{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T20:48:16Z","timestamp":1758055696854,"version":"3.44.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00530-025-01832-3","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T05:21:39Z","timestamp":1747804899000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A distribution-aware 2D multi-person pose estimation method with attention mechanisms"],"prefix":"10.1007","volume":"31","author":[{"given":"Zhongwei","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanyuan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huabiao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liuge","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"1832_CR1","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":"1832_CR2","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: TransPose: Keypoint Localization via Transformer. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11782\u201311792. IEEE, Montreal, QC, Canada (2021)","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"1832_CR3","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, S., Wang, Z., Yang, S., Yang, W., Xia, S.-T., Zhou, E.: TokenPose: Learning Keypoint Tokens for Human Pose Estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11313\u201311322 (2021)","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"1832_CR4","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"1832_CR5","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":"1832_CR6","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Huang, Y., Wang, L., Tan, T., Zhou, E.: 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"},{"issue":"5","key":"1832_CR7","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1007\/s00530-021-00755-z","volume":"27","author":"L Yue","year":"2021","unstructured":"Yue, L., Li, J., Liu, Q.: Body parts relevance learning via expectation-maximization for human pose estimation. Multimed. Syst. 27(5), 927\u2013939 (2021)","journal-title":"Multimed. Syst."},{"key":"1832_CR8","doi-asserted-by":"crossref","unstructured":"Wei, F., Sun, X., Li, H., Wang, J., Lin, S.: Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision\u2014ECCV 2020 vol. 12355, pp. 527\u2013544. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58607-2_31"},{"key":"1832_CR9","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-End Multi-Person Pose Estimation With Transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11069\u201311078 (2022)","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"1832_CR10","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv (2021)"},{"key":"1832_CR11","unstructured":"Yang, J., Zeng, A., Liu, S., Li, F., Zhang, R., Zhang, L.: Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation. In: International Conference on Learning Representations (2023)"},{"key":"1832_CR12","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Wang, X.J., Yu, D., Wang, G., Zhang, Q., He, M.: AdaptivePose: human parts as adaptive points. In: Proceedings of the AAAI Conference on Artificial Intelligence 36(3), 2813\u20132821 (2022)","DOI":"10.1609\/aaai.v36i3.20185"},{"key":"1832_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Bian, S., Zeng, A., Wang, C., Pang, B., Liu, W., Lu, C.: Human pose regression with residual log-likelihood estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11025\u201311034 (2021)","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"1832_CR14","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482\u20137491 (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"1832_CR15","doi-asserted-by":"crossref","unstructured":"Wang, R., Shivanna, R., Cheng, D., Jain, S., Lin, D., Hong, L., Chi, E.: DCN V2: improved deep & cross network and practical lessons for web-scale learning to rank systems. In: Proceedings of the Web Conference 2021, pp. 1785\u20131797. ACM, Ljubljana Slovenia (2021)","DOI":"10.1145\/3442381.3450078"},{"key":"1832_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., Wang, X., Qiao, Y.: InternImage: exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14408\u201314419 (2023)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"1832_CR17","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision\u2014ECCV 2020, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1832_CR18","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Li, Z., Chen, Y., Wang, F., Zhu, X., Luo, J., Wang, W., Lu, T., Li, H., Qiao, Y., Lu, L., Zhou, J., Dai, J.: Efficient deformable ConvNets: rethinking dynamic and sparse operator for vision applications. arXiv (2024)","DOI":"10.1109\/CVPR52733.2024.00540"},{"key":"1832_CR19","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: Convolutional Block Attention Module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1832_CR20","unstructured":"Park, J., Woo, S., Lee, J.-Y., Kweon, I.S.: BAM: bottleneck attention module. arXiv (2018)"},{"key":"1832_CR21","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhang, L., Cheng, M.-M., Feng, J.: Strip pooling: rethinking spatial pooling for scene parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4003\u20134012 (2020)","DOI":"10.1109\/CVPR42600.2020.00406"},{"issue":"1","key":"1832_CR22","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s00530-022-00981-z","volume":"29","author":"S Liu","year":"2023","unstructured":"Liu, S., He, N., Wang, C., Yu, H., Han, W.: Lightweight human pose estimation algorithm based on polarized self-attention. Multimed. Syst. 29(1), 197\u2013210 (2023)","journal-title":"Multimed. Syst."},{"key":"1832_CR23","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"1832_CR24","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv (2019)"},{"issue":"6","key":"1832_CR25","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":"1832_CR26","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision\u2014ECCV 2016 vol. 9905, pp. 21\u201337. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1832_CR27","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv (2021)"},{"key":"1832_CR28","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"2","key":"1832_CR29","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1007\/s11760-021-01999-y","volume":"16","author":"T Wan","year":"2022","unstructured":"Wan, T., Luo, Y., Zhang, Z., Ou, Z.: TSNet: Tree structure network for human pose estimation. Signal Image Video Process. 16(2), 551\u2013558 (2022)","journal-title":"Signal Image Video Process."},{"key":"1832_CR30","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: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision\u2013ECCV 2014 vol. 8693, pp. 740\u2013755. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1832_CR31","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv (2017)"},{"key":"1832_CR32","first-page":"7281","volume":"34","author":"Y Yuan","year":"2021","unstructured":"Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., Wang, J.: Hrformer: high-resolution vision transformer for dense predict. Adv. Neural Inf. Process. Syst. 34, 7281\u20137293 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1832_CR33","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: 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":"1832_CR34","doi-asserted-by":"crossref","unstructured":"McNally, W., Vats, K., Wong, A., McPhee, J.: Rethinking keypoint representations: modeling keypoints and poses as objects for multi-person human pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision\u2014ECCV 2022, pp. 37\u201354. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20068-7_3"},{"key":"1832_CR35","doi-asserted-by":"crossref","unstructured":"Lu, P., Jiang, T., Li, Y., Li, X., Chen, K., Yang, W.: RTMO: towards high-performance one-stage real-time multi-person pose estimation. arXiv (2024)","DOI":"10.1109\/CVPR52733.2024.00148"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01832-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01832-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01832-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:00:46Z","timestamp":1757926846000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01832-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1832"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01832-3","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,5,21]]},"assertion":[{"value":"6 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"259"}}