{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:58:36Z","timestamp":1768273116103,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":38,"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_34","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:31:55Z","timestamp":1768249915000},"page":"504-518","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UniPose: Unified Cross-Modality Pose Prior Propagation Towards RGB-D Data for\u00a0Weakly Supervised 3D Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Jinghong","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Changlong","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Haohong","family":"Kuang","sequence":"additional","affiliation":[]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Tingbing","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"34_CR1","unstructured":"Biswas, A., Admoni, H., Steinfeld, A.: Fast on-board 3D torso pose recovery and forecasting. In: Proceedings of the International Conference on Robotics and Automation (ICRA), pp. 20\u201324 (2019)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Cai, J., Yuan, J.: Weakly-supervised 3D hand pose estimation from monocular RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 666\u2013682 (2018)","DOI":"10.1007\/978-3-030-01231-1_41"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Lin, K.Y., Liu, W., Qian, C., Lin, L.: Weakly-supervised discovery of geometry-aware representation for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 10895\u201310904 (2019)","DOI":"10.1109\/CVPR.2019.01115"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Ge, L., Cai, Y., Weng, J., Yuan, J.: Hand PointNet: 3D hand pose estimation using point sets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8417\u20138426 (2018)","DOI":"10.1109\/CVPR.2018.00878"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Ge, L., Ren, Z., Yuan, J.: Point-to-point regression PointNet for 3D hand pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 475\u2013491 (2018)","DOI":"10.1007\/978-3-030-01261-8_29"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, G., Chen, X., Zhang, C.: Towards good practices for deep 3D hand pose estimation. arXiv preprint arXiv:1707.07248 (2017)","DOI":"10.1016\/j.jvcir.2018.04.005"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Haque, A., Peng, B., Luo, Z., Alahi, A., Yeung, S., Fei-Fei, L.: Towards viewpoint invariant 3D human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 160\u2013177 (2016)","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"34_CR8","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 (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"34_CR9","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.neucom.2015.02.068","volume":"164","author":"L He","year":"2015","unstructured":"He, L., Wang, G., Liao, Q., Xue, J.H.: Depth-images-based pose estimation using regression forests and graphical models. Neurocomputing 164, 210\u2013219 (2015)","journal-title":"Neurocomputing"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: A2J-Transformer: anchor-to-joint transformer network for 3D interacting hand pose estimation from a single RGB image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8846\u20138855 (2023)","DOI":"10.1109\/CVPR52729.2023.00854"},{"key":"34_CR11","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social interaction capture. IEEE Trans. Patt. Analy. Mach. Intell. (2017)"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Karagoz, S., Akbas, E.: Self-supervised learning of 3D human pose using multi-view geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1077\u20131086 (2019)","DOI":"10.1109\/CVPR.2019.00117"},{"issue":"4","key":"34_CR13","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","volume":"27","author":"J Liu","year":"2017","unstructured":"Liu, J., Wang, G., Duan, L.Y., Abdiyeva, K., Kot, A.C.: Skeleton-based human action recognition with global context-aware attention LSTM networks. IEEE Trans. Image Process. 27(4), 1586\u20131599 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1647\u20131656 (2017)","DOI":"10.1109\/CVPR.2017.391"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3d human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Mitra, R., Gundavarapu, N.B., Sharma, A., Jain, A.: Multiview-consistent semi-supervised learning for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6907\u20136916 (2020)","DOI":"10.1109\/CVPR42600.2020.00694"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: V2V-PoseNet: voxel-to-voxel prediction network for accurate 3d hand and human pose estimation from a single depth map. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5079\u20135088 (2018)","DOI":"10.1109\/CVPR.2018.00533"},{"key":"34_CR18","unstructured":"Obdr\u017e\u00e1lek, \u0160., Kurillo, G., Han, J., Abresch, T., Bajcsy, R.: Real-time human pose detection and tracking for tele-rehabilitation in virtual reality. In: Medicine Meets Virtual Reality, vol. 19, pp. 320\u2013324. IOS Press (2012)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"34_CR20","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Remelli, E., Han, S., Honari, S., Fua, P., Wang, R.: Lightweight multi-view 3D pose estimation through camera-disentangled representation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6040\u20136049 (2020)","DOI":"10.1109\/CVPR42600.2020.00608"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Schn\u00fcrer, T., Fuchs, S., Eisenbach, M., Gro\u00df, H.M.: Real-time 3D pose estimation from single depth images. In: VISIGRAPP (5: VISAPP), pp. 716\u2013724 (2019)","DOI":"10.5220\/0007394707160724"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+ d: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1297\u20131304 (2011)","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2107\u20132116 (2017)","DOI":"10.1109\/CVPR.2017.241"},{"key":"34_CR26","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":"34_CR27","doi-asserted-by":"crossref","unstructured":"Svenstrup, M., Tranberg, S., Andersen, H.J., Bak, T.: Pose estimation and adaptive robot behaviour for human-robot interaction. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 3571\u20133576 (2009)","DOI":"10.1109\/ROBOT.2009.5152690"},{"key":"34_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Wandt, B., Rosenhahn, B.: RepNet: weakly supervised training of an adversarial reprojection network for 3D human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7782\u20137791 (2019)","DOI":"10.1109\/CVPR.2019.00797"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Wang, K., Lin, L., Ren, C., Zhang, W., Sun, W.: Convolutional memory blocks for depth data representation learning. In: Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), pp. 2790\u20132797 (2018)","DOI":"10.24963\/ijcai.2018\/387"},{"key":"34_CR31","doi-asserted-by":"publisher","unstructured":"Wu, C., Xiao, Y., Zhang, B., Zhang, M., Cao, Z., Zhou, J.T.: C3P: cross-domain pose prior propagation for weakly supervised 3D human pose estimation. In: European Conference on Computer Vision, pp. 554\u2013571. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_32","DOI":"10.1007\/978-3-031-20065-6_32"},{"key":"34_CR32","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) (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Xiong, F., et al.: A2J: anchor-to-joint regression network for 3D articulated pose estimation from a single depth image. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 793\u2013802 (2019)","DOI":"10.1109\/ICCV.2019.00088"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, J., Tu, Z., Yang, J., Chen, Y., Yuan, J.: MIXSTE: Seq2Seq mixed SPATIO-temporal encoder for 3D human pose estimation in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13232\u201313242 (2022)","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"34_CR36","unstructured":"Zhao, Q., Zheng, C., Liu, M., Chen, C.: A single 2D pose with context is worth hundreds for 3D human pose estimation. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zheng, C., Liu, M., Wang, P., Chen, C.: PoseformerV2: exploring frequency domain for efficient and robust 3D human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8877\u20138886 (2023)","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"34_CR38","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)"}],"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_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:32:01Z","timestamp":1768249921000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_34","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"}}]}}