{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:26:35Z","timestamp":1747200395829},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2021,4,10]],"date-time":"2021-04-10T00:00:00Z","timestamp":1618012800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,10]],"date-time":"2021-04-10T00:00:00Z","timestamp":1618012800000},"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":["Vis Comput"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s00371-021-02122-5","type":"journal-article","created":{"date-parts":[[2021,4,10]],"date-time":"2021-04-10T09:03:23Z","timestamp":1618045403000},"page":"2447-2459","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Localization of hard joints in human pose estimation based on residual down-sampling and attention mechanism"],"prefix":"10.1007","volume":"38","author":[{"given":"Qiaoning","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weimin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,10]]},"reference":[{"key":"2122_CR1","doi-asserted-by":"crossref","unstructured":"Alp G\u00fcler, R., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"2122_CR2","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., Lu, C.: Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"2122_CR3","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":"2122_CR4","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. 1281\u20131290 (2017)","DOI":"10.1109\/ICCV.2017.144"},{"key":"2122_CR5","doi-asserted-by":"crossref","unstructured":"Tang, W., Wu, Y.: Does learning specific features for related parts help human pose estimation? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1107\u20131116 (2019)","DOI":"10.1109\/CVPR.2019.00120"},{"issue":"6","key":"2122_CR6","first-page":"683","volume":"25","author":"M Sypetkowski","year":"2019","unstructured":"Sypetkowski, M., Sarwas, G., Trzcinski, T.: Synthetic image translation for football players pose estimation. J. UCS 25(6), 683\u2013700 (2019)","journal-title":"J. UCS"},{"key":"2122_CR7","doi-asserted-by":"crossref","unstructured":"Sapp, B., Toshev, A., Taskar, B.: Cascaded models for articulated pose estimation. In: Lecture Notes in Computer Science Proceedings of the 11th European Conference on Computer Vision: Part II, pp. 406\u2013420 (2010)","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"2122_CR8","doi-asserted-by":"crossref","unstructured":"Ferrari, V., Marin-Jimenez, M., Zisserman, A.: Progressive search space reduction for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587468"},{"key":"2122_CR9","doi-asserted-by":"publisher","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.214","DOI":"10.1109\/CVPR.2014.214"},{"key":"2122_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Ye, M.: Fast human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3517\u20133526 (2019)","DOI":"10.1109\/CVPR.2019.00363"},{"key":"2122_CR11","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":"2122_CR12","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"2122_CR13","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\u20134937 (2016)","DOI":"10.1109\/CVPR.2016.533"},{"key":"2122_CR14","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Lecture Notes in Computer Science European Conference on Computer Vision. Springer, Cham, pp. 483\u2013499 (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2122_CR15","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-toend learning for joint detection and grouping. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 2277\u20132287 (2017)"},{"key":"2122_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: Proceedings of the 31st AAAI conference on artificial intelligence, pp. 4278\u20134284 (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"2122_CR17","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":"2122_CR18","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"2122_CR19","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"3","key":"2122_CR20","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s00371-018-1566-y","volume":"35","author":"X Liu","year":"2019","unstructured":"Liu, X., Xu, Q., Wang, N.: A survey on deep neural network-based image captioning. Vis. Comput. 35(3), 445\u2013470 (2019)","journal-title":"Vis. Comput."},{"issue":"11","key":"2122_CR21","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1007\/s00371-018-1565-z","volume":"35","author":"T Jiang","year":"2019","unstructured":"Jiang, T., Zhang, Z., Yang, Y.: Modeling coverage with semantic embedding for image caption generation. Vis. Comput. 35(11), 1655\u20131665 (2019)","journal-title":"Vis. Comput."},{"key":"2122_CR22","first-page":"2017","volume":"28","author":"M Jaderberg","year":"2015","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. Adv. Neural. Inf. Process. Syst. 28, 2017\u20132025 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2122_CR23","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Lecture Notes in Computer Science Proceedings of the European Conference on Computer Vision, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2122_CR24","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":"2122_CR25","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 (2019)","DOI":"10.1109\/CVPR.2019.00582"},{"key":"2122_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). arXiv:1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"2122_CR27","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: Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, pp: 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"2122_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol. 2, no. 4, p. 5 (2010)","DOI":"10.5244\/C.24.12"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02122-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02122-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02122-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T00:09:34Z","timestamp":1671840574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02122-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,10]]},"references-count":28,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["2122"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02122-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,10]]},"assertion":[{"value":"22 March 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 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":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}