{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:33:13Z","timestamp":1777656793439,"version":"3.51.4"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726392","type":"print"},{"value":"9783031726408","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-72640-8_27","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"481-497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Global-To-Pixel Regression for\u00a0Human Mesh Recovery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7135-2140","authenticated-orcid":false,"given":"Yabo","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2896-4595","authenticated-orcid":false,"given":"Mingshu","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongdong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"27_CR1","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":"27_CR2","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: European Conference on Computer Vision, pp. 342\u2013359. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_20","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"27_CR3","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1007\/978-3-030-58571-6_45","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII","author":"H Choi","year":"2020","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, J.-M. (eds.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII, pp. 769\u2013787. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_45"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14676\u201314686 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., Malik, J.: Humans in 4D: Reconstructing and tracking humans with transformers. arXiv preprint arXiv:2305.20091 (2023)","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Guler, R.A., Kokkinos, I.: Holopose: Holistic 3d human reconstruction in-the-wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10884\u201310894 (2019)","DOI":"10.1109\/CVPR.2019.01114"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"27_CR8","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":"27_CR9","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":"27_CR10","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":"27_CR11","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":"27_CR12","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":"27_CR13","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":"27_CR14","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":"27_CR15","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":"27_CR16","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":"27_CR17","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"27_CR18","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":"27_CR19","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","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.) Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, pp. 740\u2013755. Springer International Publishing, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. In: Seminal Graphics Papers: Pushing the Boundaries, Volume 2, pp. 851\u2013866 (2023)","DOI":"10.1145\/3596711.3596800"},{"key":"27_CR21","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"},{"key":"27_CR22","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":"27_CR23","doi-asserted-by":"crossref","unstructured":"Muller, L., Osman, A.A., Tang, S., Huang, C.H.P., Black, M.J.: On self-contact and human pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9990\u20139999 (2021)","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"27_CR24","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":"27_CR25","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":"27_CR26","doi-asserted-by":"crossref","unstructured":"Shetty, K., et al.: 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":"27_CR27","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-58565-5_44","volume-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX","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.) Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XX, pp. 744\u2013760. Springer International Publishing, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_44"},{"key":"27_CR28","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":"27_CR29","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"27_CR30","unstructured":"Tung, H.Y., Tung, H.W., Yumer, E., Fragkiadaki, K.: Self-supervised learning of motion capture. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR31","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":"27_CR32","doi-asserted-by":"crossref","unstructured":"Xiang, D., Joo, H., Sheikh, Y.: Monocular total capture: posing face, body, and hands in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310974 (2019)","DOI":"10.1109\/CVPR.2019.01122"},{"key":"27_CR33","first-page":"12464","volume":"35","author":"Y Xiao","year":"2022","unstructured":"Xiao, Y., et al.: Querypose: sparse multi-person pose regression via spatial-aware part-level query. Adv. Neural. Inf. Process. Syst. 35, 12464\u201312477 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Wang, X.J., Yu, D., Wang, G., Zhang, Q., Mingshu, H.: Adaptivepose: human parts as adaptive points. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2813\u20132821 (2022)","DOI":"10.1609\/aaai.v36i3.20185"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Yu, D., Wang, X.J., Jin, L., Wang, G., Zhang, Q.: Learning quality-aware representation for multi-person pose regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2822\u20132830 (2022)","DOI":"10.1609\/aaai.v36i3.20186"},{"issue":"5","key":"27_CR36","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":"27_CR37","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":"27_CR38","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"27_CR39","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","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72640-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:51:22Z","timestamp":1730109082000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}