{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T02:47:08Z","timestamp":1745462828327,"version":"3.37.3"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s00530-022-00919-5","type":"journal-article","created":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T10:57:41Z","timestamp":1648810661000},"page":"1597-1609","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fixed-resolution representation network for human pose estimation"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0577-9618","authenticated-orcid":false,"given":"Yongxiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorong","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,1]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, Y., Yuille, A.L.: An approach to pose-based action recognition. In: CVPR, pp. 915\u2013922 (2013)","key":"919_CR1","DOI":"10.1109\/CVPR.2013.123"},{"key":"919_CR2","doi-asserted-by":"publisher","first-page":"4500","DOI":"10.1109\/TIP.2019.2910414","volume":"28","author":"L Zheng","year":"2019","unstructured":"Zheng, L., Huang, Y., Lu, H., Yang, Y.: Pose invariant embedding for deep person re-identification. Proc. IEEE Trans. Image Process. 28, 4500\u20134509 (2019)","journal-title":"Proc. IEEE Trans. Image Process."},{"key":"919_CR3","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MMUL.2012.24","volume":"19","author":"Z Zhang","year":"2012","unstructured":"Zhang, Z.: Microsoft kinect sensor and its effect. IEEE MultiMedia 19, 4\u201310 (2012)","journal-title":"IEEE MultiMedia"},{"doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware Siamese networks for visual object tracking. In: ECCV, pp. 103\u2013119 (2018)","key":"919_CR4","DOI":"10.1007\/978-3-030-01240-3_7"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., Zhu, Z., Xie, L., Huang, G., Du, D., Wang, X.: Attention-guided unified network for panoptic segmentation. In: CVPR, pp. 7019\u20137028 (2019)","key":"919_CR5","DOI":"10.1109\/CVPR.2019.00719"},{"unstructured":"Zhu, J., Zou, W., Xu, L., Hu, Y., Zhu, Z., Chang, M., Huang, J., Huang, G., Du, D.: Action machine: rethinking action recognition in trimmed videos. In: arXiv (2018)","key":"919_CR6"},{"key":"919_CR7","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.neucom.2019.08.043","volume":"370","author":"J Zhu","year":"2019","unstructured":"Zhu, J., Zou, W., Zhu, Z., Hu, Y.: Convolutional relation network for skeleton-based action recognition. Neurocomputing 370, 109\u2013117 (2019)","journal-title":"Neurocomputing"},{"doi-asserted-by":"crossref","unstructured":"Zhu, J., Zou, W., Zhu, Z.: End-to-end video-live representation learning for action recognition. In: ICPR, pp. 645\u2013650 (2018)","key":"919_CR8","DOI":"10.1109\/ICPR.2018.8545710"},{"doi-asserted-by":"crossref","unstructured":"Zhu, J., Zhou, W., Zhu, Z.: Two-stream gated fusion convnets for action recognition. In: ICPR, pp. 597\u2013602 (2018)","key":"919_CR9","DOI":"10.1109\/ICPR.2018.8545639"},{"key":"919_CR10","first-page":"1799","volume":"27","author":"J Tompson","year":"2014","unstructured":"Tompson, J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. NIPS 27, 1799\u20131807 (2014)","journal-title":"NIPS"},{"key":"919_CR11","first-page":"1653","volume":"27","author":"A Toshev","year":"2014","unstructured":"Toshev, A., Szegedy DeepPose, C.: Human pose estimation via deep neural networks. CVPR 27, 1653\u20131660 (2014)","journal-title":"CVPR"},{"key":"919_CR12","first-page":"483","volume":"9912","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K.: Jia Deng Stacked hourglass networks for human pose estimation. ECCV 9912, 483\u2013499 (2016)","journal-title":"ECCV"},{"doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: CVPR, pp. 4733\u20134742 (2016)","key":"919_CR13","DOI":"10.1109\/CVPR.2016.512"},{"key":"919_CR14","first-page":"4724","volume":"9912","author":"S Wei","year":"2016","unstructured":"Wei, S., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. CVPR 9912, 4724\u20134732 (2016)","journal-title":"CVPR"},{"key":"919_CR15","doi-asserted-by":"publisher","first-page":"102897","DOI":"10.1016\/j.cviu.2019.102897","volume":"192","author":"Y Chen","year":"2020","unstructured":"Chen, Y., Yingli, T., Mingyi, H.: Monocular human pose estimation: a survey of deep learning-based methods. Comput. Vis. Image Understand. 192, 102897 (2020)","journal-title":"Comput. Vis. Image Understand."},{"key":"919_CR16","first-page":"1799","volume":"27","author":"W Yang","year":"2017","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. ICCV 27, 1799\u20131807 (2017)","journal-title":"ICCV"},{"doi-asserted-by":"crossref","unstructured":"Rafi, U., Leibe, B., Gall, J., Kostrikov, I.: An efficient convolutional network for human pose estimation. In: BMVC (2016)","key":"919_CR17","DOI":"10.5244\/C.30.109"},{"doi-asserted-by":"crossref","unstructured":"Belagiannis, V., Zisserman, A.: Recurrent human pose estimation. In: IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017), pp. 468\u2013475 (2017)","key":"919_CR18","DOI":"10.1109\/FG.2017.64"},{"key":"919_CR19","first-page":"717","volume":"9911","author":"A Bulat","year":"2016","unstructured":"Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. ECCV 9911, 717\u2013732 (2016)","journal-title":"ECCV"},{"doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zuo, Y., Yan, S.: Human pose estimation with parsing induced learner. In: CVPR (2018)","key":"919_CR20","DOI":"10.1109\/CVPR.2018.00224"},{"doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Ye, M.: Fast human pose estimation. In: CVPR, pp. 3512\u20133521 (2019)","key":"919_CR21","DOI":"10.1109\/CVPR.2019.00363"},{"unstructured":"Lipeng, K., Ming Ching, C., Honggang, Q., Siwei, L.: Multi-scale structure-aware network for human pose estimation. In: ECCV (2018)","key":"919_CR22"},{"doi-asserted-by":"crossref","unstructured":"Sun, K., xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR, pp. 5686\u20135696 (2019)","key":"919_CR23","DOI":"10.1109\/CVPR.2019.00584"},{"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: CVPR, pp. 5385\u20135394 (2020)","key":"919_CR24","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"919_CR25","first-page":"455","volume":"12348","author":"Y Cai","year":"2020","unstructured":"Cai, Y., Wang, Z., Luo, Z., Yin, B., Angang, D., Wang, H., Zhang, X., Zhou, X., Zhou, E., Sun, J.: Learning delicate local representations for multi-person pose estimation. ECCV 12348, 455\u2013472 (2020)","journal-title":"ECCV"},{"doi-asserted-by":"crossref","unstructured":"Kim, S.-T., Lee, H.J.: Lightweight stacked hourglass network for human pose estimation. In: Appl. Sci., 10 (2020)","key":"919_CR26","DOI":"10.3390\/app10186497"},{"key":"919_CR27","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1007\/s11554-020-01025-3","volume":"18","author":"Y Lianping","year":"2021","unstructured":"Lianping, Y., Qin, Y., Xiangde, Z.: Lightweight densely connected residual network for human pose estimation. Real Time Image Process 18, 825\u2013827 (2021)","journal-title":"Real Time Image Process"},{"unstructured":"Xiao, Y., Yu, D., Wang, X., Lv, T., Fan, Y., Wu, L.: SPCNet: spatial preserve and content-aware network for human pose estimation. In: European Conference on Artificial Intelligence, pp. 2776\u20132783 (2020)","key":"919_CR28"},{"doi-asserted-by":"crossref","unstructured":"Yu, C., Xiao, B., Gao, C.: et. Lite-HRNet: a lightweight high-resolution network. In: CVPR, pp. 10440\u201310450 (2021)","key":"919_CR29","DOI":"10.1109\/CVPR46437.2021.01030"},{"doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Ye, M.: Fast human pose estimation. In: CVPR, pp. 3517\u20133526 (2019)","key":"919_CR30","DOI":"10.1109\/CVPR.2019.00363"},{"doi-asserted-by":"crossref","unstructured":"Ren, Z., Zhou, Y., Chen, Y., et al.: Efficient human pose estimation by maximizing fusion and high-level spatial attention. In: arXiv (2021)","key":"919_CR31","DOI":"10.1109\/FG52635.2021.9666981"},{"doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: CVPR, pp. 648\u2013656 (2015)","key":"919_CR32","DOI":"10.1109\/CVPR.2015.7298664"},{"doi-asserted-by":"crossref","unstructured":"Hou, L., Cao, J., Zhao, Y., et al.: $$P^{2}$$ Net: augmented parallel-pyramid net for attention guided pose estimation. In: ICPR, pp. 9658\u20139665 (2020)","key":"919_CR33","DOI":"10.1109\/ICPR48806.2021.9412759"},{"doi-asserted-by":"crossref","unstructured":"Yang, H., Guo, L., Wu, X., et al.: Scale-aware attention-based multi-resolution representation for multi-person pose estimation. In: Multimedia Systems (2021)","key":"919_CR34","DOI":"10.1007\/s00530-021-00795-5"},{"unstructured":"Artacho, B., Savakis, A.: OmniPose: a multi-scale framework for multi-person pose estimation. In: arXiv (2021)","key":"919_CR35"},{"doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., Tang, X.: Residual attention network for image classification. In: CVPR, pp. 6450\u20136458 (2017)","key":"919_CR36","DOI":"10.1109\/CVPR.2017.683"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","key":"919_CR37","DOI":"10.1109\/CVPR.2018.00745"},{"unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: arXiv, pp. 1412\u20137755 (2014)","key":"919_CR38"},{"doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: CVPR, pp. 21\u201329 (2016)","key":"919_CR39","DOI":"10.1109\/CVPR.2016.10"},{"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: CVPR, pp. 5669\u20135678 (2017)","key":"919_CR40","DOI":"10.1109\/CVPR.2017.601"},{"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: CVPR, pp. 5674\u20135682 (2019)","key":"919_CR41","DOI":"10.1109\/CVPR.2019.00582"},{"unstructured":"Yuan, Y., Fu, R., Huang, L., et al.: HRFormer: high-resolution transformer for dense prediction. In: arXiv (2021)","key":"919_CR42"},{"doi-asserted-by":"crossref","unstructured":"Huang, L., Yuan, Y., Guo, J., et al.: Interlaced sparse self-attention for semantic segmentation. In: arXiv (2019)","key":"919_CR43","DOI":"10.1109\/ICCV.2019.00069"},{"doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Cai, Y., et al.: Efficient human pose estimation by learning deeply aggregated representations. In: arXiv (2020)","key":"919_CR44","DOI":"10.1109\/ICME51207.2021.9428206"},{"key":"919_CR45","first-page":"7132","volume":"9912","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Banggu, W., Zhu, P., Li, P., Zuo, W., Qinghua, H.: ECA-Net: efficient channel attention for deep convolutional neural network. CVPR 9912, 7132\u20137141 (2020)","journal-title":"CVPR"},{"doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., et al.: Integral human pose regression. In: ECCV, pp. 536\u2013553 (2018)","key":"919_CR46","DOI":"10.1007\/978-3-030-01231-1_33"},{"doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Dai, H., et al.: Distribution-aware coordinate representation for human pose estimation. In: CVPR, pp. 7091\u20137100 (2020)","key":"919_CR47","DOI":"10.1109\/CVPR42600.2020.00712"},{"doi-asserted-by":"crossref","unstructured":"Huang, J., Zhu, Z., Guo, F., Huang, G.: The devil is in the details: delving into unbiased data processing for human pose estimation. In: CVPR, pp. 5699\u20135708 (2020)","key":"919_CR48","DOI":"10.1109\/CVPR42600.2020.00574"},{"doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: ECCV, pp. 472\u2013487 (2018)","key":"919_CR49","DOI":"10.1007\/978-3-030-01231-1_29"},{"unstructured":"Zhang, Z., Tang, J., Wu, G.: Simple and lightweight human pose estimation. In: arXiv (2020)","key":"919_CR50"},{"unstructured":"Yilun, C., Zhicheng, W., Yuxiang, P., Zhiqiang, Z., Gang, Y., Jian, S.: Cascaded pyramid network for multi-person pose estimation. In: CVPR, pp. 7103\u20137112 (2018)","key":"919_CR51"},{"unstructured":"Cosmin Duta, I., Liu, L., Zhu, F., Shao, L.: Pyramidal convolution: rethinking convolutional neural network for visual recognition. In: arXiv (2020)","key":"919_CR52"},{"unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: arXiv (2020)","key":"919_CR53"},{"doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: British Machine Vision Conference (2010)","key":"919_CR54","DOI":"10.5244\/C.24.12"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Computer Science, vol. 12 (2014)","key":"919_CR55"},{"doi-asserted-by":"crossref","unstructured":"Peng, X., Tang, Z., Yang, F., Feris, R., Metaxas, D.: Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation. In: CVPR, pp. 2226\u20132234 (2018)","key":"919_CR56","DOI":"10.1109\/CVPR.2018.00237"},{"unstructured":"Su, Z., Ye, M., Zhang, G., Dai, L., Sheng, J.: Cascade feature aggregation for human pose estimation. In: arXiv, pp. 1902\u201307837 (2019)","key":"919_CR57"},{"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: ECCV (2020)","key":"919_CR58","DOI":"10.1007\/978-3-030-58529-7_36"},{"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 (2014)","key":"919_CR59"},{"key":"919_CR60","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1109\/TMM.2017.2762010","volume":"20","author":"G Ning","year":"2018","unstructured":"Ning, G., Zhang, Z., He, Z.: Knowledge-guided deep fractal neural networks for human pose estimation. IEEE Trans. Multim. 20, 1246\u20131259 (2018)","journal-title":"IEEE Trans. Multim."},{"doi-asserted-by":"crossref","unstructured":"Bulat, D., Kossaifi, J., Tzimiropoulos, G., Pantic, M.: Toward fast and accurate human pose estimation via soft-gated skip connections. In: FG, pp. 8\u201315 (2020)","key":"919_CR61","DOI":"10.1109\/FG47880.2020.00014"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00919-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-022-00919-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00919-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T12:18:01Z","timestamp":1726921081000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-022-00919-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,1]]},"references-count":61,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["919"],"URL":"https:\/\/doi.org\/10.1007\/s00530-022-00919-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2022,4,1]]},"assertion":[{"value":"17 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2022","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}