{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:14:44Z","timestamp":1782317684152,"version":"3.54.5"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73337-6_12","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"202-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Multi-HMR: Multi-person Whole-Body Human Mesh Recovery in\u00a0a\u00a0Single Shot"],"prefix":"10.1007","author":[{"given":"Fabien","family":"Baradel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthieu","family":"Armando","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salma","family":"Galaaoui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romain","family":"Br\u00e9gier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe","family":"Weinzaepfel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gr\u00e9gory","family":"Rogez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Lucas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"12_CR1","unstructured":"Blender. https:\/\/www.blender.org\/"},{"key":"12_CR2","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"12_CR3","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"12_CR4","unstructured":"Cai, Z., et\u00a0al.: SMPLer-X: scaling up expressive human pose and shape estimation. In: NeurIPS (2023)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Park, J., Lee, K.M.: Learning to estimate robust 3D human mesh from in-the-wild crowded scenes. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00153"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M.J.: Monocular expressive body regression through body-driven attention. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58607-2_2"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"De\u00a0Santis, A., Siciliano, B., De\u00a0Luca, A., Bicchi, A.: An atlas of physical human\u2013robot interaction. Mechanism and Machine Theory (2008)","DOI":"10.1016\/j.mechmachtheory.2007.03.003"},{"key":"12_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Facil, J.M., Ummenhofer, B., Zhou, H., Montesano, L., Brox, T., Civera, J.: CAM-Convs: camera-aware multi-scale convolutions for single-view depth. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01210"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Feng, Y., Choutas, V., Bolkart, T., Tzionas, D., Black, M.J.: Collaborative regression of expressive bodies using moderation. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"12_CR12","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":"12_CR13","doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR16","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. PAMI (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"12_CR17","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: ICML (2021)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, W., Kolotouros, N., Pavlakos, G., Zhou, X., Daniilidis, K.: Coherent reconstruction of multiple humans from a single image. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"12_CR19","unstructured":"Jocher, G., et al.: ultralytics\/YOLOv5: v7.0 - YOLOv5 SOTA realtime instance segmentation (2022)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Joo, H., et al.: Panoptic studio: a massively multiview system for social motion capture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.381"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human pose fitting towards in-the-wild 3D human pose estimation. In: 3DV (2020)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"12_CR22","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Kim, J., Gwon, M.G., Park, H., Kwon, H., Um, G.M., Kim, W.: Sampling is matter: point-guided 3D human mesh reconstruction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01238"},{"key":"12_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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"12_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: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"12_CR26","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1007\/978-3-031-20065-6_34","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part V","author":"Z Li","year":"2022","unstructured":"Li, Z., Liu, J., Zhang, Z., Xu, S., Yan, Y.: CLIFF: carrying location information in\u00a0full frames into\u00a0human pose and\u00a0shape estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part V, pp. 590\u2013606. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20065-6_34"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., Zhang, L., Li, Y.: One-stage 3D whole-body mesh recovery with component aware transformer. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"12_CR28","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Ma, X., Su, J., Wang, C., Zhu, W., Wang, Y.: 3D human mesh estimation from virtual markers. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00059"},{"key":"12_CR31","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: ECCV (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: XNect: real-time multi-person 3D motion capture with a single RGB camera. ACM Trans. Graph (2020)","DOI":"10.1145\/3386569.3392410"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Single-shot multi-person 3d pose estimation from monocular RGB. In: 3DV (2018)","DOI":"10.1109\/3DV.2018.00024"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Mertan, A., Duff, D.J., Unal, G.: Single image depth estimation: an overview. Digital Signal Process. (2022)","DOI":"10.1016\/j.dsp.2022.103441"},{"key":"12_CR35","doi-asserted-by":"crossref","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. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Chun, S., Lee, J., Yun, S.: Three recipes for better 3D pseudo-GTs of 3D human mesh estimation in the wild. In: CVPR Workshop (2023)","DOI":"10.1109\/CVPRW59228.2023.00276"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Lee, K.M.: Accurate 3D hand pose estimation for whole-body 3D human mesh estimation. In: CVPR Worskhop (2022)","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Moon, G., Choi, H., Lee, K.M.: NeuralAnnot: neural annotator for 3D human mesh training sets. In: CVPR Worskhop (2022)","DOI":"10.1109\/CVPRW56347.2022.00256"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Moon, G., Yu, S.I., Wen, H., Shiratori, T., Lee, K.M.: InterHand2.6M: a dataset and baseline for 3D interacting hand pose estimation from a single RGB image. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"12_CR40","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. TMLR (2023)"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Patel, P., Huang, C.H.P., Tesch, J., Hoffmann, D.T., Tripathi, S., Black, M.J.: AGORA: avatars in geography optimized for regression analysis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Qiu, Z., et al.: PSVT: end-to-end multi-person 3D pose and shape estimation with progressive video transformers. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02036"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yang, Q., Wang, J., Fu, D.: Dynamic graph reasoning for multi-person 3D pose estimation. In: ACMMM (2022)","DOI":"10.1145\/3503161.3547846"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Feichtenhofer, C., Malik, J.: On the benefits of 3D pose and tracking for human action recognition. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00069"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Rajasegaran, J., Pavlakos, G., Kanazawa, A., Malik, J.: Tracking people by predicting 3D appearance, location and pose. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00276"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: FrankMocap: a monocular 3D whole-body pose estimation system via regression and integration. In: ICCV (2021)","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Salzmann, T., Chiang, H.T.L., Ryll, M., Sadigh, D., Parada, C., Bewley, A.: Robots that can see: leveraging human pose for trajectory prediction. IEEE RAL (2023)","DOI":"10.1109\/LRA.2023.3312035"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Shah, A., Mishra, S., Bansal, A., Chen, J.C., Chellappa, R., Shrivastava, A.: Pose and joint-aware action recognition. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00022"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M.J., Mei, T.: Monocular, one-stage, regression of multiple 3D people. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"12_CR52","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":"12_CR53","doi-asserted-by":"crossref","unstructured":"Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.492"},{"key":"12_CR54","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. PAMI (2020)"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., et al.: CroCo v2: improved cross-view completion pre-training for stereo matching and optical flow. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01647"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Synbody: synthetic dataset with layered human models for 3D human perception and modeling. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01855"},{"key":"12_CR57","doi-asserted-by":"crossref","unstructured":"Yoshiyasu, Y.: Deformable mesh transformer for 3D human mesh recovery. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01631"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: PyMAF-X: towards well-aligned full-body model regression from monocular images. IEEE Trans. PAMI (2023)","DOI":"10.1109\/TPAMI.2023.3271691"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: PyMAF: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Zhen, J., et al.: SMAP: single-shot multi-person absolute 3D pose estimation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58555-6_33"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Zheng, C., Liu, X., Qi, G.J., Chen, C.: POTTER: pooling attention transformer for efficient human mesh recovery. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00161"},{"key":"12_CR62","unstructured":"Zhou, L., Meng, X., Liu, Z., Wu, M., Gao, Z., Wang, P.: Human pose-based estimation, tracking and action recognition with deep learning: a survey. arXiv preprint arXiv:2310.13039 (2023)"},{"key":"12_CR63","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Habermann, M., Habibie, I., Tewari, A., Theobalt, C., Xu, F.: Monocular real-time full body capture with inter-part correlations. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00478"}],"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\/978-3-031-73337-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:05:12Z","timestamp":1730329512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}