{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:38:21Z","timestamp":1742945901036,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784552"},{"type":"electronic","value":"9783031784569"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78456-9_12","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:24:33Z","timestamp":1733138673000},"page":"180-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Skeletal Triangulation for\u00a03D Human Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0870-5120","authenticated-orcid":false,"given":"YiHeng","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ZhiPeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YunLong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ChunYan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bartol, K., Bojani\u0107, D., Petkovi\u0107, T., Pribani\u0107, T.: Generalizable human pose triangulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11028\u201311037 (2022)","DOI":"10.1109\/CVPR52688.2022.01075"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Belagiannis, V., Amin, S., Andriluka, M., Schiele, B., Navab, N., Ilic, S.: 3d pictorial structures for multiple human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1669\u20131676 (2014)","DOI":"10.1109\/CVPR.2014.216"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., et\u00a0al.: Humman: multi-modal 4d human dataset for versatile sensing and modeling. In: European Conference on Computer Vision, pp. 557\u2013577. Springer, Heidelberg (2022)","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhao, X., Wan, X.: Structural triangulation: a closed-form solution to constrained 3d human pose estimation. In: European Conference on Computer Vision, pp. 695\u2013711. Springer, Heidelberg (2022)","DOI":"10.1007\/978-3-031-20065-6_40"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Ci, H., Wang, C., Ma, X., Wang, Y.: Optimizing network structure for 3d human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2262\u20132271 (2019)","DOI":"10.1109\/ICCV.2019.00235"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Dong, J., Fang, Q., Jiang, W., Yang, Y., Bao, H., Zhou, X.: Fast and robust multi-person 3d pose estimation and tracking from multiple views (2021)","DOI":"10.1109\/TPAMI.2021.3098052"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X.: Fast and robust multi-person 3d pose estimation from multiple views (2019)","DOI":"10.1109\/CVPR.2019.00798"},{"key":"12_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Gong, K., Zhang, J., Feng, J.: Poseaug: a differentiable pose augmentation framework for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8575\u20138584 (2021)","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"HanbyulJoo, T., XulongLi, H., LeiTan, L., SeanBanerjee, T.: Panoptic studio: a massively multiview system for social interaction capture. IEEE Trans. Pattern Anal. Mach. Intell. 41(1) (2019)","DOI":"10.1109\/TPAMI.2017.2782743"},{"key":"12_CR11","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)"},{"issue":"2","key":"12_CR12","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1006\/cviu.1997.0547","volume":"68","author":"RI Hartley","year":"1997","unstructured":"Hartley, R.I., Sturm, P.: Triangulation. Comput. Vis. Image Underst. 68(2), 146\u2013157 (1997)","journal-title":"Comput. Vis. Image Underst."},{"key":"12_CR13","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":"12_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., Yan, R., Fragkiadaki, K., Yu, S.I.: Epipolar transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7779\u20137788 (2020)","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., Malkov, Y.: Learnable triangulation of human pose. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7718\u20137727 (2019)","DOI":"10.1109\/ICCV.2019.00781"},{"key":"12_CR17","unstructured":"Ma, H., et al.: Transfusion: cross-view fusion with transformer for 3d human pose estimation. arXiv preprint arXiv:2110.09554 (2021)"},{"key":"12_CR18","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, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"issue":"4","key":"12_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., et al.: Vnect: real-time 3d human pose estimation with a single rgb camera. ACM Trans. Graph. (tog) 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph. (tog)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Harvesting multiple views for marker-less 3d human pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6988\u20136997 (2017)","DOI":"10.1109\/CVPR.2017.138"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Peng, J., Zhou, Y., Mok, P.: Ktpformer: kinematics and trajectory prior knowledge-enhanced transformer for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1123\u20131132 (2024)","DOI":"10.1109\/CVPR52733.2024.00113"},{"key":"12_CR22","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/j.neunet.2018.09.001","volume":"108","author":"AV Phan","year":"2018","unstructured":"Phan, A.V., Le Nguyen, M., Nguyen, Y.L.H., Bui, L.T.: Dgcnn: a convolutional neural network over large-scale labeled graphs. Neural Netw. 108, 533\u2013543 (2018)","journal-title":"Neural Netw."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Popa, A.I., Zanfir, M., Sminchisescu, C.: Deep multitask architecture for integrated 2d and 3d human sensing. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6289\u20136298 (2017)","DOI":"10.1109\/CVPR.2017.501"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Qiu, H., Wang, C., Wang, J., Wang, N., Zeng, W.: Cross view fusion for 3d human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4342\u20134351 (2019)","DOI":"10.1109\/ICCV.2019.00444"},{"key":"12_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1007\/978-3-030-58529-7_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Qiu","year":"2020","unstructured":"Qiu, L., et al.: Peeking into occluded joints: a novel framework for crowd pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 488\u2013504. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_29"},{"issue":"4","key":"12_CR26","doi-asserted-by":"publisher","first-page":"4122","DOI":"10.1109\/TPAMI.2022.3188716","volume":"45","author":"H Shuai","year":"2022","unstructured":"Shuai, H., Wu, L., Liu, Q.: Adaptive multi-view and temporal fusing transformer for 3d human pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4122\u20134135 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: 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":"12_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-030-58452-8_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Tu","year":"2020","unstructured":"Tu, H., Wang, C., Zeng, W.: VoxelPose: towards multi-camera 3D human pose estimation in wild environment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 197\u2013212. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_12"},{"key":"12_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"12_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103225","volume":"210","author":"J Wang","year":"2021","unstructured":"Wang, J., et al.: Deep 3d human pose estimation: a review. Comput. Vis. Image Underst. 210, 103225 (2021)","journal-title":"Comput. Vis. Image Underst."},{"key":"12_CR31","unstructured":"Wang, J., et al.: Freeman: towards benchmarking 3d human pose estimation in the wild. arXiv preprint arXiv:2309.05073 (2023)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Graph-based 3d multi-person pose estimation using multi-view images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11148\u201311157 (2021)","DOI":"10.1109\/ICCV48922.2021.01096"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Zhang, Z., Liu, Y., Zhong, S.H., Liu, Y., Chen, C.W.: Gla-gcn: global-local adaptive graph convolutional network for 3d human pose estimation from monocular video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8818\u20138829 (2023)","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"12_CR35","first-page":"13153","volume":"34","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Cai, Y., Yan, S., Feng, J., et al.: Direct multi-view multi-person 3d pose estimation. Adv. Neural. Inf. Process. Syst. 34, 13153\u201313164 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., Metaxas, D.N.: Semantic graph convolutional networks for 3d human pose regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Liu, Z., Liu, L., Wu, W., Wang, Y.: Motionbert: a unified perspective on learning human motion representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15085\u201315099 (2023)","DOI":"10.1109\/ICCV51070.2023.01385"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:10:29Z","timestamp":1733141429000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}