{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:04:56Z","timestamp":1773860696792,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001807","name":"S\u00e3o Paulo Research Foundation","doi-asserted-by":"publisher","award":["2022\/07055-4"],"award-info":[{"award-number":["2022\/07055-4"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"S\u00e3o Paulo Research Foundation","doi-asserted-by":"publisher","award":["2021\/02028-6"],"award-info":[{"award-number":["2021\/02028-6"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"S\u00e3o Paulo Research Foundation","doi-asserted-by":"publisher","award":["2662\/2017"],"award-info":[{"award-number":["2662\/2017"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Petrobras\/Fundunesp","award":["2022\/07055-4"],"award-info":[{"award-number":["2022\/07055-4"]}]},{"name":"Petrobras\/Fundunesp","award":["2021\/02028-6"],"award-info":[{"award-number":["2021\/02028-6"]}]},{"name":"Petrobras\/Fundunesp","award":["2662\/2017"],"award-info":[{"award-number":["2662\/2017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human pose estimation is an important Computer Vision problem, whose goal is to estimate the human body through joints. Currently, methods that employ deep learning techniques excel in the task of 2D human pose estimation. However, the use of 3D poses can bring more accurate and robust results. Since 3D pose labels can only be acquired in restricted scenarios, fully convolutional methods tend to perform poorly on the task. One strategy to solve this problem is to use 2D pose estimators, to estimate 3D poses in two steps using 2D pose inputs. Due to database acquisition constraints, the performance improvement of this strategy can only be observed in controlled environments, therefore domain adaptation techniques can be used to increase the generalization capability of the system by inserting information from synthetic domains. In this work, we propose a novel method called Domain Unified approach, aimed at solving pose misalignment problems on a cross-dataset scenario, through a combination of three modules on top of the pose estimator: pose converter, uncertainty estimator, and domain classifier. Our method led to a 44.1mm (29.24%) error reduction, when training with the SURREAL synthetic dataset and evaluating with Human3.6M over a no-adaption scenario, achieving state-of-the-art performance.<\/jats:p>","DOI":"10.3390\/s23177312","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T09:10:56Z","timestamp":1692695456000},"page":"7312","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["DUA: A Domain-Unified Approach for Cross-Dataset 3D Human Pose Estimation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1617-5142","authenticated-orcid":false,"given":"Jo\u00e3o Renato Ribeiro","family":"Manesco","sequence":"first","affiliation":[{"name":"Faculty of Sciences, UNESP\u2014S\u00e3o Paulo State University, Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1219-4386","authenticated-orcid":false,"given":"Stefano","family":"Berretti","sequence":"additional","affiliation":[{"name":"Media Integration and Communication Center (MICC), University of Florence, 50134 Florence, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4861-7061","authenticated-orcid":false,"given":"Aparecido Nilceu","family":"Marana","sequence":"additional","affiliation":[{"name":"Faculty of Sciences, UNESP\u2014S\u00e3o Paulo State University, Bauru 17033-360, SP, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,22]]},"reference":[{"key":"ref_1","unstructured":"Zheng, C., Wu, W., Yang, T., Zhu, S., Chen, C., Liu, R., Shen, J., Kehtarnavaz, N., and Shah, M. (2020). Deep Learning-Based Human Pose Estimation: A Survey. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102897","DOI":"10.1016\/j.cviu.2019.102897","article-title":"Monocular Human Pose Estimation: A Survey of Deep Learning-Based Methods","volume":"192","author":"Chen","year":"2020","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_3","unstructured":"Doersch, C., and Zisserman, A. (2019). Sim2real Transfer Learning for 3D Human Pose Estimation: Motion to the Rescue. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bartol, K., Bojanic, D., Petkovic, T., D\u2019Apuzzo, N., and Pribanic, T. (2020, January 17\u201318). A Review of 3D Human Pose Estimation from 2D Images. Proceedings of the 3DBODY.TECH 2020\u201411th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Virtual.","DOI":"10.15221\/20.29"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014). Computer Vision\u2014ECCV 2014, Springer International Publishing. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-319-10602-1"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime multi-person 2D pose estimation using Part Affinity Fields","volume":"43","author":"Cao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kreiss, S., Bertoni, L., and Alahi, A. (2019, January 15\u201320). Pifpaf: Composite fields for human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01225"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). Computer Vision\u2014ECCV 2016, Springer International Publishing. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-319-46487-9"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., and Little, J.J. (2017, January 22\u201329). A Simple Yet Effective Baseline for 3d Human Pose Estimation. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4601","DOI":"10.1109\/TCSVT.2019.2928813","article-title":"View invariant 3d human pose estimation","volume":"30","author":"Wei","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1016\/j.neucom.2019.02.029","article-title":"3D human pose estimation with siamese equivariant embedding","volume":"339","author":"Varga","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xu, J., Yu, Z., Ni, B., Yang, J., Yang, X., and Zhang, W. (2020, January 13\u201319). Deep kinematics analysis for monocular 3d human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6327","DOI":"10.1109\/TPAMI.2021.3087695","article-title":"Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation","volume":"44","author":"Xu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","article-title":"Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Csurka, G. (2017). Domain Adaptation in Computer Vision Applications, Springer Publishing Company, Incorporated. [1st ed.].","DOI":"10.1007\/978-3-319-58347-1"},{"key":"ref_16","unstructured":"Stamou, G., Krinidis, M., Loutas, E., Nikolaidis, N., and Pitas, I. (2005). Handbook of Image and Video Processing, Elsevier. XVI\u2013XVIII."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Moreno-Noguer, F. (2017, January 21\u201326). 3d human pose estimation from a single image via distance matrix regression. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.170"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M., and Metaxas, D.N. (2019, January 15\u201320). Semantic graph convolutional networks for 3d human pose regression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00354"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wong, Y., Kankanhalli, M.S., and Geng, W. (2019, January 21\u201325). Unsupervised domain adaptation for 3D human pose estimation. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.","DOI":"10.1145\/3343031.3351052"},{"key":"ref_20","unstructured":"Manesco, J.R.R., and Marana, A.N. (December, January 28). A Survey of Recent Advances on Two-Step 3D Human Pose Estimation. Proceedings of the Brazilian Conference on Intelligent Systems, Campinas, Brazil."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mundhada, A., Kusupati, U., Afaque, S., Sharma, A., and Jain, A. (2018, January 8\u201314). Learning 3d human pose from structure and motion. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, W., Ouyang, W., Wang, X., Ren, J., Li, H., and Wang, X. (2018, January 18\u201323). 3d human pose estimation in the wild by adversarial learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00551"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"012003","DOI":"10.1088\/1742-6596\/1873\/1\/012003","article-title":"Residual Deep Monocular 3D Human Pose Estimation using CVAE synthetic data","volume":"1873","author":"Jiang","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Gong, K., Zhang, J., and Feng, J. (2021, January 20\u201325). Poseaug: A differentiable pose augmentation framework for 3d human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Gholami, M., Wandt, B., Rhodin, H., Ward, R., and Wang, Z.J. (2022, January 18\u201324). Adaptpose: Cross-dataset adaptation for 3d human pose estimation by learnable motion generation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01273"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Guan, S., Xu, J., Wang, Y., Ni, B., and Yang, X. (2021, January 20\u201325). Bilevel online adaptation for out-of-domain human mesh reconstruction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01033"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chai, W., Jiang, Z., Hwang, J.N., and Wang, G. (2023). Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation. arXiv.","DOI":"10.1109\/ICCV51070.2023.01347"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Seth, S., YM, P., Jampani, V., Chakraborty, A., and Babu, R.V. (2022, January 18\u201324). Uncertainty-aware adaptation for self-supervised 3d human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01980"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wong, Y., Wu, X., Lu, J., Kankanhalli, M., Li, X., and Geng, W. (2021, January 20\u201325). Learning causal representation for training cross-domain pose estimator via generative interventions. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Nashville, TN, USA.","DOI":"10.1109\/ICCV48922.2021.01108"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Rapczy\u0144ski, M., Werner, P., Handrich, S., and Al-Hamadi, A. (2021). A baseline for cross-database 3d human pose estimation. Sensors, 21.","DOI":"10.3390\/s21113769"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"S\u00e1r\u00e1ndi, I., Hermans, A., and Leibe, B. (2023, January 3\u20137). Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV56688.2023.00297"},{"key":"ref_32","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., and Black, M.J. (November, January 27). AMASS: Archive of Motion Capture as Surface Shapes. Proceedings of the International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2661229.2661273","article-title":"MoSh: Motion and Shape Capture from Sparse Markers","volume":"33","author":"Loper","year":"2014","journal-title":"Acm Trans. Graph."},{"key":"ref_34","unstructured":"Kendall, A., Gal, Y., and Cipolla, R. (2018, January 18\u201322). Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Li, H., Shi, B., Dai, W., Zheng, H., Wang, B., Sun, Y., Guo, M., Li, C., Zou, J., and Xiong, H. (2023). Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation. arXiv.","DOI":"10.1609\/aaai.v37i1.25213"},{"key":"ref_36","unstructured":"Kouw, W.M., and Loog, M. (2018). An introduction to domain adaptation and transfer learning. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MSP.2014.2347059","article-title":"Visual domain adaptation: A survey of recent advances","volume":"32","author":"Patel","year":"2015","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_39","first-page":"1","article-title":"Domain-Adversarial Training of Neural Networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Varol, G., Romero, J., Martin, X., Mahmood, N., Black, M.J., Laptev, I., and Schmid, C. (2017, January 21\u201326). Learning from Synthetic Humans. Proceedings of the CVPR, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.492"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1007\/978-3-030-01249-6_37","article-title":"Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera","volume":"Volume 11214","author":"Ferrari","year":"2018","journal-title":"Computer Vision\u2014ECCV 2018"},{"key":"ref_42","unstructured":"Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., and Darrell, T. (2014). Deep domain confusion: Maximizing for domain invariance. arXiv."},{"key":"ref_43","unstructured":"Long, M., Cao, Y., Wang, J., and Jordan, M.I. (2015, January 6\u201311). Learning Transferable Features with Deep Adaptation Networks. Proceedings of the ICML\u201915: 32nd International Conference on International Conference on Machine Learning, Lille, France."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/17\/7312\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:39:12Z","timestamp":1760128752000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/17\/7312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,22]]},"references-count":43,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["s23177312"],"URL":"https:\/\/doi.org\/10.3390\/s23177312","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,22]]}}}