{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:05:28Z","timestamp":1764687928941,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["No.2017YFB1402102"],"award-info":[{"award-number":["No.2017YFB1402102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61907028","No.11872036"],"award-info":[{"award-number":["No.61907028","No.11872036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010031","name":"Postdoctoral Research Foundation of China","doi-asserted-by":"publisher","award":["No. 2018M640950"],"award-info":[{"award-number":["No. 2018M640950"]}],"id":[{"id":"10.13039\/501100010031","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s00530-021-00795-5","type":"journal-article","created":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T14:07:17Z","timestamp":1620050837000},"page":"57-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Scale-aware attention-based multi-resolution representation for multi-person pose estimation"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4124-5317","authenticated-orcid":false,"given":"Honghong","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longfei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,1]]},"reference":[{"key":"795_CR1","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s00530-017-0570-9","volume":"24","author":"J Liu","year":"2018","unstructured":"Liu, J., Gu, Y., Kamijo, S.: Customer pose estimation using orientational spatio-temporal network from surveillance camera. Multimedia Syst. 24, 439\u2013457 (2018)","journal-title":"Multimedia Syst."},{"key":"795_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"issue":"23","key":"795_CR3","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s00530-016-0504-y","volume":"2017","author":"M Gavrilescu","year":"2017","unstructured":"Gavrilescu, M.: Recognizing human gestures in videos by modeling the mutual context of body position and hands movement. Multimedia Syst. 2017(23), 381\u2013393 (2017)","journal-title":"Multimedia Syst."},{"key":"795_CR4","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. In: The International Conference on Image Processing (ICIP), pp. 1\u20139 (2020). arXiv:1909.05090","DOI":"10.1109\/ICIP40778.2020.9191174"},{"key":"795_CR5","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked Hourglass networks for human pose estimation. In: The European Conference on Computer Vision (ECCV), pp. 483\u2013499 (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"795_CR6","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: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"795_CR7","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"795_CR8","doi-asserted-by":"crossref","unstructured":"Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: IEEE International Conference on Computer Vision (ICCV), pp. 1290\u20131299 (2017)","DOI":"10.1109\/ICCV.2017.144"},{"key":"795_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, T.: SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6298\u20136306 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"795_CR10","doi-asserted-by":"crossref","unstructured":"Ke, L., Chang, M.C., Qi, H., Lyu, S.: Multi-scale structure-aware network for human pose estimation. In: The European Conference on Computer Vision (ECCV), pp. 731\u2013746 (2018)","DOI":"10.1007\/978-3-030-01216-8_44"},{"key":"795_CR11","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: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5667\u20135675 (2019)","DOI":"10.1109\/CVPR.2019.00582"},{"key":"795_CR12","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Bottom-up higher-resolution networks for multi-person pose estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u201310 (2020)"},{"key":"795_CR13","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: The European Conference on Computer Vision (ECCV), pp. 472\u2013487 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"795_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, T., Qi, J., Lu, H., Wang, G.: Progressive attention guided recurrent network for salient object detection. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 714\u2013722 (2018)","DOI":"10.1109\/CVPR.2018.00081"},{"key":"795_CR15","doi-asserted-by":"crossref","unstructured":"Woo, S.H., Park, J.C., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: The European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"795_CR16","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: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5669\u20135678 (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"795_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Doll\u00e1r, P.: Microsoft COCO: common objects in context. In: The European Conference on Computer Vision (ECCV), pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"795_CR18","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Iqbal, U., Insafutdinov, E., Pishchulin, L., Milan, A., Gall, J., Schiele, B.: PoseTrack: a benchmark for human pose estimation and tracking. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5167\u20135176 (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"issue":"6","key":"795_CR19","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"795_CR20","doi-asserted-by":"crossref","unstructured":"Cao, Z., Martinez, G.H., Simon, T., Wei, S., Sheikh, Y.A.: OpenPose: Realtime multi-person 2D pose estimation using part affinity fields. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 172\u2013186 (2017)","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"795_CR21","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., Alahi, A.: PifPaf: composite fields for human pose estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11969\u201311978 (2019)","DOI":"10.1109\/CVPR.2019.01225"},{"key":"795_CR22","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6950\u20136959 (2019)","DOI":"10.1109\/ICCV.2019.00705"},{"key":"795_CR23","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: The European Conference on Computer Vision (ECCV), pp. 282\u2013299 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"795_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"795_CR25","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: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3711\u20133719 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"795_CR26","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: The European Conference on Computer Vision (ECCV), pp. 536\u2013553 (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"795_CR27","doi-asserted-by":"crossref","unstructured":"Fang, H., Xie, S., Tai, Y., Lu, C.: \u2018RMPE: Regional Multi-person pose estimation. In: IEEE International Conference on Computer Vision (ICCV), pp. 2353\u20132362 (2017)","DOI":"10.1109\/ICCV.2017.256"},{"key":"795_CR28","doi-asserted-by":"crossref","unstructured":"Huang, S., Gong, M., Tao, D.: A coarse-fine network for keypoint localization. In: IEEE International Conference on Computer Vision (ICCV), pp. 3047\u20133056 (2017)","DOI":"10.1109\/ICCV.2017.329"},{"key":"795_CR29","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Bottom-up and top-down reasoning with hierarchical rectified Gaussians. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5600\u20135609 (2016)","DOI":"10.1109\/CVPR.2016.604"},{"key":"795_CR30","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., et al.: DeepCut joint subset partition and labeling for multi person pose estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4929\u20134937 (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"795_CR31","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Toshev, A., Jaitly, N.: Chained predictions using convolutional neural networks. In: The European Conference on Computer Vision (ECCV), pp. 728\u2013743 (2016)","DOI":"10.1007\/978-3-319-46493-0_44"},{"key":"795_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Dai, H., et al.: Distribution-aware coordinate representation for human pose estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7091\u20137100 (2020)","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"795_CR33","doi-asserted-by":"crossref","unstructured":"Sun, K., Lan, C., Xing, J., Zeng, W., Liu, D., Wang, J.: Human pose estimation using global and local normalization. In: IEEE International Conference on Computer Vision (ICCV), pp. 5600\u20135608 (2017)","DOI":"10.1109\/ICCV.2017.597"},{"key":"795_CR34","doi-asserted-by":"crossref","unstructured":"Tang, Z., Peng, X., Geng, S., Wu, L., Zhang, S., Metaxas, D.: Quantized densely connected U-Nets for efficient landmark localization. In: The European Conference on Computer Vision (ECCV), pp. 348\u2013364 (2018)","DOI":"10.1007\/978-3-030-01219-9_21"},{"issue":"5","key":"795_CR35","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. Multimedia 20(5), 1246\u20131259 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"795_CR36","doi-asserted-by":"crossref","unstructured":"Luvizon, D.C., Tabia, H., Picard, D.: Human pose regression by combining indirect part detection and contextual information. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15\u201322 (2017)","DOI":"10.1016\/j.cag.2019.09.002"},{"key":"795_CR37","unstructured":"Chou, C.J., Chien, J.T., Chen, H.T.: Self adversarial training for human pose estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition workshops (CVPRW), pp. 1\u201314 (2017)"},{"key":"795_CR38","doi-asserted-by":"crossref","unstructured":"Lifshitz, I., Fetaya, E., Ullman, S.: Human pose estimation using deep consensus voting. In: The European Conference on Computer Vision (ECCV), pp. 246\u2013260 (2016)","DOI":"10.1007\/978-3-319-46475-6_16"},{"key":"795_CR39","doi-asserted-by":"crossref","unstructured":"Tang, W., Yu, P., Wu. Y.: Deeply learned compositional models for human pose estimation. In: The European Conference on Computer Vision (ECCV), pp. 197\u2013214 (2018)","DOI":"10.1007\/978-3-030-01219-9_12"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00795-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00795-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00795-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T06:08:40Z","timestamp":1643350120000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00795-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["795"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00795-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2021,5,1]]},"assertion":[{"value":"10 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}