{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:42:59Z","timestamp":1768272179099,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556755","type":"print"},{"value":"9789819556762","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5676-2_27","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:31:54Z","timestamp":1768249914000},"page":"400-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ViTRotPose: Light-Weight Human Pose Estimation Based On Vision Transformer and\u00a0Rotational Position Coding"],"prefix":"10.1007","author":[{"given":"Zhaoli","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Jikai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xianghao","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Chenjie","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"issue":"11","key":"27_CR1","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.1007\/s11263-023-01842-6","volume":"131","author":"W Lin","year":"2023","unstructured":"Lin, W., et al.: HiEve: a large-scale benchmark for human-centric video analysis in complex events. Int. J. Comput. Vision 131(11), 2994\u20133018 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR2","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"},{"issue":"9","key":"27_CR3","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1007\/s11263-021-01482-8","volume":"129","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Chen, Z., Tao, D.: Towards high performance human keypoint detection. Int. J. Comput. Vision 129(9), 2639\u20132662 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR4","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":"27_CR5","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation. Adv. Neural. Inf. Process. Syst. 35, 38571\u201338584 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR6","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":"27_CR7","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: 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":"27_CR8","unstructured":"Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., Grundmann, M.: BlazePose: on-device real-time body pose tracking. arXiv preprint arXiv:2006.10204 (2020)"},{"key":"27_CR9","unstructured":"Votel, R., Li, N., et\u00a0al.: Next-generation pose detection with moveNet and TensorFlow. js. TensorFlow Blog 4(4) (2021)"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Yu, 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"},{"key":"27_CR11","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":"27_CR12","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":"27_CR13","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":"27_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: SimCC: a simple coordinate classification perspective for human pose estimation. In: European Conference on Computer Vision, pp. 89\u2013106. Springer (2022)","DOI":"10.1007\/978-3-031-20068-7_6"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: 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. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"27_CR16","unstructured":"Yu, H., Xu, Y., Zhang, J., Zhao, W., Guan, Z., Tao, D.: AP-10K: a benchmark for animal pose estimation in the wild. arXiv preprint arXiv:2108.12617 (2021)"},{"key":"27_CR17","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":"27_CR18","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: 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":"27_CR19","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":"27_CR20","unstructured":"Jiang, T., et al.: RTMPose: real-time multi-person pose estimation based on MMpose. arXiv preprint arXiv:2303.07399 (2023)"},{"key":"27_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129154","volume":"619","author":"Z Xu","year":"2025","unstructured":"Xu, Z., Dai, M., Zhang, Q., Jiang, X.: HRPVT: high-resolution pyramid vision transformer for medium and small-scale human pose estimation. Neurocomputing 619, 129154 (2025)","journal-title":"Neurocomputing"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Jin, S., et al.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII 16, pp. 718\u2013734. Springer (2020)","DOI":"10.1007\/978-3-030-58571-6_42"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: Learning delicate local representations for multi-person pose estimation. In: European Conference on Computer Vision, pp. 455\u2013472. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_27"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, F., Fan, X., Huang, D.: Polarized self-attention: towards high-quality pixel-wise regression. arXiv preprint arXiv:2107.00782 (2021)","DOI":"10.1016\/j.neucom.2022.07.054"},{"key":"27_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Info. Process. Syst. 30 (2017)"},{"key":"27_CR27","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, pp. 1491\u20131500 (2024)","DOI":"10.1109\/CVPR52733.2024.00148"},{"key":"27_CR28","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":"27_CR29","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Lin, Z., Han, J., Ding, G.: RepViT: revisiting mobile CNN from ViT perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15909\u201315920 (2024)","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: 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":"27_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"27_CR32","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: International Conference on Machine Learning, pp. 5156\u20135165. PMLR (2020)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Yang, J., Liu, S., Wu, J., Su, X., Hai, N., Huang, X.: Pinwheel-shaped convolution and scale-based dynamic loss for infrared small target detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 9202\u20139210 (2025)","DOI":"10.1609\/aaai.v39i9.32996"},{"key":"27_CR34","unstructured":"Contributors, M.: OpenMMlab Pose Estimation Toolbox and Benchmark (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5676-2_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:00Z","timestamp":1768249920000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}