolerant and personalized 3D human pose estimation in RGB images, Proceedings of the International Conference on Pattern Recognition. IEEE, 2021: 6904\u20136911.","DOI":"10.1109\/ICPR48806.2021.9411956"},{"key":"2282_CR38","doi-asserted-by":"crossref","unstructured":"Cheng Y, Yang B, Wang B, et al. Occlusion-aware networks for 3d human pose estimation in video, Proceedings of the IEEE International Conference on Computer Vision. 2019: 723\u2013732.","DOI":"10.1109\/ICCV.2019.00081"},{"key":"2282_CR39","doi-asserted-by":"crossref","unstructured":"Kocabas M, Athanasiou N, Black M J. Vibe: Video inference for human body pose and shape estimation, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 5253\u20135263.","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"2282_CR40","doi-asserted-by":"crossref","unstructured":"Kanazawa A, Zhang J Y, Felsen P, et al. Learning 3d human dynamics from video, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 5614\u20135623.","DOI":"10.1109\/CVPR.2019.00576"},{"key":"2282_CR41","doi-asserted-by":"crossref","unstructured":"Yang Q, Shi W, Chen J, et al. Localization of hard joints in human pose estimation based on residual down-sampling and attention mechanism. Vis. Comput. 2021: 1\u201313.","DOI":"10.1007\/s00371-021-02122-5"},{"key":"2282_CR42","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-019-01757-9","author":"M Vidanpathirana","year":"2020","unstructured":"Vidanpathirana, M., Sudasingha, I., Vidanapathirana, J., et al.: Tracking and frame-rate enhancement for real-time 2D human pose estimation. Vis. Comput. (2020). https:\/\/doi.org\/10.1007\/s00371-019-01757-9","journal-title":"Vis. Comput."},{"issue":"3","key":"2282_CR43","first-page":"1","volume":"35","author":"S Agahian","year":"2018","unstructured":"Agahian, S., Negin, F., K\u00f6se, C.: Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition. Vis. Comput. 35(3), 1\u201317 (2018)","journal-title":"Vis. Comput."},{"key":"2282_CR44","doi-asserted-by":"crossref","unstructured":"Abdelbaky A , Aly S. Two-stream spatiotemporal feature fusion for human action recognition. Vis. Comput. 2020. 1\u201315.","DOI":"10.1007\/s00371-020-01940-3"},{"key":"2282_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-017-1446-x","author":"EJ Rechy-Ramirez","year":"2017","unstructured":"Rechy-Ramirez, E.J., Marin-Hernandez, A., Rios-Figueroa, H.V.: A human\u2013computer interface for wrist rehabilitation: a pilot study using commercial sensors to detect wrist movements. Vis. Comput. (2017). https:\/\/doi.org\/10.1007\/s00371-017-1446-x","journal-title":"Vis. Comput."},{"issue":"5","key":"2282_CR46","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/s00371-018-1499-5","volume":"35","author":"G Tripathi","year":"2019","unstructured":"Tripathi, G., Singh, K., Vishwakarma, D.K.: Convolutional neural networks for crowd behaviour analysis: a survey. Vis. Comput. 35(5), 753\u2013776 (2019)","journal-title":"Vis. Comput."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02282-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02282-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02282-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,21]],"date-time":"2022-07-21T14:22:23Z","timestamp":1658413343000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02282-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,6]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["2282"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02282-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2021,9,6]]},"assertion":[{"value":"5 August 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest or competing interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"The source code used during the current study are available from the authors on reasonable request.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}