{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T01:58:02Z","timestamp":1770775082705,"version":"3.50.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:00:00Z","timestamp":1641772800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:00:00Z","timestamp":1641772800000},"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":["61573168"],"award-info":[{"award-number":["61573168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173160"],"award-info":[{"award-number":["62173160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s00371-021-02364-3","type":"journal-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T11:03:23Z","timestamp":1641812603000},"page":"651-662","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Spatial and contextual aware network based on multi-resolution for human pose estimation"],"prefix":"10.1007","volume":"39","author":[{"given":"Qingyu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Ying","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,10]]},"reference":[{"issue":"5","key":"2364_CR1","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1109\/TCYB.2013.2276430","volume":"43","author":"A Barmpoutis","year":"2013","unstructured":"Barmpoutis, A.: Tensor body: real-time reconstruction of the human body and avatar synthesis from RGB-d. IEEE Trans. Cybern. 43(5), 1347\u20131356 (2013)","journal-title":"IEEE Trans. Cybern."},{"key":"2364_CR2","doi-asserted-by":"crossref","unstructured":"Bin, Y., Cao, X., Chen, X., Ge, Y., Tai, Y., Wang, C., Li, J., Huang, F., Gao, C., Sang, N.: Adversarial semantic data augmentation for human pose estimation. In: European Conference on Computer Vision, pp. 606\u2013622. Springer (2020)","DOI":"10.1007\/978-3-030-58529-7_36"},{"key":"2364_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 4733\u20134742. IEEE (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"2364_CR4","unstructured":"Chen, X., Yuille, A.L.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in Neural Information Processing Systems, pp. 1736\u20131744 (2014)"},{"key":"2364_CR5","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. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"2364_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"2364_CR7","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. IEEE (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"2364_CR8","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. 2353\u20132362. IEEE (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"2364_CR9","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2364_CR10","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315\u2013323. JMLR (2011)"},{"key":"2364_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2364_CR12","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. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"11","key":"2364_CR13","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.1155\/S1110865704401206","volume":"2004","author":"CL Huang","year":"2004","unstructured":"Huang, C.L., Chung, C.Y.: A real-time model-based human motion tracking and analysis for human-computer interface systems. EURASIP J. Adv. Signal Process. 2004(11), 1648\u20131662 (2004)","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"2364_CR14","doi-asserted-by":"publisher","first-page":"224947","DOI":"10.1109\/ACCESS.2020.3044885","volume":"8","author":"Z Huo","year":"2020","unstructured":"Huo, Z., Jin, H., Qiao, Y., Luo, F.: Deep high-resolution network with double attention residual blocks for human pose estimation. IEEE Access 8, 224947\u2013224957 (2020)","journal-title":"IEEE Access"},{"key":"2364_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift 37, 448\u2013456 (2015)"},{"key":"2364_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, C., Huang, K., Zhang, S., Wang, X., Xiao, J.: Pay attention selectively and comprehensively: Pyramid gating network for human pose estimation without pre-training. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2364\u20132371 (2020)","DOI":"10.1145\/3394171.3414041"},{"key":"2364_CR17","unstructured":"Liang, S., Chu, G., Xie, C., Wang: Joint relation based human pose estimation. The Visual Computer pp. 1\u201313 (2021)"},{"key":"2364_CR18","doi-asserted-by":"crossref","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. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2364_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, D., et\u00a0al.: Receptive field block net for accurate and fast object detection. In: Proceedings of the European Conference on Computer Vision, pp. 404\u2013419. Springer (2018)","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"2364_CR20","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping, pp. 2277\u20132287 (2017)"},{"key":"2364_CR21","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: European Conference on Computer Vision, pp. 483\u2013499. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2364_CR22","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. pp. 3711\u20133719 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"2364_CR23","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. 3711\u20133719. IEEE (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"2364_CR24","doi-asserted-by":"crossref","unstructured":"Su, K., Yu, D., Xu, Z., Geng, X., Wang, C.: Multi-person pose estimation with enhanced channel-wise and spatial information. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5674\u20135682. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00582"},{"key":"2364_CR25","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. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"2364_CR26","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. 536\u2013553. Springer (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"2364_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2364_CR28","doi-asserted-by":"crossref","unstructured":"Tang, W., Yu, P., Wu, Y.: Deeply learned compositional models for human pose estimation. In: Proceedings of the European Conference on Computer Vision, pp. 197\u2013214. Springer (2018)","DOI":"10.1007\/978-3-030-01219-9_12"},{"key":"2364_CR29","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. IEEE (2014)","DOI":"10.1109\/CVPR.2014.214"},{"issue":"7","key":"2364_CR30","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1007\/s00371-019-01757-9","volume":"36","author":"M Vidanpathirana","year":"2020","unstructured":"Vidanpathirana, M., Sudasingha, I., Vidanapathirana, J., Kanchana, P., Perera, I.: Tracking and frame-rate enhancement for real-time 2d human pose estimation. Vis. Comput. 36(7), 1501\u20131519 (2020)","journal-title":"Vis. Comput."},{"key":"2364_CR31","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., Cottrell, G.: Understanding convolution for semantic segmentation. In: Winter Conference on Applications of Computer Vision, pp. 1451\u20131460. IEEE (2018)","DOI":"10.1109\/WACV.2018.00163"},{"key":"2364_CR32","unstructured":"Wang, Z., Tang, Z., Li, Y., Chen, Y., Ling, H., Lin, W., et\u00a0al.: Gsto: Gated scale-transfer operation for multi-scale feature learning in pixel labeling. arXiv preprint arXiv:2005.13363 (2020)"},{"key":"2364_CR33","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. IEEE (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"2364_CR34","doi-asserted-by":"crossref","unstructured":"Wei Tang and Ying Wu: Does Learning Specific Features for Related Parts Help Human Pose Estimation? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1107\u20131116 (2019)","DOI":"10.1109\/CVPR.2019.00120"},{"key":"2364_CR35","doi-asserted-by":"crossref","unstructured":"Wu, X., Liang, W., Jia, Y.: Action recognition feedback-based framework for human pose reconstruction from monocular images. Pattern Recognit. Lett. 30(12)(12), 1077\u20131085 (2009)","DOI":"10.1016\/j.patrec.2009.04.002"},{"key":"2364_CR36","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. Springer (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"2364_CR37","unstructured":"Xu, X., Zou, Q., Lin, X.: Multi-person pose estimation with enhanced feature aggregation and selection. arXiv preprint arXiv:2003.10238 (2020)"},{"key":"2364_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Q., Shi, W., Chen, J., Tang, Y.: Localization of hard joints in human pose estimation based on residual down-sampling and attention mechanism. The Visual Computer pp. 1\u201313 (2021)","DOI":"10.1007\/s00371-021-02122-5"},{"key":"2364_CR39","doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: proceedings of the IEEE International Conference on Computer Vision, pp. 1290\u20131299. IEEE (2017)","DOI":"10.1109\/ICCV.2017.144"},{"key":"2364_CR40","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: Bilateral segmentation network for real-time semantic segmentation. In: Proceedings of the European conference on computer vision, pp. 334\u2013349. Springer (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"2364_CR41","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations, pp. 1\u20139 (2016)"},{"key":"2364_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Dai, H., Ye, M., Zhu, C.: Distribution-aware coordinate representation for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7091\u20137100 (2020)","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"2364_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, K., He, P., Yao, P., Chen, G., Yang, C., Li, H., Fu, L., Zheng, T.: Dnanet: De-normalized attention based multi-resolution network for human pose estimation. arXiv preprint arXiv:1909.05090 (2019)","DOI":"10.1109\/ICIP40778.2020.9191174"},{"key":"2364_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, L., Chen, Y., Gao, Y., Wang, J., Lu, H.: Occlusion-aware siamese network for human pose estimation. In: European Conference on Computer Vision, pp. 396\u2013412. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_24"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02364-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02364-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02364-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T19:24:01Z","timestamp":1675797841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02364-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,10]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["2364"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02364-3","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,10]]},"assertion":[{"value":"9 November 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}