{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T06:01:09Z","timestamp":1778392869745,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,13]],"date-time":"2022-11-13T00:00:00Z","timestamp":1668297600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,13]],"date-time":"2022-11-13T00:00:00Z","timestamp":1668297600000},"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":["61771299"],"award-info":[{"award-number":["61771299"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s00138-022-01352-4","type":"journal-article","created":{"date-parts":[[2022,11,13]],"date-time":"2022-11-13T18:03:00Z","timestamp":1668362580000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Human pose estimation based on lightweight basicblock"],"prefix":"10.1007","volume":"34","author":[{"given":"Yanping","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7974-9510","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,13]]},"reference":[{"key":"1352_CR1","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":"1352_CR2","unstructured":"Mao, W., Ge, Y., Shen, C., et al.: Tfpose: Direct human pose estimation with transformers (2021). arXiv preprint arXiv:2103.15320"},{"key":"1352_CR3","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":"1352_CR4","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., et al.: 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":"1352_CR5","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Huang, Y., et al.: Rethinking the heatmap regression for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13264\u201313273 (2021)","DOI":"10.1109\/CVPR46437.2021.01306"},{"key":"1352_CR6","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., et al.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1352_CR7","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., et al.: 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":"1352_CR8","doi-asserted-by":"crossref","unstructured":"Ke, L., Chang, M.C., Qi, H., et al.: Multi-scale structure-aware network for human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 713\u2013728 (2018)","DOI":"10.1007\/978-3-030-01216-8_44"},{"key":"1352_CR9","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 (ECCV), pp. 190\u2013206 (2018)","DOI":"10.1007\/978-3-030-01219-9_12"},{"key":"1352_CR10","first-page":"17","volume":"2018","author":"CJ Chou","year":"2018","unstructured":"Chou, C.J., Chien, J.T., Chen, H.T., Self adversarial training for human pose estimation.: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE 2018, 17\u201330 (2018)","journal-title":"IEEE"},{"key":"1352_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shen, C., Wei, X.S., et al.: Adversarial posenet: a structure-aware convolutional network for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1212\u20131221 (2017)","DOI":"10.1109\/ICCV.2017.137"},{"key":"1352_CR12","unstructured":"Li, Y., Yang, S., Zhang, S., et al.: Is 2D Heatmap Representation Even Necessary for Human Pose Estimation? (2021). arXiv preprint arXiv:2107.03332"},{"key":"1352_CR13","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1352_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et al.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1352_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1352_CR16","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 (ECCV), pp. 466\u2013481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"1352_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., et al.: 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":"1352_CR18","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: Posefix: model-agnostic general human pose refinement network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7773\u20137781 (2019)","DOI":"10.1109\/CVPR.2019.00796"},{"key":"1352_CR19","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., et al.: 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":"1352_CR20","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., et al.: Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14676\u201314686 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"1352_CR21","unstructured":"Howard, A.G., Zhu, M., Chen, B., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications (2017). arXiv preprint arXiv:1704.04861"},{"key":"1352_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., et al.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1352_CR23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., et al.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1352_CR24","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., et al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1352_CR25","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T. et al.: Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1352_CR26","doi-asserted-by":"crossref","unstructured":"Tang, Z., Peng, X., Geng, S., et al.: Quantized densely connected u-nets for efficient landmark localization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 339\u2013354 (2018)","DOI":"10.1007\/978-3-030-01219-9_21"},{"key":"1352_CR27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1352_CR28","doi-asserted-by":"crossref","unstructured":"Debnath, B., O\u2019brien, M., Yamaguchi, M., et al.: Adapting mobilenets for mobile based upper body pose estimation. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, pp. 1\u20136 (2018)","DOI":"10.1109\/AVSS.2018.8639378"},{"key":"1352_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhu, X., Ye, M.: Fast human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3517\u20133526 (2019)","DOI":"10.1109\/CVPR.2019.00363"},{"issue":"18","key":"1352_CR30","doi-asserted-by":"publisher","first-page":"6497","DOI":"10.3390\/app10186497","volume":"10","author":"S-T Kim","year":"2020","unstructured":"Kim, S.-T., Lee, H.J.: Lightweight stacked hourglass network for human pose estimation. Appl. Sci. 10(18), 6497 (2020)","journal-title":"Appl. Sci."},{"key":"1352_CR31","doi-asserted-by":"crossref","unstructured":"Yu, C., Xiao, B., Gao, C., et al. Lite-hrnet: a lightweight high-resolution network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10440\u201310450 (2021)","DOI":"10.1109\/CVPR46437.2021.01030"},{"issue":"3","key":"1352_CR32","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1007\/s11554-020-01025-3","volume":"18","author":"L Yang","year":"2021","unstructured":"Yang, L., Qin, Y., Zhang, X.: Lightweight densely connected residual network for human pose estimation. J. Real-Time Image Proc. 18(3), 825\u2013837 (2021)","journal-title":"J. Real-Time Image Proc."},{"key":"1352_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et al.: 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":"1352_CR34","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., et al.: 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":"1352_CR35","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Kanazawa, N., et al.: 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":"1352_CR36","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., et al.: Integral human pose regression. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 529\u2013545 (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"1352_CR37","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Xie, S., Tai, Y.W., et al.: 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":"1352_CR38","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., et al.: Transpose: Keypoint localization via transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11802\u201311812 (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"1352_CR39","unstructured":"Balakrishnan, K., Upadhyay, D.: BTranspose: Bottleneck Transformers for Human Pose Estimation with Self-Supervised Pre-Training (2022). arXiv preprint arXiv:2204.10209"},{"issue":"12","key":"1352_CR40","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Yi Yang","year":"2013","unstructured":"Yang, Yi., Ramanan, D.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Software Eng. 35(12), 2878\u20132890 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2012.261","journal-title":"IEEE Trans. Software Eng."},{"key":"1352_CR41","doi-asserted-by":"publisher","unstructured":"Debapriya Maji, Soyeb Nagori, Manu Mathew, Deepak Poddar: YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2637\u20132646 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.06806.","DOI":"10.48550\/arXiv.2204.06806"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-022-01352-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-022-01352-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-022-01352-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T16:07:09Z","timestamp":1673971629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-022-01352-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,13]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["1352"],"URL":"https:\/\/doi.org\/10.1007\/s00138-022-01352-4","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,13]]},"assertion":[{"value":"12 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"3"}}