{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:13Z","timestamp":1777567513288,"version":"3.51.4"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726545","type":"print"},{"value":"9783031726552","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"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\/978-3-031-72655-2_20","type":"book-chapter","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:13:22Z","timestamp":1733393602000},"page":"343-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["WorldPose: A World Cup Dataset for\u00a0Global 3D Human Pose Estimation"],"prefix":"10.1007","author":[{"given":"Tianjian","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Johsan","family":"Billingham","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"M\u00fcksch","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Zarate","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Evans","sequence":"additional","affiliation":[]},{"given":"Martin R.","family":"Oswald","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Polleyfeys","sequence":"additional","affiliation":[]},{"given":"Otmar","family":"Hilliges","sequence":"additional","affiliation":[]},{"given":"Manuel","family":"Kaufmann","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"20_CR1","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":"20_CR2","doi-asserted-by":"crossref","unstructured":"Black, M.J., Patel, P., Tesch, J., Yang, J.: BEDLAM: a synthetic dataset of bodies exhibiting detailed lifelike animated motion. In: Proceedings IEEE\/CVF Conference\u00a0on Computer Vision and Pattern Recognition (CVPR), pp. 8726\u20138737 (2023)","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"20_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Little, J.J.: Sports camera calibration via synthetic data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00305"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Cho, J., Youwang, K., Oh, T.H.: Cross-attention of disentangled modalities for 3D human mesh recovery with transformers. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Choudhury, R., Kitani, K.M., Jeni, L.A.: Tempo: efficient multi-view pose estimation, tracking, and forecasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14750\u201314760 (2023)","DOI":"10.1109\/ICCV51070.2023.01355"},{"issue":"3","key":"20_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-020-01064-7","volume":"31","author":"L Citraro","year":"2020","unstructured":"Citraro, L., et al.: Real-time camera pose estimation for sports fields. Mach. Vis. Appl. 31(3), 1\u201313 (2020). https:\/\/doi.org\/10.1007\/s00138-020-01064-7","journal-title":"Mach. Vis. Appl."},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Y., et al.: Sloper4D: a scene-aware dataset for global 4D human pose estimation in urban environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 682\u2013692 (2023)","DOI":"10.1109\/CVPR52729.2023.00073"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Deliege, A., et al.: Soccernet-v2: a dataset and benchmarks for holistic understanding of broadcast soccer videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4508\u20134519 (2021)","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"20_CR10","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7792\u20137801 (2019)","DOI":"10.1109\/CVPR.2019.00798"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Dong, Z., Song, J., Chen, X., Guo, C., Hilliges, O.: Shape-aware multi-person pose estimation from multi-view images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11158\u201311168 (2021)","DOI":"10.1109\/ICCV48922.2021.01097"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Fieraru, M., Zanfir, M., Oneata, E., Popa, A.I., Olaru, V., Sminchisescu, C.: Three-dimensional reconstruction of human interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7214\u20137223 (2020)","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"20_CR13","unstructured":"FreePik: Designed by Freepik (2023). https:\/\/www.freepik.com\/. Accessed 16 Nov 2023"},{"issue":"4","key":"20_CR14","first-page":"5","volume":"52","author":"S Geman","year":"1987","unstructured":"Geman, S., McClure, D.E.: Statistical methods for tomographic image reconstruction. Bull. Int. Stat. Inst. 52(4), 5\u201321 (1987)","journal-title":"Bull. Int. Stat. Inst."},{"key":"20_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/978-3-319-46843-3_8","volume-title":"Human Behavior Understanding","author":"C van Gemeren","year":"2016","unstructured":"van Gemeren, C., Poppe, R., Veltkamp, R.C.: Spatio-temporal detection of fine-grained dyadic human interactions. In: Chetouani, M., Cohn, J., Salah, A.A. (eds.) HBU 2016. LNCS, vol. 9997, pp. 116\u2013133. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46843-3_8"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Giancola, S., Amine, M., Dghaily, T., Ghanem, B.: Soccernet: a scalable dataset for action spotting in soccer videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1711\u20131721 (2018)","DOI":"10.1109\/CVPRW.2018.00223"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., Malik, J.: Humans in 4D: reconstructing and tracking humans with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3D human pose ambiguities with 3D scene constraints. In: International Conference on Computer Vision (2019). https:\/\/prox.is.tue.mpg.de","DOI":"10.1109\/ICCV.2019.00237"},{"key":"20_CR19","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1007\/978-3-031-19842-7_38","volume-title":"ECCV 2022","author":"DF Henning","year":"2022","unstructured":"Henning, D.F., Laidlow, T., Leutenegger, S.: BodySLAM: joint camera localisation, mapping, and human motion tracking. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, pp. 656\u2013673. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_38"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Homayounfar, N., Fidler, S., Urtasun, R.: Sports field localization via deep structured models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5212\u20135220 (2017)","DOI":"10.1109\/CVPR.2017.427"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Huang, B., Ju, J., Li, Z., Wang, Y.: Reconstructing groups of people with hypergraph relational reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14873\u201314883 (2023)","DOI":"10.1109\/ICCV51070.2023.01366"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Huang, C.H.P., et al.: Capturing and inferring dense full-body human-scene contact. In: Proceedings IEEE\/CVF Conference\u00a0on Computer Vision and Pattern Recognition (CVPR), pp. 13274\u201313285 (2022)","DOI":"10.1109\/CVPR52688.2022.01292"},{"issue":"7","key":"20_CR23","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","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 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Xie, K., Guo, Y., Kautz, J., Molchanov, P.: Kama: 3D keypoint aware body mesh articulation. In: 2021 International Conference on 3D Vision (3DV), pp. 689\u2013699 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233423487","DOI":"10.1109\/3DV53792.2021.00078"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social motion capture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3334\u20133342 (2015)","DOI":"10.1109\/ICCV.2015.381"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Kaufmann, M., et al.: EMDB: the electromagnetic database of global 3D human pose and shape in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14632\u201314643 (2023)","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Kazemi, V., Burenius, M., Azizpour, H., Sullivan, J.: Multi-view body part recognition with random forests. In: British Machine Vision Conference (2013). https:\/\/api.semanticscholar.org\/CorpusID:17823362","DOI":"10.5244\/C.27.48"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Bansal, A., Ma, L., Newcombe, R., Vo, M., Kitani, K.: Ego-humans: an ego-centric 3d multi-human benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19807\u201319819 (2023)","DOI":"10.1109\/ICCV51070.2023.01814"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: video inference for human body pose and shape estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: part attention regressor for 3D human body estimation. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Kocabas, M., et al.: Pace: human and motion estimation from in-the-wild videos. In: 3DV (2024)","DOI":"10.1109\/3DV62453.2024.00103"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: closing the loop between 3D and 2D human representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6050\u20136059 (2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Coordinate transformer: achieving single-stage multi-person mesh recovery from videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8744\u20138753 (2023)","DOI":"10.1109\/ICCV51070.2023.00803"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., Lu, C.: Hybrik: a hybrid analytical-neural inverse kinematics solution for 3D human pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3383\u20133393 (2021)","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, J., Zhang, Z., Xu, S., Yan, Y.: Cliff: carrying location information in full frames into human pose and shape estimation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20065-6_34"},{"issue":"6","key":"20_CR38","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 248 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"von Marcard, T., Henschel, R., Black, M., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using imus and a moving camera. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"20_CR40","doi-asserted-by":"publisher","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 Fifth International Conference on 3D Vision (3DV). IEEE (2017). https:\/\/doi.org\/10.1109\/3dv.2017.00064. http:\/\/gvv.mpi-inf.mpg.de\/3dhp_dataset","DOI":"10.1109\/3dv.2017.00064"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3D pose estimation from monocular RGB. In: 2018 International Conference on 3D Vision (3DV), pp. 120\u2013130. IEEE (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Park, S., You, E., Lee, I., Lee, J.: Towards robust and smooth 3D multi-person pose estimation from monocular videos in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14772\u201314782 (2023)","DOI":"10.1109\/ICCV51070.2023.01357"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"20_CR44","unstructured":"Puwein, J.: Camera calibration and human pose estimation for sports broadcasts and human performances. Ph.D. thesis, ETH Zurich (2014)"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Puwein, J., Ziegler, R., Ballan, L., Pollefeys, M.: PTZ camera network calibration from moving people in sports broadcasts. In: 2012 IEEE Workshop on the Applications of Computer Vision (WACV), pp. 25\u201332. IEEE (2012)","DOI":"10.1109\/WACV.2012.6163030"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Puwein, J., Ziegler, R., Vogel, J., Pollefeys, M.: Robust multi-view camera calibration for wide-baseline camera networks. In: 2011 IEEE Workshop on Applications of Computer Vision (WACV), pp. 321\u2013328. IEEE (2011)","DOI":"10.1109\/WACV.2011.5711521"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Rematas, K., Kemelmacher-Shlizerman, I., Curless, B., Seitz, S.: Soccer on your tabletop. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4738\u20134747 (2018)","DOI":"10.1109\/CVPR.2018.00498"},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., Guibas, L.J.: Humor: 3D human motion model for robust pose estimation. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Sha, L., Hobbs, J., Felsen, P., Wei, X., Lucey, P., Ganguly, S.: End-to-end camera calibration for broadcast videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13627\u201313636 (2020)","DOI":"10.1109\/CVPR42600.2020.01364"},{"issue":"1","key":"20_CR50","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal, L., Balan, A., Black, M.: Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. (IJCV) 87(1), 4\u201327 (2010)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"20_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-58565-5_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Song","year":"2020","unstructured":"Song, J., Chen, X., Hilliges, O.: Human body model fitting by learned gradient descent. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 744\u2013760. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_44"},{"key":"20_CR52","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Michael\u00a0J.B., Mei, T.: Monocular, one-stage, regression of multiple 3D people. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"20_CR53","doi-asserted-by":"publisher","unstructured":"Sun, Y., Bao, Q., Liu, W., Mei, T., Black, M.J.: Trace: 5D temporal regression of avatars with dynamic cameras in 3D environments. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8856\u20138866 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00855","DOI":"10.1109\/CVPR52729.2023.00855"},{"key":"20_CR54","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, W., Bao, Q., Fu, Y., Mei, T., Black, M.J.: Putting people in their place: monocular regression of 3D people in depth. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"20_CR55","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras. In: Advances in Neural Information Processing Systems (2021)"},{"key":"20_CR56","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.cviu.2017.04.011","volume":"159","author":"G Thomas","year":"2017","unstructured":"Thomas, G., Gade, R., Moeslund, T.B., Carr, P., Hilton, A.: Computer vision for sports: current applications and research topics. Comput. Vis. Image Underst. 159, 3\u201318 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"20_CR57","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":"20_CR58","unstructured":"Vicon: Vicon Motion Systems Ltd UK (2022). https:\/\/www.vicon.com\/. Accessed 10 Apr"},{"key":"20_CR59","unstructured":"Vizrt: Viz Arena, AR Graphics and Virtual Advertising (2023). https:\/\/www.vizrt.com\/products\/viz-arena\/. Accessed 16 Nov 2023"},{"key":"20_CR60","doi-asserted-by":"publisher","unstructured":"Wei, W.L., Lin, J.C., Liu, T.L., Liao, H.Y.M.: Capturing humans in motion: temporal-attentive 3D human pose and shape estimation from monocular video. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13201\u201313210 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01286","DOI":"10.1109\/CVPR52688.2022.01286"},{"key":"20_CR61","unstructured":"Wen, G., Xiaoyu, B., Xavier, A.P., Francesc, M.N.: Multi-person extreme motion prediction. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)"},{"key":"20_CR62","doi-asserted-by":"crossref","unstructured":"Wen, H., et al.: Crowd3D: towards hundreds of people reconstruction from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8937\u20138946 (2023)","DOI":"10.1109\/CVPR52729.2023.00863"},{"key":"20_CR63","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation. In: Advances in Neural Information Processing Systems (2022)"},{"key":"20_CR64","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-031-20068-7_9","volume-title":"ECCV 2022","author":"H Ye","year":"2022","unstructured":"Ye, H., Zhu, W., Wang, C., Wu, R., Wang, Y.: Faster VoxelPose: real-time 3D human pose estimation by orthographic projection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13666, pp. 142\u2013159. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20068-7_9"},{"key":"20_CR65","doi-asserted-by":"crossref","unstructured":"Ye, V., Pavlakos, G., Malik, J., Kanazawa, A.: Decoupling human and camera motion from videos in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21222\u201321232 (2023)","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"20_CR66","doi-asserted-by":"crossref","unstructured":"Yin, Y., Guo, C., Kaufmann, M., Zarate, J., Song, J., Hilliges, O.: HI4D: 4D instance segmentation of close human interaction. In: Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"20_CR67","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Iqbal, U., Molchanov, P., Kitani, K., Kautz, J.: GLAMR: global occlusion-aware human mesh recovery with dynamic cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"20_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: PyMAF: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: Proceedings of the IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"20_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Egobody: human body shape and motion of interacting people from head-mounted devices. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"20_CR70","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20047-2_1","volume-title":"ECCV 2022","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_1"},{"issue":"2","key":"20_CR71","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1109\/TPAMI.2022.3163709","volume":"45","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Wang, C., Wang, X., Liu, W., Zeng, W.: Voxeltrack: multi-person 3D human pose estimation and tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2613\u20132626 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, Y., An, L., Yu, T., Li, X., Li, K., Liu, Y.: 4D association graph for realtime multi-person motion capture using multiple video cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1324\u20131333 (2020)","DOI":"10.1109\/CVPR42600.2020.00140"},{"issue":"11","key":"20_CR73","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/34.888718","volume":"22","author":"Z Zhang","year":"2000","unstructured":"Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330\u20131334 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Quickpose: real-time multi-view multi-person pose estimation in crowded scenes. In: ACM SIGGRAPH 2022 Conference Proceedings, pp.\u00a01\u20139 (2022)","DOI":"10.1145\/3528233.3530746"},{"key":"20_CR75","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-58558-7_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Zhu","year":"2020","unstructured":"Zhu, L., Rematas, K., Curless, B., Seitz, S.M., Kemelmacher-Shlizerman, I.: Reconstructing NBA players. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 177\u2013194. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_11"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72655-2_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T11:32:45Z","timestamp":1733398365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72655-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"ISBN":["9783031726545","9783031726552"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72655-2_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"6 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}