{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T09:24:47Z","timestamp":1769160287900,"version":"3.49.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T00:00:00Z","timestamp":1755302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T00:00:00Z","timestamp":1755302400000},"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":["Mach. Intell. Res."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11633-024-1524-2","type":"journal-article","created":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T06:42:38Z","timestamp":1755326558000},"page":"1116-1126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semi-supervised Learning for Detector-free Multi-person Pose Estimation"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2455-4840","authenticated-orcid":false,"given":"Haixin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5049-8092","authenticated-orcid":false,"given":"Yingying","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,16]]},"reference":[{"key":"1524_CR1","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1109\/CVPR.2014.214","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA","author":"A Toshev","year":"2014","unstructured":"A. Toshev, C. Szegedy. DeepPose: Human pose estimation via deep neural networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, pp. 1653\u20131660, 2014. DOI: https:\/\/doi.org\/10.1109\/CVPR.2014.214."},{"key":"1524_CR2","doi-asserted-by":"publisher","first-page":"4724","DOI":"10.1109\/CVPR.2016.511","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA","author":"S E Wei","year":"2016","unstructured":"S. E. Wei, V. Ramakrishna, T. Kanade, Y. Sheikh. Convolutional pose machines. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 4724\u20134732, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.511."},{"key":"1524_CR3","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/978-3-030-01231-1_29","volume-title":"Proceedings of the 15th European Conference on Computer Vision, Munich, Germany","author":"B Xiao","year":"2018","unstructured":"B. Xiao, H. P. Wu, Y. C. Wei. Simple baselines for human pose estimation and tracking. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 466\u2013481, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01231-1_29."},{"key":"1524_CR4","first-page":"2274","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA","author":"A Newell","year":"2017","unstructured":"A. Newell, Z. Huang, J. Deng. Associative embedding: End-to-end learning for joint detection and grouping. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 2274\u20132284, 2017."},{"key":"1524_CR5","doi-asserted-by":"publisher","first-page":"5386","DOI":"10.1109\/CVPR42600.2020.00543","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA","author":"B W Cheng","year":"2020","unstructured":"B. W. Cheng, B. Xiao, J. D. Wang, H. H. Shi, T. S. Huang, L. Zhang. HigherHRNet: Scale-aware representation learning for bottom-up human pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 5386\u20135395, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00543."},{"key":"1524_CR6","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-030-01231-1_33","volume-title":"Proceedings of the 15th European Conference on Computer Vision, Munich, Germany","author":"X Sun","year":"2018","unstructured":"X. Sun, B. Xiao, F. Y. Wei, S. Liang, Y. C. Wei. Integral human pose regression. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 529\u2013545, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01231-1_33."},{"key":"1524_CR7","doi-asserted-by":"publisher","first-page":"5693","DOI":"10.1109\/CVPR.2019.00584","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA","author":"K Sun","year":"2019","unstructured":"K. Sun, B. Xiao, D. Liu, J. D. Wang. Deep high-resolution representation learning for human pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 5693\u20135703, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00584."},{"key":"1524_CR8","doi-asserted-by":"publisher","first-page":"5700","DOI":"10.1109\/CVPR42600.2020.00574","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA","author":"J J Huang","year":"2020","unstructured":"J. J. Huang, Z. Zhu, F. Guo, G. Huang. The devil is in the details: Delving into unbiased data processing for human pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 5700\u20135709, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00574."},{"key":"1524_CR9","doi-asserted-by":"publisher","first-page":"11025","DOI":"10.1109\/ICCV48922.2021.01084","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada","author":"J F Li","year":"2021","unstructured":"J. F. Li, S. Y. Bian, A. L. Zeng, C. Wang, B. Pang, W. T. Liu, C. W. Lu. Human pose regression with residual loglikelihood estimation. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 11025\u201311034, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01084."},{"key":"1524_CR10","doi-asserted-by":"publisher","first-page":"4929","DOI":"10.1109\/CVPR.2016.533","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Las Vegas, USA","author":"L Pishchulin","year":"2016","unstructured":"L. Pishchulin, E. Insafutdinov, S. Y. Tang, B. Andres, M. Andriluka, P. Gehler, B. Schiele. DeepCut: Joint subset partition and labeling for multi person pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 4929\u20134937, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.533."},{"key":"1524_CR11","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-319-48881-3_44","volume-title":"Proceedings of European Conference on Computer Vision, Amsterdam, The Netherlands","author":"U Iqbal","year":"2016","unstructured":"U. Iqbal, J. Gall. Multi-person pose estimation with local joint-to-person associations. In Proceedings of European Conference on Computer Vision, Amsterdam, The Netherlands, pp. 627\u2013642, 2016. DOI: https:\/\/doi.org\/10.1007\/978-3-319-48881-3_44."},{"key":"1524_CR12","doi-asserted-by":"publisher","first-page":"7291","DOI":"10.1109\/CVPR.2017.143","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA","author":"Z Cao","year":"2017","unstructured":"Z. Cao, T. Simon, S. E. Wei, Y. Sheikh. Realtime multiperson 2D pose estimation using part affinity fields. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 7291\u20137299, 2017. DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.143."},{"key":"1524_CR13","doi-asserted-by":"publisher","first-page":"11969","DOI":"10.1109\/CVPR.2019.01225","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA","author":"S Kreiss","year":"2019","unstructured":"S. Kreiss, L. Bertoni, A. Alahi. PifPaf: Composite fields for human pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 11969\u201311978, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.01225."},{"key":"1524_CR14","doi-asserted-by":"publisher","first-page":"6951","DOI":"10.1109\/ICCV.2019.00705","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea","author":"X C Nie","year":"2019","unstructured":"X. C. Nie, J. S. Feng, J. F. Zhang, S. C. Yan. Single-stage multi-person pose machines. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 6951\u20136960, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00705."},{"key":"1524_CR15","unstructured":"X. Y. Zhou, D. Q. Wang, Kr\u00e4henb\u00fchl. Objects as points, [Online], Available: https:\/\/arxiv.org\/abs\/1904.07850."},{"key":"1524_CR16","doi-asserted-by":"publisher","first-page":"14676","DOI":"10.1109\/CVPR46437.2021.01444","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA","author":"Z G Geng","year":"2021","unstructured":"Z. G. Geng, K. Sun, B. Xiao, Z. X. Zhang, J. D. Wang. Bottom-up human pose estimation via disentangled keypoint regression. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 14676\u201314686, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.01444."},{"key":"1524_CR17","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1109\/CVPR.2018.00167","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City USA","author":"S Honari","year":"2018","unstructured":"S. Honari, P. Molchanov, S. Tyree, P. Vincent, C. Pal, J. Kautz. Improving landmark localization with semi-supervised learning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City USA, pp. 1546\u20131555, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00167."},{"key":"1524_CR18","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1109\/ICCV.2019.00087","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea","author":"X Y Dong","year":"2019","unstructured":"X. Y. Dong, Y. Yang. Teacher supervises students how to learn from partially labeled images for facial landmark detection. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 783\u2013792, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00087."},{"key":"1524_CR19","volume-title":"Proceedings Of The 9Th International Conference On Learning Representations","author":"O Moskvyak","year":"2021","unstructured":"O. Moskvyak, F. Maire, F. Dayoub, M. Baktashmotlagh. Semi-supervised keypoint localization. In Proceedings Of The 9Th International Conference On Learning Representations, 2021."},{"key":"1524_CR20","doi-asserted-by":"publisher","first-page":"11364","DOI":"10.1109\/ICCV48922.2021.01117","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada","author":"L L Yang","year":"2021","unstructured":"L. L. Yang, S. C. Chen, A. Yao. SemiHand: Semi-supervised hand pose estimation with consistency. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 11364\u201311373, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01117."},{"key":"1524_CR21","doi-asserted-by":"publisher","first-page":"11240","DOI":"10.1109\/ICCV48922.2021.01105","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada","author":"R C Xie","year":"2021","unstructured":"R. C. Xie, C. Y. Wang, W. J. Zeng, Y. Z. Wang. An empirical study of the collapsing problem in semi-supervised 2D human pose estimation. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 11240\u201311249, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01105."},{"key":"1524_CR22","doi-asserted-by":"publisher","first-page":"10863","DOI":"10.1109\/CVPR.2019.01112","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA","author":"J F Li","year":"2019","unstructured":"J. F. Li, C. Wang, H. Zhu, Y. H. Mao, H. S. Fang, C. W. Lu. CrowdPose: Efficient crowded scenes pose estimation and a new benchmark. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 10863\u201310872, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.01112."},{"key":"1524_CR23","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Proceedings of the 13th European Conference on Computer Vision, Z\u00fcrich, Switzerland","author":"T Y Lin","year":"2014","unstructured":"T. Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, C. L. Zitnick. Microsoft COCO: Common objects in context. In Proceedings of the 13th European Conference on Computer Vision, Z\u00fcrich, Switzerland, pp. 740\u2013755, 2014. DOI: https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48."},{"key":"1524_CR24","volume-title":"Proceedings of Workshop on Challenges in Representation Learning, Atlanta, USA","author":"D H Lee","year":"2013","unstructured":"D. H. Lee. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Proceedings of Workshop on Challenges in Representation Learning, Atlanta, USA, Article number 896, 2013."},{"issue":"2","key":"1524_CR25","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10115-013-0706-y","volume":"42","author":"I Triguero","year":"2015","unstructured":"I. Triguero, S. Garc\u00eda, F. Herrera. Self-labeled techniques for semi-supervised learning: Taxonomy, software and empirical study. Knowledge and Information Systems, vol. 42, no. 2, pp. 245\u2013284, 2015. DOI: https:\/\/doi.org\/10.1007\/s10115-013-0706-y.","journal-title":"Knowledge and Information Systems"},{"key":"1524_CR26","doi-asserted-by":"publisher","first-page":"4119","DOI":"10.1109\/CVPR.2018.00433","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA","author":"I Radosavovic","year":"2018","unstructured":"I. Radosavovic, P. Doll\u00e1r, R. Girshick, G. Gkioxari, K. M. He. Data distillation: Towards omni-supervised learning. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 4119\u20134128, 2018. DOI: https:\/\/doi.org\/10.1109\/CVPR.2018.00433."},{"key":"1524_CR27","doi-asserted-by":"publisher","first-page":"10687","DOI":"10.1109\/CVPR42600.2020.01070","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA","author":"Q Z Xie","year":"2020","unstructured":"Q. Z. Xie, M. T. Luong, E. Hovy, Q. V. Le. Self-training with noisy student improves ImageNet classification. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 10687\u201310698, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01070."},{"key":"1524_CR28","first-page":"3365","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada","author":"P Bachman","year":"2014","unstructured":"P. Bachman, O. Alsharif, D. Precup. Learning with pseudo-ensembles. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 3365\u20133373, 2014."},{"key":"1524_CR29","first-page":"1171","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain","author":"M Sajjadi","year":"2016","unstructured":"M. Sajjadi, M. Javanmardi, T. Tasdizen. Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, pp. 1171\u20131179, 2016."},{"key":"1524_CR30","volume-title":"Proceedings of the 5th International Conference on Learning Representations, Toulon, France","author":"S Laine","year":"2017","unstructured":"S. Laine, T Aila. Temporal ensembling for semi-supervised learning. In Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 2017."},{"key":"1524_CR31","first-page":"1195","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA","author":"A Tarvainen","year":"2017","unstructured":"A. Tarvainen, H. Valpola. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 1195\u20131204, 2017."},{"key":"1524_CR32","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada","author":"D Berthelot","year":"2019","unstructured":"D. Berthelot, N. Carlini, I. Goodfellow, A. Oliver, N. Papernot, C. Raffel. MixMatch: A holistic approach to semisupervised learning. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 454, 2019."},{"key":"1524_CR33","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada","author":"Q Z Xie","year":"2020","unstructured":"Q. Z. Xie, Z. H. Dai, E. Hovy, M. T. Luong, Q. V. Le. Unsupervised data augmentation for consistency training. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 525, 2020."},{"key":"1524_CR34","doi-asserted-by":"publisher","first-page":"12674","DOI":"10.1109\/CVPR42600.2020.01269","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA","author":"Y Ouali","year":"2020","unstructured":"Y. Ouali, C. Hudelot, M. Tami. Semi-supervised semantic segmentation with cross-consistency training. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 12674\u201312684, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.01269."},{"key":"1524_CR35","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-030-58601-0_26","volume-title":"Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK","author":"Z H Ke","year":"2020","unstructured":"Z. H. Ke, D. Qiu, K. C. Li, Q. Yan, R. W. H. Lau. Guided collaborative training for pixel-wise semi-supervised learning. In Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK, pp. 429\u2013445, 2020. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58601-0_26."},{"key":"1524_CR36","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-01267-0_9","volume-title":"In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany","author":"S Y Qiao","year":"2018","unstructured":"S. Y. Qiao, W. Shen, Z. S. Zhang, B. Wang, A. Yuille. Deep co-training for semi-supervised image recognition. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 135\u2013152, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01267-0_9."},{"key":"1524_CR37","doi-asserted-by":"publisher","first-page":"6728","DOI":"10.1109\/ICCV.2019.00683","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea","author":"Z H Ke","year":"2019","unstructured":"Z. H. Ke, D. Y. Wang, Q. Yan, J. Ren, R. Lau. Dual student: Breaking the limits of the teacher in semi-supervised learning. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 6728\u20136736, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00683"},{"key":"1524_CR38","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada","author":"K Sohn","year":"2020","unstructured":"K. Sohn, D. Berthelot, C. L. Li, Z. Zhang, N. Carlini, E. D. Cubuk, A. Kurakin, H. Zhang, C. Raffel. FixMatch: Simplifying semi-supervised learning with consistency and confidence. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 51, 2020."},{"key":"1524_CR39","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/978-3-030-01264-9_17","volume-title":"Proceedings of the 15th European Conference on Computer Vision, Munich, Germany","author":"G Papandreou","year":"2018","unstructured":"G. Papandreou, T. Zhu, L. C. Chen, S. Gidaris, J. Tompson, K. Murphy. PersonLab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In Proceedings of the 15th European Conference on Computer Vision, Munich, Germany, pp. 269\u2013286, 2018. DOI: https:\/\/doi.org\/10.1007\/978-3-030-01264-9_17."},{"key":"1524_CR40","doi-asserted-by":"publisher","first-page":"13264","DOI":"10.1109\/CVPR46437.2021.01306","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA","author":"Z X Luo","year":"2021","unstructured":"Z. X. Luo, Z. C. Wang, Y. Huang, L. Wang, T. N. Tan, E. J. Zhou. Rethinking the heatmap regression for bottom-up human pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 13264\u201313273, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.01306."},{"key":"1524_CR41","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-031-20068-7_7","volume-title":"Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel","author":"H X Wang","year":"2022","unstructured":"H. X. Wang, L. Zhou, Y. Y. Chen, M. Tang, J. Q. Wang. Regularizing vector embedding in bottom-up human pose estimation. In Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel, pp. 107\u2013122, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-20068-7_7."},{"key":"1524_CR42","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1609\/aaai.v36i3.20186","volume-title":"Proceedings of the 36th AAAI Conference on Artificial Intelligence","author":"Y B Xiao","year":"2022","unstructured":"Y. B. Xiao, D. D. Yu, X. J. Wang, L. Jin, G. L. Wang, Q. Zhang. Learning quality-aware representation for multiperson pose regression. In Proceedings of the 36th AAAI Conference on Artificial Intelligence pp. 2822\u20132830, 2022. DOI: https:\/\/doi.org\/10.1609\/aaai.v36i3.20186."},{"key":"1524_CR43","doi-asserted-by":"publisher","first-page":"2813","DOI":"10.1609\/aaai.v36i3.20185","volume-title":"Proceedings of the 36th AAAI Conference on Artificial Intelligence","author":"Y B Xiao","year":"2022","unstructured":"Y. B. Xiao, X. J. Wang, D. D. Yu, G. L. Wang, Q. Zhang, M. S. He. AdaptivePose: Human parts as adaptive points. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, pp. 2813\u20132821, 2022. DOI: https:\/\/doi.org\/10.1609\/aaai.v36i3.20185."},{"key":"1524_CR44","doi-asserted-by":"publisher","first-page":"13065","DOI":"10.1109\/CVPR52688.2022.01272","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA","author":"N Xue","year":"2022","unstructured":"N. Xue, T. F. Wu, G. S. Xia, L. P. Zhang. Learning localglobal contextual adaptation for multi-person pose estimation. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 13065\u201313074, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01272."},{"key":"1524_CR45","doi-asserted-by":"publisher","first-page":"9034","DOI":"10.1109\/CVPR46437.2021.00892","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA","author":"W A Mao","year":"2021","unstructured":"W. A. Mao, Z. Tian, X. L. Wang, C. H. Shen. FCPose: Fully convolutional multi-person pose estimation with dynamic instance-aware convolutions. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 9034\u20139043, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.00892."},{"key":"1524_CR46","doi-asserted-by":"publisher","unstructured":"F. Y. Wei, X. Sun, H. Y. Li, J. D. Wang, S. Lin. Point-set anchors for object detection, instance segmentation and pose estimation. In Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK, pp. 527\u2013544. DOI: https:\/\/doi.org\/10.1007\/978-3-030-58607-2_31.","DOI":"10.1007\/978-3-030-58607-2_31"},{"key":"1524_CR47","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-031-20068-7_3","volume-title":"Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel","author":"W McNally","year":"2022","unstructured":"W. McNally, K. Vats, A. Wong, J. McPhee. Rethinking keypoint representations: Modeling keypoints and poses as objects for multi-person human pose estimation. In Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel, pp. 37\u201354, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-20068-7_3."},{"key":"1524_CR48","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1109\/CVPR52729.2023.00074","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada","author":"L Z Huang","year":"2023","unstructured":"L. Z. Huang, Y. L. Li, H. B. Tian, Y. Yang, X. G. Li, W. H. Deng, J. P. Ye. Semi-supervised 2D human pose estimation driven by position inconsistency pseudo label correction module. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, pp. 693\u2013703, 2023. DOI: https:\/\/doi.org\/10.1109\/CVPR52729.2023.00074."},{"issue":"1\u20132","key":"1524_CR49","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"H W Kuhn","year":"1955","unstructured":"H. W. Kuhn. The Hungarian method for the assignment problem. Naval research logistics quarterly, vol. 2, no. 1\u20132, pp. 83\u201397, 1955. DOI: https:\/\/doi.org\/10.1002\/nav.3800020109.","journal-title":"Naval research logistics quarterly"},{"key":"1524_CR50","volume-title":"Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA","author":"D P Kingma","year":"2015","unstructured":"D. P. Kingma, J. Ba. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2015."},{"key":"1524_CR51","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA","author":"K M He","year":"2016","unstructured":"K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770\u2013778, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-024-1524-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-024-1524-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-024-1524-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T10:02:54Z","timestamp":1764151374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-024-1524-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,16]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["1524"],"URL":"https:\/\/doi.org\/10.1007\/s11633-024-1524-2","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,16]]},"assertion":[{"value":"23 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}