{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T08:44:02Z","timestamp":1766047442668,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["11772053","11727801"],"award-info":[{"award-number":["11772053","11727801"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s11554-022-01214-2","type":"journal-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T09:03:24Z","timestamp":1651136604000},"page":"703-713","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SimpleMeshNet: end to end recovery of 3d body mesh with one fully connected layer"],"prefix":"10.1007","volume":"19","author":[{"given":"Wenzhang","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaopeng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanfang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-8389","authenticated-orcid":false,"given":"Qinwei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,28]]},"reference":[{"key":"1214_CR1","doi-asserted-by":"publisher","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4501\u20134510 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00463","DOI":"10.1109\/cvpr.2019.00463"},{"key":"1214_CR2","doi-asserted-by":"publisher","unstructured":"Sun, Y., Ye, Y., Liu, W., Gao, W., Fu, Y., Mei, T.: Human mesh recovery from monocular images via a skeleton-disentangled representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5349\u20135358 (2019). https:\/\/doi.org\/10.1109\/iccv.2019.00545","DOI":"10.1109\/iccv.2019.00545"},{"key":"1214_CR3","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/cvpr.2018.00744","DOI":"10.1109\/cvpr.2018.00744"},{"key":"1214_CR4","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"1214_CR5","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/iccv.2019.00234","DOI":"10.1109\/iccv.2019.00234"},{"key":"1214_CR6","doi-asserted-by":"publisher","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: Video inference for human body pose and shape estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253\u20135263. (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00530","DOI":"10.1109\/cvpr42600.2020.00530"},{"key":"1214_CR7","doi-asserted-by":"publisher","unstructured":"Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM SIGGRAPH 2005 Papers, pp. 408\u2013416 (2005). https:\/\/doi.org\/10.1145\/1186822.1073207","DOI":"10.1145\/1186822.1073207"},{"issue":"6","key":"1214_CR8","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). https:\/\/doi.org\/10.1145\/2816795.2818013","journal-title":"ACM Trans. Graph."},{"key":"1214_CR9","doi-asserted-by":"publisher","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A.A., Black, M.J.: 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) https:\/\/doi.org\/10.1109\/cvpr.2019.01123","DOI":"10.1109\/cvpr.2019.01123"},{"key":"1214_CR10","doi-asserted-by":"publisher","unstructured":"Tan, J.K.V., Budvytis, I., Cipolla, R.: Indirect deep structured learning for 3d human body shape and pose prediction. In: British Machine Vision Conference (2017). https:\/\/doi.org\/10.5244\/c.31.15","DOI":"10.5244\/c.31.15"},{"key":"1214_CR11","unstructured":"Tung, H-Y.F., Tung, H-W., Yumer, E., Fragkiadaki, K.: Self-supervised learning of motion capture. arXiv Prepr. arXiv1712.01337 (2017)"},{"key":"1214_CR12","doi-asserted-by":"publisher","unstructured":"Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., Schiele, B.: Neural body fitting: unifying deep learning and model based human pose and shape estimation. In: 2018 International Conference on 3D vision (3DV),pp. 484\u2013494 (2018). https:\/\/doi.org\/10.1109\/3dv.2018.00062","DOI":"10.1109\/3dv.2018.00062"},{"key":"1214_CR13","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/cvpr.2018.00055","DOI":"10.1109\/cvpr.2018.00055"},{"key":"1214_CR14","doi-asserted-by":"publisher","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: European Conference on Computer Vision, pp. 561\u2013578 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"1214_CR15","doi-asserted-by":"publisher","unstructured":"Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Schiele, B.: Deepcut: joint subset partition and labeling for multi person pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929\u20134937 (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.533","DOI":"10.1109\/cvpr.2016.533"},{"key":"1214_CR16","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/cvpr.2017.500","DOI":"10.1109\/cvpr.2017.500"},{"key":"1214_CR17","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/cvpr.2019.01114","DOI":"10.1109\/cvpr.2019.01114"},{"key":"1214_CR18","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. arXiv Prepr. arXiv2012.09760 (2020)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"1214_CR19","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3d human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1214_CR20","doi-asserted-by":"publisher","unstructured":"Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Jain, A.: Structure-aware and temporally coherent 3d human pose estimation. arXiv Prepr. arXiv1711.09250, 3(4):6. https:\/\/doi.org\/10.1016\/j.patrec.2019.05.020 (2017)","DOI":"10.1016\/j.patrec.2019.05.020"},{"key":"1214_CR21","doi-asserted-by":"publisher","unstructured":"Hossain, M.R.I., Little, J.J.: Exploiting temporal information for 3d human pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 68\u201384 (2018). https:\/\/doi.org\/10.51202\/9783186869104-40","DOI":"10.51202\/9783186869104-40"},{"key":"1214_CR22","doi-asserted-by":"publisher","unstructured":"Mehta, D., Sotnychenko, O., Mueller, F., Xu, W., Elgharib, M., Theobalt, C.: Xnect: Real-time multi-person 3d human pose estimation with a single rgb camera. arXiv Prepr. arXiv1907.00837 (2019) https:\/\/doi.org\/10.1145\/3386569.3392410","DOI":"10.1145\/3386569.3392410"},{"issue":"4","key":"1214_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., Sridhar, S., Sotnychenko, O., Rhodin, H., Shafiei, M., Theobalt, C.: Vnect: Real-time 3d human pose estimation with a single rgb camera. ACM Trans. Graph. 36(4), 1\u201314 (2017). https:\/\/doi.org\/10.1145\/3072959.3073596","journal-title":"ACM Trans. Graph."},{"key":"1214_CR24","doi-asserted-by":"publisher","unstructured":"Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3D human pose estimation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3395\u20133404 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00351","DOI":"10.1109\/cvpr.2019.00351"},{"key":"1214_CR25","doi-asserted-by":"publisher","unstructured":"Huang, Y., Bogo, F., Lassner, C., Kanazawa, A., Gehler, P.V., Black, M.J.: Towards accurate marker-less human shape and pose estimation over time. In: 2017 International Conference on 3D vision (3DV), pp. 421\u2013430 (2017). https:\/\/doi.org\/10.1109\/3dv.2017.00055","DOI":"10.1109\/3dv.2017.00055"},{"key":"1214_CR26","doi-asserted-by":"publisher","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3d human dynamics from video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5614\u20135623 (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.00576","DOI":"10.1109\/cvpr.2019.00576"},{"key":"1214_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Polosukhin, I.: Attention is all you need. arXiv Prepr. arXiv1706.03762 (2017)"},{"key":"1214_CR28","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: European Conference on Computer Vision, pp. 630\u2013645 (2016). https:\/\/doi.org\/10.1109\/cvpr.2018.00466","DOI":"10.1109\/cvpr.2018.00466"},{"key":"1214_CR29","doi-asserted-by":"crossref","unstructured":"Luo, Z., Golestaneh, S.A., Kitani, K.M.: 3d human motion estimation via motion compression and refinement, In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69541-5_20"},{"key":"1214_CR30","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Chang, J.Y., Lee, K.M.: Beyond static features for temporally consistent 3d human pose and shape from a video, In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1964\u20131973 (2021)","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"1214_CR31","unstructured":"Doersch, C., Zisserman, A.: Sim2real transfer learning for 3D human pose estimation: motion to the rescue. arXiv Prepr. arXiv1907.02499 (2019)"},{"key":"1214_CR32","unstructured":"Shanyan G., Jingwei X., Yunbo W., Bingbing N., Xiaokang Y.: Bilevel online adaptation for out-of-Domain human mesh reconstruction. arXiv Prepr. arXiv2013.16449. ECCV (2021)"},{"issue":"6","key":"1214_CR33","doi-asserted-by":"publisher","first-page":"1","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), 1\u201313 (2014). https:\/\/doi.org\/10.1145\/2661229\/2661273","journal-title":"ACM Trans. Graph."},{"key":"1214_CR34","doi-asserted-by":"publisher","unstructured":"von Marcard, 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), 601\u2013617. 4, https:\/\/doi.org\/10.1007\/978-3-030-01249-6_37 (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"1214_CR35","unstructured":"Hanbyul, J., Natalia, N., Andrea V.: Exemplar Fine-Tuning for 3d human pose fitting towards in-the-wild 3d human pose estimation. arXiv preprint arXiv:2004.03686 (2020)"},{"key":"1214_CR36","doi-asserted-by":"publisher","unstructured":"Gyeongsik M., Kyoung M.L.: I2l-MeshNet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image. In: ECCV. https:\/\/doi.org\/10.1007\/978-3-030-58571-6_44 (2020)","DOI":"10.1007\/978-3-030-58571-6_44"},{"key":"1214_CR37","doi-asserted-by":"publisher","unstructured":"Hongsuk, C., Gyeongsik M., Kyoung M.L.: Pose2Mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose. In: ECCV, pp. 769\u2013787. https:\/\/doi.org\/10.1007\/978-3-030-58571-6_45 (2020)","DOI":"10.1007\/978-3-030-58571-6_45"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-022-01214-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-022-01214-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-022-01214-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T04:54:50Z","timestamp":1727067290000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-022-01214-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,28]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["1214"],"URL":"https:\/\/doi.org\/10.1007\/s11554-022-01214-2","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"type":"print","value":"1861-8200"},{"type":"electronic","value":"1861-8219"}],"subject":[],"published":{"date-parts":[[2022,4,28]]},"assertion":[{"value":"9 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}