{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:20:57Z","timestamp":1743110457674,"version":"3.40.3"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729690"},{"type":"electronic","value":"9783031729706"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-72970-6_25","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:51:36Z","timestamp":1732272696000},"page":"439-458","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-RoI Human Mesh Recovery with\u00a0Camera Consistency and\u00a0Contrastive Losses"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8922-3205","authenticated-orcid":false,"given":"Yongwei","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8802-0996","authenticated-orcid":false,"given":"Changzhen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1584-7290","authenticated-orcid":false,"given":"Chengjiang","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5312-2800","authenticated-orcid":false,"given":"Qing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4598-1522","authenticated-orcid":false,"given":"Guiqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2747-7234","authenticated-orcid":false,"given":"Hongmin","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"25_CR1","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":"25_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 of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8726\u20138737 (2023)","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"25_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":"25_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: SimCLR: a simple framework for contrastive learning of visual representations. In: International Conference on Learning Representations, vol.\u00a02 (2020)"},{"key":"25_CR5","unstructured":"Cheng, Y., Huang, S., Ning, J., Shan, Y.: BoPR: body-aware part regressor for human shape and pose estimation. arXiv preprint arXiv:2303.11675 (2023)"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Cho, J., Youwang, K., Oh, T.H.: Cross-attention of disentangled modalities for 3D human mesh recovery with transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 342\u2013359. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_20","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"25_CR7","doi-asserted-by":"publisher","unstructured":"Choi, H., Moon, G., Lee, K.M.: Pose2Mesh: graph convolutional network for 3D human pose and mesh recovery from a 2D human pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII 16, pp. 769\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_45","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Dou, Z., et al.: Tore: token reduction for efficient human mesh recovery with transformer. arXiv preprint arXiv:2211.10705 (2022)","DOI":"10.1109\/ICCV51070.2023.01390"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Fan, T., Alwala, K.V., Xiang, D., Xu, W., Murphey, T., Mukadam, M.: Revitalizing optimization for 3D human pose and shape estimation: a sparse constrained formulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11457\u201311466 (2021)","DOI":"10.1109\/ICCV48922.2021.01126"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Fang, Q., Chen, K., Fan, Y., Shuai, Q., Li, J., Zhang, W.: Learning analytical posterior probability for human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8781\u20138791 (2023)","DOI":"10.1109\/CVPR52729.2023.00848"},{"key":"25_CR11","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: Proceedings of the IEEE International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Guan, P., Weiss, A., Balan, A.O., Black, M.J.: Estimating human shape and pose from a single image. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1381\u20131388. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459300"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"25_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"25_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":"25_CR16","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. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00078"},{"key":"25_CR17","unstructured":"Jocher, G., et\u00a0al.: ultralytics\/yolov5: v7. 0-yolov5 sota realtime instance segmentation. Zenodo (2022)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human model fitting towards in-the-wild 3D human pose estimation. In: 2021 International Conference on 3D Vision (3DV), pp. 42\u201352. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"25_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Tripathi, S., Kitani, K.: Occluded human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1715\u20131725 (2022)","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"25_CR21","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"25_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-030-66096-3_37","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"I Kissos","year":"2020","unstructured":"Kissos, I., Fritz, L., Goldman, M., Meir, O., Oks, E., Kliger, M.: Beyond weak perspective for monocular 3D human pose estimation. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 541\u2013554. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66096-3_37"},{"key":"25_CR23","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 IEEE\/CVF International Conference on Computer Vision, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Tesch, J., M\u00fcller, L., Hilliges, O., Black, M.J.: SPEC: seeing people in the wild with an estimated camera. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11035\u201311045 (2021)","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"25_CR25","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\/CVF International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Li, J., Bian, S., Liu, Q., Tang, J., Wang, F., Lu, C.: Niki: neural inverse kinematics with invertible neural networks for 3D human pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12933\u201312942 (2023)","DOI":"10.1109\/CVPR52729.2023.01243"},{"key":"25_CR27","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":"25_CR28","doi-asserted-by":"publisher","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: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 590\u2013606. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_34","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., Oskarsson, M., Heyden, A.: 3D human pose and shape estimation through collaborative learning and multi-view model-fitting. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1888\u20131897 (2021)","DOI":"10.1109\/WACV48630.2021.00193"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Li, Z., Xu, B., Huang, H., Lu, C., Guo, Y.: Deep two-stream video inference for human body pose and shape estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 430\u2013439 (2022)","DOI":"10.1109\/WACV51458.2022.00071"},{"key":"25_CR31","unstructured":"Lin, K., Lin, C.C., Liang, L., Liu, Z., Wang, L.: MPT: mesh pre-training with transformers for human pose and mesh reconstruction. arXiv preprint arXiv:2211.13357 (2022)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12939\u201312948 (2021)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"25_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yang, J., Gu, X., Guo, Y., Yang, G.Z.: EgoHMR: egocentric human mesh recovery via hierarchical latent diffusion model. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 9807\u20139813. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161247"},{"issue":"6","key":"25_CR35","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1145\/2661229.2661273","volume":"33","author":"M Loper","year":"2014","unstructured":"Loper, M., Mahmood, N., Black, M.J.: Mosh: motion and shape capture from sparse markers. ACM Trans. Graph. 33(6), 220\u20131 (2014)","journal-title":"ACM Trans. Graph."},{"issue":"6","key":"25_CR36","doi-asserted-by":"publisher","first-page":"1","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. 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph."},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: The IEEE International Conference on Computer Vision (ICCV) (2019). https:\/\/amass.is.tue.mpg.de","DOI":"10.1109\/ICCV.2019.00554"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"issue":"1","key":"25_CR39","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"25_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-030-58571-6_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Lee, K.M.: I2L-MeshNet: image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 752\u2013768. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_44"},{"key":"25_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1007\/978-3-030-58539-6_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"AAA Osman","year":"2020","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: sparse trained articulated human body regressor. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 598\u2013613. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_36"},{"key":"25_CR42","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Malik, J., Kanazawa, A.: Human mesh recovery from multiple shots. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1485\u20131495 (2022)","DOI":"10.1109\/CVPR52688.2022.00154"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"25_CR45","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610 (2022)"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Sengupta, A., Budvytis, I., Cipolla, R.: Probabilistic 3D human shape and pose estimation from multiple unconstrained images in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16094\u201316104 (2021)","DOI":"10.1109\/CVPR46437.2021.01583"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Shetty, K., et al.: PLIKS: a pseudo-linear inverse kinematic solver for 3D human body estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 574\u2013584 (2023)","DOI":"10.1109\/CVPR52729.2023.00063"},{"key":"25_CR48","unstructured":"Shin, S., Halilaj, E.: Multi-view human pose and shape estimation using learnable volumetric aggregation. arXiv preprint arXiv:2011.13427 (2020)"},{"key":"25_CR49","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":"25_CR50","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Von\u00a0Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 601\u2013617 (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., Jiang, Y.G.: Pixel2Mesh: generating 3D mesh models from single RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 52\u201367 (2018)","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Zolly: zoom focal length correctly for perspective-distorted human mesh reconstruction. arXiv preprint arXiv:2303.13796 (2023)","DOI":"10.1109\/ICCV51070.2023.00363"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Wang, Y., Daniilidis, K.: Refit: recurrent fitting network for 3D human recovery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14644\u201314654 (2023)","DOI":"10.1109\/ICCV51070.2023.01346"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Xue, Y., Chen, J., Zhang, Y., Yu, C., Ma, H., Ma, H.: 3D human mesh reconstruction by learning to sample joint adaptive tokens for transformers. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6765\u20136773 (2022)","DOI":"10.1145\/3503161.3548133"},{"key":"25_CR56","unstructured":"Yao, P., Fang, Z., Wu, F., Feng, Y., Li, J.: DenseBody: directly regressing dense 3D human pose and shape from a single color image. arXiv preprint arXiv:1903.10153 (2019)"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Yoshiyasu, Y.: Deformable mesh transformer for 3D human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17006\u201317015 (2023)","DOI":"10.1109\/CVPR52729.2023.01631"},{"key":"25_CR58","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Skeleton2Mesh: kinematics prior injected unsupervised human mesh recovery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8619\u20138629 (2021)","DOI":"10.1109\/ICCV48922.2021.00850"},{"key":"25_CR59","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, pp. 11038\u201311049 (2022)","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"25_CR60","doi-asserted-by":"crossref","unstructured":"Zanfir, M., Zanfir, A., Bazavan, E.G., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: THUNDR: transformer-based 3D human reconstruction with markers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12971\u201312980 (2021)","DOI":"10.1109\/ICCV48922.2021.01273"},{"issue":"5","key":"25_CR61","first-page":"2610","volume":"44","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Cao, J., Lu, G., Ouyang, W., Sun, Z.: Learning 3D human shape and pose from dense body parts. IEEE Trans. Pattern Anal. Mach. Intell. 44(5), 2610\u20132627 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR62","doi-asserted-by":"publisher","first-page":"12287","DOI":"10.1109\/TPAMI.2023.3271691","volume":"45","author":"H Zhang","year":"2023","unstructured":"Zhang, H., et al.: PyMAF-X: towards well-aligned full-body model regression from monocular images. IEEE Trans. Pattern Anal. Mach. Intell. 45, 12287\u201312303 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR63","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\/CVF International Conference on Computer Vision, pp. 11446\u201311456 (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"25_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yu, D., Liew, J.H., Nie, X., Feng, J.: Body meshes as points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 546\u2013556 (2021)","DOI":"10.1109\/CVPR46437.2021.00061"},{"key":"25_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, S., Ma, Q., Zhang, Y., Aliakbarian, S., Cosker, D., Tang, S.: Probabilistic human mesh recovery in 3D scenes from egocentric views. arXiv preprint arXiv:2304.06024 (2023)","DOI":"10.1109\/ICCV51070.2023.00734"},{"key":"25_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, T., Huang, B., Wang, Y.: Object-occluded human shape and pose estimation from a single color image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7376\u20137385 (2020)","DOI":"10.1109\/CVPR42600.2020.00740"},{"issue":"4","key":"25_CR67","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1109\/TPAMI.2018.2816031","volume":"41","author":"X Zhou","year":"2018","unstructured":"Zhou, X., Zhu, M., Pavlakos, G., Leonardos, S., Derpanis, K.G., Daniilidis, K.: MonoCap: monocular human motion capture using a CNN coupled with a geometric prior. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 901\u2013914 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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\/978-3-031-72970-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T11:18:22Z","timestamp":1732274302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 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"}}]}}