{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T07:51:42Z","timestamp":1782978702182,"version":"3.54.5"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T00:00:00Z","timestamp":1745366400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T00:00:00Z","timestamp":1745366400000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03893-x","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T02:59:32Z","timestamp":1745377172000},"page":"8703-8714","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["BR-Pose: enhancing human pose estimation through Bi-level routing attention and multi-level weight fusion"],"prefix":"10.1007","volume":"41","author":[{"given":"Zhi","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengzhao","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,23]]},"reference":[{"issue":"5","key":"3893_CR1","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1002\/cav.2293","volume":"35","author":"Z Xiao","year":"2024","unstructured":"Xiao, Z., Chen, Y., Zhou, X., He, M., Liu, L., Yu, F., Jiang, M.: Human action recognition in immersive virtual reality based on multi-scale spatio-temporal attention network. Comput. Anim. Virtual Worlds 35(5), 2293 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"3","key":"3893_CR2","doi-asserted-by":"publisher","first-page":"2233","DOI":"10.1002\/cav.2233","volume":"35","author":"L Jiang","year":"2024","unstructured":"Jiang, L., Xiong, Y., Wang, Q., Chen, T., Wu, W., Zhou, Z.: SADNet: generating immersive virtual reality avatars by real-time monocular pose estimation. Comput. Anim. Virtual Worlds 35(3), 2233 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"3893_CR3","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":"3893_CR4","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: Composite Fields for Human Pose Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11977\u201311986 (2019)","DOI":"10.1109\/CVPR.2019.01225"},{"key":"3893_CR5","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision - ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision - ECCV 2016, pp. 483\u2013499. Springer, Cham (2016)"},{"key":"3893_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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"3893_CR7","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":"3893_CR8","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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 269\u2013286 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"issue":"10","key":"3893_CR9","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Patt. Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"3893_CR10","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3893_CR11","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. Advances in neural information processing systems 32 (2019)"},{"issue":"2","key":"3893_CR12","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1109\/TPAMI.2023.3330016","volume":"46","author":"Y Xu","year":"2023","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose++: vision transformer for generic body pose estimation. IEEE Trans. Patt. Anal. Mach. Intell. 46(2), 1212\u20131230 (2023)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"3893_CR13","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3893_CR14","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"3893_CR15","unstructured":"Tian, Z., Chen, H., Shen, C.: Directpose: Direct end-to-end multi-person pose estimation. arXiv preprint arXiv:1911.07451 (2019)"},{"key":"3893_CR16","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: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part X 16, pp. 527\u2013544 (2020)","DOI":"10.1007\/978-3-030-58607-2_31"},{"issue":"8","key":"3893_CR17","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1007\/s00371-023-02953-4","volume":"39","author":"S Li","year":"2023","unstructured":"Li, S., Dai, J., Chen, Z., Pan, J.: A lightweight pose estimation network with multi-scale receptive field. Visual Comput. 39(8), 3429\u20133440 (2023)","journal-title":"Visual Comput."},{"key":"3893_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, S., Liu, P., Zhang, S., Wang, Y., Wang, Z., Yang, W., Xia, S.-T.: Simcc: A simple coordinate classification perspective for human pose estimation. In: European Conference on Computer Vision, pp. 89\u2013106 (2022)","DOI":"10.1007\/978-3-031-20068-7_6"},{"key":"3893_CR19","unstructured":"Jiang, T., Lu, P., Zhang, L., Ma, N., Han, R., Lyu, C., Li, Y., Chen, K.: Rtmpose: Real-time multi-person pose estimation based on mmpose. arXiv preprint arXiv:2303.07399 (2023)"},{"key":"3893_CR20","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., Poddar, D.: 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)","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"3893_CR21","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":"3893_CR22","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/TMM.2020.2999181","volume":"23","author":"A Kamel","year":"2020","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Hybrid refinement-correction heatmaps for human pose estimation. IEEE Trans. Multimed. 23, 1330\u20131342 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"3893_CR23","doi-asserted-by":"crossref","unstructured":"Wang, J., Long, X., Gao, Y., Ding, E., Wen, S.: Graph-pcnn: Two stage human pose estimation with graph pose refinement. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XI 16, pp. 492\u2013508 (2020)","DOI":"10.1007\/978-3-030-58621-8_29"},{"key":"3893_CR24","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1491\u20131500 (2024)","DOI":"10.1109\/CVPR52733.2024.00148"},{"key":"3893_CR25","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, S., Zhang, X., Xu, Y., Xu, W., Tu, Z.: Pose recognition with cascade transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1944\u20131953 (2021)","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"3893_CR26","doi-asserted-by":"crossref","unstructured":"Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., Yan, S.: Metaformer is actually what you need for vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"3893_CR27","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks. Advan. Neural Inf. Process. Syst. 34, 12116\u201312128 (2021)","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"3893_CR28","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3893_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3893_CR30","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"3893_CR31","doi-asserted-by":"crossref","unstructured":"Zeng, W., Jin, S., Liu, W., Qian, C., Luo, P., Ouyang, W., Wang, X.: Not all tokens are equal: Human-centric visual analysis via token clustering transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"3893_CR32","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhu, Y., Zhao, C., Hu, G., Zeng, W., Wang, J., Tang, M.: Dpt: Deformable patch-based transformer for visual recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2899\u20132907 (2021)","DOI":"10.1145\/3474085.3475467"},{"key":"3893_CR33","doi-asserted-by":"crossref","unstructured":"Yue, X., Sun, S., Kuang, Z., Wei, M., Torr, P.H., Zhang, W., Lin, D.: Vision transformer with progressive sampling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 387\u2013396 (2021)","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"3893_CR34","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"issue":"5","key":"3893_CR35","doi-asserted-by":"publisher","first-page":"3123","DOI":"10.1109\/TPAMI.2023.3341806","volume":"46","author":"W Wang","year":"2024","unstructured":"Wang, W., Chen, W., Qiu, Q., Chen, L., Wu, B., Lin, B., He, X., Liu, W.: Crossformer++: a versatile vision transformer hinging on cross-scale attention. IEEE Trans. Patt. Anal. Mach. Intell. 46(5), 3123\u20133136 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2023.3341806","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"3893_CR36","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., Guo, B.: Cswin transformer: A general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"3893_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.: Biformer: Vision transformer with bi-level routing attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10323\u201310333 (2023)","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"3893_CR38","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":"3893_CR39","doi-asserted-by":"crossref","unstructured":"Yang, S., Quan, Z., Nie, M., Yang, W.: 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":"3893_CR40","unstructured":"Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., Wang, J.: Hrformer: High-resolution transformer for dense prediction. arXiv preprint arXiv:2110.09408 (2021)"},{"key":"3893_CR41","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: 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":"3893_CR42","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., Liang, R.: Afpn: Asymptotic feature pyramid network for object detection. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2184\u20132189 (2023)","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"3893_CR43","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection (2019). https:\/\/arxiv.org\/abs\/1911.09516"},{"key":"3893_CR44","doi-asserted-by":"crossref","unstructured":"Wang, D., Zhang, S.: Contextual instance decoupling for robust multi-person pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11060\u201311068 (2022)","DOI":"10.1109\/CVPR52688.2022.01078"},{"key":"3893_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, L., Huang, W., Zheng, J., Li, C., Wu, X., Xiang, B., Yang, J., Xu, D.: Edgepose: Real-time human pose estimation scheme for industrial scenes. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3446247"},{"key":"3893_CR46","doi-asserted-by":"crossref","unstructured":"Ye, S., Zhang, Y., Hu, J., Cao, L., Zhang, S., Shen, L., Wang, J., Ding, S., Ji, R.: Distilpose: Tokenized pose regression with heatmap distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2163\u20132172 (2023)","DOI":"10.1109\/CVPR52729.2023.00215"},{"key":"3893_CR47","doi-asserted-by":"crossref","unstructured":"Jiang, W., Jin, S., Liu, W., Qian, C., Luo, P., Liu, S.: Posetrans: A simple yet effective pose transformation augmentation for human pose estimation. In: European Conference on Computer Vision, pp. 643\u2013659 (2022)","DOI":"10.1007\/978-3-031-20065-6_37"},{"key":"3893_CR48","unstructured":"Yang, J., Zeng, A., Liu, S., Li, F., Zhang, R., Zhang, L.: Explicit box detection unifies end-to-end multi-person pose estimation. arXiv preprint arXiv:2302.01593 (2023)"},{"issue":"10","key":"3893_CR49","doi-asserted-by":"publisher","first-page":"12581","DOI":"10.1109\/TPAMI.2023.3282631","volume":"45","author":"K Li","year":"2023","unstructured":"Li, K., Wang, Y., Zhang, J., Gao, P., Song, G., Liu, Y., Li, H., Qiao, Y.: Uniformer: unifying convolution and self-attention for visual recognition. IEEE Trans. Patt. Anal. Mach. Intell. 45(10), 12581\u201312600 (2023)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"3893_CR50","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: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3893_CR51","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"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03893-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03893-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03893-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T12:01:40Z","timestamp":1757160100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03893-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,23]]},"references-count":51,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3893"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03893-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,23]]},"assertion":[{"value":"16 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare that they have no conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}