{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T23:01:23Z","timestamp":1771369283354,"version":"3.50.1"},"reference-count":99,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T00:00:00Z","timestamp":1771286400000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-36668-y","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T01:33:30Z","timestamp":1769736810000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-aware self-supervised learning using progressive sub-action regression for action quality assessment"],"prefix":"10.1038","volume":"16","author":[{"given":"Marjan","family":"Mazruei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Fazl-Ersi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abedin","family":"Vahedian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahad","family":"Harati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"36668_CR1","doi-asserted-by":"publisher","unstructured":"Parmar, P. & Tran Morris, B. Learning to score olympic events. Proceedings of the IEEE conference on computer vision and pattern recognition workshops 20\u201328. https:\/\/doi.org\/10.1109\/CVPRW.2017.16 (2017).","DOI":"10.1109\/CVPRW.2017.16"},{"key":"36668_CR2","doi-asserted-by":"publisher","unstructured":"Xu, J. et al. Finediving: A fine-grained dataset for procedure-aware action quality assessment. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2949\u20132958. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00296 (2022).","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"36668_CR3","doi-asserted-by":"publisher","unstructured":"Pirsiavash, H., Vondrick, C. & Torralba, A. Assessing the quality of actions. European conference on computer vision 556\u2013571. https:\/\/doi.org\/10.1007\/978-3-319-10599-4_36 (2014).","DOI":"10.1007\/978-3-319-10599-4_36"},{"key":"36668_CR4","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C. & Liu, C.-L. Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103, 60\u201379. https:\/\/doi.org\/10.1007\/s11263-012-0594-8 (2013).","journal-title":"Int. J. Comput. Vis."},{"key":"36668_CR5","doi-asserted-by":"publisher","unstructured":"Wang, H. & Schmid, C. Action recognition with improved trajectories. Proceedings of the IEEE international conference on computer vision 3551\u20133558. https:\/\/doi.org\/10.1109\/ICCV.2013.441 (2013).","DOI":"10.1109\/ICCV.2013.441"},{"key":"36668_CR6","doi-asserted-by":"publisher","first-page":"7749","DOI":"10.1109\/TCSVT.2023.3281413","volume":"33","author":"K Zhou","year":"2023","unstructured":"Zhou, K., Ma, Y., Shum, H. P. H. & Liang, X. Hierarchical graph convolutional networks for action quality assessment. IEEE Trans. Circuits Syst. Video Technol. 33, 7749\u20137763. https:\/\/doi.org\/10.1109\/TCSVT.2023.3281413 (2023).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR7","doi-asserted-by":"publisher","unstructured":"Karpathy, A. et al. Large-scale video classification with convolutional neural networks. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition 1725\u20131732. https:\/\/doi.org\/10.1109\/CVPR.2014.223 (2014).","DOI":"10.1109\/CVPR.2014.223"},{"key":"36668_CR8","doi-asserted-by":"publisher","unstructured":"Simonyan, K. & Zisserman, A. Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1406.2199 (2014).","DOI":"10.48550\/arXiv.1406.2199"},{"key":"36668_CR9","doi-asserted-by":"publisher","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L. & Paluri, M. Learning spatiotemporal features with 3d convolutional networks. Proceedings of the IEEE international conference on computer vision 4489\u20134497. https:\/\/doi.org\/10.1109\/ICCV.2015.510 (2015).","DOI":"10.1109\/ICCV.2015.510"},{"key":"36668_CR10","doi-asserted-by":"publisher","unstructured":"Carreira, J. & Zisserman, A. Quo vadis, action recognition? A new model and the kinetics dataset. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 6299\u20136308. https:\/\/doi.org\/10.1109\/CVPR.2017.502 (2017).","DOI":"10.1109\/CVPR.2017.502"},{"key":"36668_CR11","doi-asserted-by":"publisher","unstructured":"Qiu, Z., Yao, T. & Mei, T. Learning spatio-temporal representation with pseudo-3d residual networks. Proceedings of the IEEE International Conference on Computer Vision 5533\u20135541. https:\/\/doi.org\/10.1109\/ICCV.2017.590 (2017).","DOI":"10.1109\/ICCV.2017.590"},{"key":"36668_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110898","volume":"157","author":"Y Su","year":"2025","unstructured":"Su, Y., Tan, Y., An, S., Xing, M. & Feng, Z. Semantic-driven dual consistency learning for weakly supervised video anomaly detection. Pattern Recognit. 157, 110898. https:\/\/doi.org\/10.1016\/j.patcog.2024.110898 (2025).","journal-title":"Pattern Recognit."},{"key":"36668_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124392","volume":"254","author":"Y Su","year":"2024","unstructured":"Su, Y., Tan, Y., An, S. & Xing, M. Anomalies cannot materialize or vanish out of thin air: A hierarchical multiple instance learning with position-scale awareness for video anomaly detection. Expert Syst. Appl. 254, 124392. https:\/\/doi.org\/10.1016\/j.eswa.2024.124392 (2024).","journal-title":"Expert Syst. Appl."},{"key":"36668_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2020.102380","volume":"113","author":"Y Su","year":"2021","unstructured":"Su, Y., Xing, M., An, S., Peng, W. & Feng, Z. VDARNet: Video disentangling attentive relation network for few-shot and zero-shot action recognition. Ad Hoc Networks 113, 102380. https:\/\/doi.org\/10.1016\/j.adhoc.2020.102380 (2021).","journal-title":"Ad Hoc Networks"},{"key":"36668_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5244\/C.29.67","volume":"67","author":"V Venkataraman","year":"2015","unstructured":"Venkataraman, V., Vlachos, I. & Turaga, P. K. Dynamical Regularity for Action Analysis. BMVC 67, 1\u201312. https:\/\/doi.org\/10.5244\/C.29.67 (2015).","journal-title":"BMVC"},{"key":"36668_CR16","doi-asserted-by":"publisher","unstructured":"Parisi, G. I., Magg, S. & Wermter, S. Human motion assessment in real time using recurrent self-organization. 2016 25th IEEE international symposium on robot and human interactive communication (RO-MAN) 71\u201376. https:\/\/doi.org\/10.1109\/ROMAN.2016.7745093 (2016).","DOI":"10.1109\/ROMAN.2016.7745093"},{"key":"36668_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735 (1997).","journal-title":"Neural Comput."},{"key":"36668_CR18","doi-asserted-by":"publisher","unstructured":"Li, Y., Chai, X. & Chen, X. End-to-end learning for action quality assessment. Pacific Rim Conference on Multimedia 125\u2013134. https:\/\/doi.org\/10.1007\/978-3-030-00767-6_12 (2018).","DOI":"10.1007\/978-3-030-00767-6_12"},{"key":"36668_CR19","doi-asserted-by":"publisher","first-page":"604","DOI":"10.3390\/signals2030037","volume":"2","author":"P Parmar","year":"2021","unstructured":"Parmar, P. & Morris, B. T. HalluciNet-ing spatiotemporal representations using a 2D-CNN. Signals 2, 604\u2013618. https:\/\/doi.org\/10.3390\/signals2030037 (2021).","journal-title":"Signals"},{"key":"36668_CR20","doi-asserted-by":"publisher","first-page":"2186","DOI":"10.1109\/TCSVT.2021.3089323","volume":"32","author":"B Wang","year":"2021","unstructured":"Wang, B., Zhang, X. & Zhao, Y. Exploring sub-action granularity for weakly supervised temporal action localization. IEEE Trans. Circuits Syst. Video Technol. 32, 2186\u20132198. https:\/\/doi.org\/10.1109\/TCSVT.2021.3089323 (2021).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR21","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/s11263-016-0897-2","volume":"118","author":"C Liu","year":"2016","unstructured":"Liu, C., Wu, X. & Jia, Y. A hierarchical video description for complex activity understanding. Int. J. Comput. Vis. 118, 240\u2013255. https:\/\/doi.org\/10.1007\/s11263-016-0897-2 (2016).","journal-title":"Int. J. Comput. Vis."},{"key":"36668_CR22","doi-asserted-by":"publisher","unstructured":"Xiang, X., Tian, Y., Reiter, A., Hager, G. D. & Tran, T. D. S3D: Stacking segmental P3D for action quality assessment. 2018 25th IEEE International conference on image processing (ICIP) 928\u2013932. https:\/\/doi.org\/10.1109\/ICIP.2018.8451364 (2018).","DOI":"10.1109\/ICIP.2018.8451364"},{"key":"36668_CR23","doi-asserted-by":"publisher","unstructured":"Lea, C., Flynn, M. D., Vidal, R., Reiter, A. & Hager, G. D. Temporal convolutional networks for action segmentation and detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 156\u2013165. https:\/\/doi.org\/10.1109\/CVPR.2017.113 (2017).","DOI":"10.1109\/CVPR.2017.113"},{"key":"36668_CR24","doi-asserted-by":"publisher","unstructured":"Li, Y., Chai, X. & Chen, X. ScoringNet: Learning key fragment for action quality assessment with ranking loss in skilled sports. Asian Conference on Computer Vision 149\u2013164. https:\/\/doi.org\/10.1007\/978-3-030-20876-9_10 (2018).","DOI":"10.1007\/978-3-030-20876-9_10"},{"key":"36668_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107388","volume":"229","author":"L-J Dong","year":"2021","unstructured":"Dong, L.-J. et al. Learning and fusing multiple hidden substages for action quality assessment. Knowl.-Based Syst. 229, 107388. https:\/\/doi.org\/10.1016\/j.knosys.2021.107388 (2021).","journal-title":"Knowl.-Based Syst."},{"key":"36668_CR26","doi-asserted-by":"publisher","first-page":"10053","DOI":"10.1007\/s10489-022-03984-5","volume":"53","author":"H-B Zhang","year":"2023","unstructured":"Zhang, H.-B., Dong, L.-J., Lei, Q., Yang, L.-J. & Du, J.-X. Label-reconstruction-based pseudo-subscore learning for action quality assessment in sporting events. Appl. Intell. 53, 10053\u201310067. https:\/\/doi.org\/10.1007\/s10489-022-03984-5 (2023).","journal-title":"Appl. Intell."},{"key":"36668_CR27","doi-asserted-by":"publisher","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1706.0376230 (2017).","DOI":"10.48550\/arXiv.1706.03762"},{"key":"36668_CR28","doi-asserted-by":"publisher","first-page":"4578","DOI":"10.1109\/TCSVT.2019.2927118","volume":"30","author":"C Xu","year":"2019","unstructured":"Xu, C. et al. Learning to score figure skating sport videos. IEEE Trans. Circuits Syst. Video Technol. 30, 4578\u20134590. https:\/\/doi.org\/10.1109\/TCSVT.2019.2927118 (2019).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR29","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1007\/s11760-021-01890-w","volume":"15","author":"Q Lei","year":"2021","unstructured":"Lei, Q., Zhang, H. & Du, J. Temporal attention learning for action quality assessment in sports video. Signal Image Video Process. 15, 1575\u20131583. https:\/\/doi.org\/10.1007\/s11760-021-01890-w (2021).","journal-title":"Signal Image Video Process."},{"key":"36668_CR30","doi-asserted-by":"publisher","unstructured":"Xu, A., Zeng, L.-A. & Zheng, W.-S. Likert scoring with grade decoupling for long-term action assessment. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 3232\u20133241. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00323 (2022).","DOI":"10.1109\/CVPR52688.2022.00323"},{"key":"36668_CR31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.12318","author":"A Iyer","year":"2022","unstructured":"Iyer, A., Alali, M., Bodala, H. & Vaidya, S. Action quality assessment using transformers. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2207.12318 (2022).","journal-title":"Preprint at"},{"key":"36668_CR32","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.patrec.2022.04.015","volume":"158","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Xiong, W. & Mi, S. Learning time-aware features for action quality assessment. Pattern Recognit. Lett. 158, 104\u2013110. https:\/\/doi.org\/10.1016\/j.patrec.2022.04.015 (2022).","journal-title":"Pattern Recognit. Lett."},{"key":"36668_CR33","doi-asserted-by":"publisher","unstructured":"Ji, Y. et al. Localization-assisted uncertainty score disentanglement network for action quality assessment. Proceedings of the 31st ACM International Conference on Multimedia 8590\u20138597. https:\/\/doi.org\/10.1145\/3581783.3613795 (2023).","DOI":"10.1145\/3581783.3613795"},{"key":"36668_CR34","doi-asserted-by":"publisher","first-page":"30443","DOI":"10.1007\/s10489-023-05166-3","volume":"53","author":"P-X Lian","year":"2023","unstructured":"Lian, P.-X. & Shao, Z.-G. Improving action quality assessment with across-staged temporal reasoning on imbalanced data. Appl. Intell. 53, 30443\u201330454. https:\/\/doi.org\/10.1007\/s10489-023-05166-3 (2023).","journal-title":"Appl. Intell."},{"key":"36668_CR35","doi-asserted-by":"publisher","unstructured":"Liu, Y., Cheng, X. & Ikenaga, T. A figure skating jumping dataset for replay-guided action quality assessment. Proceedings of the 31st ACM International Conference on Multimedia 2437\u20132445. https:\/\/doi.org\/10.1145\/3581783.3613774 (2023).","DOI":"10.1145\/3581783.3613774"},{"key":"36668_CR36","doi-asserted-by":"publisher","unstructured":"Zhang, S. et al. Logo: A long-form video dataset for group action quality assessment. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2405\u20132414. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00238 (2023).","DOI":"10.1109\/CVPR52729.2023.00238"},{"key":"36668_CR37","doi-asserted-by":"publisher","first-page":"3245","DOI":"10.1007\/s10489-024-05349-6","volume":"54","author":"F Huang","year":"2024","unstructured":"Huang, F. & Li, J. Assessing action quality with semantic-sequence performance regression and densely distributed sample weighting. Appl. Intell. 54, 3245\u20133259. https:\/\/doi.org\/10.1007\/s10489-024-05349-6 (2024).","journal-title":"Appl. Intell."},{"key":"36668_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120347","volume":"664","author":"X Ke","year":"2024","unstructured":"Ke, X., Xu, H., Lin, X. & Guo, W. Two-path target-aware contrastive regression for action quality assessment. Inf. Sci. 664, 120347. https:\/\/doi.org\/10.1016\/j.ins.2024.120347 (2024).","journal-title":"Inf. Sci."},{"key":"36668_CR39","doi-asserted-by":"publisher","unstructured":"Pan, J.-H., Gao, J. & Zheng, W.-S. Action assessment by joint relation graphs. Proceedings of the IEEE\/CVF international conference on computer vision 6331\u20136340. https:\/\/doi.org\/10.1109\/ICCV.2019.00643 (2019).","DOI":"10.1109\/ICCV.2019.00643"},{"key":"36668_CR40","doi-asserted-by":"publisher","unstructured":"Zeng, L.-A. et al. Hybrid dynamic-static context-aware attention network for action assessment in long videos. Proceedings of the 28th ACM international conference on multimedia 2526\u20132534. https:\/\/doi.org\/10.1145\/3394171.3413560 (2020).","DOI":"10.1145\/3394171.3413560"},{"key":"36668_CR41","doi-asserted-by":"publisher","first-page":"2846","DOI":"10.1007\/s11263-021-01486-4","volume":"129","author":"X Chen","year":"2021","unstructured":"Chen, X. et al. Sportscap: Monocular 3d human motion capture and fine-grained understanding in challenging sports videos. Int. J. Comput. Vis. 129, 2846\u20132864. https:\/\/doi.org\/10.1007\/s11263-021-01486-4 (2021).","journal-title":"Int. J. Comput. Vis."},{"key":"36668_CR42","doi-asserted-by":"publisher","unstructured":"Nagai, T., Takeda, S., Matsumura, M., Shimizu, S. & Yamamoto, S. Action quality assessment with ignoring scene context. 2021 IEEE International Conference on Image Processing (ICIP) 1189\u20131193. https:\/\/doi.org\/10.1109\/ICIP42928.2021.9506257 (2021).","DOI":"10.1109\/ICIP42928.2021.9506257"},{"key":"36668_CR43","doi-asserted-by":"publisher","unstructured":"Wang, S., Yang, D., Zhai, P., Chen, C. & Zhang, L. TSA-Net: Tube self-attention network for action quality assessment. Proceedings of the 29th ACM international conference on multimedia 4902\u20134910. https:\/\/doi.org\/10.1145\/3474085.3475438 (2021).","DOI":"10.1145\/3474085.3475438"},{"key":"36668_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128786","volume":"614","author":"K Huang","year":"2025","unstructured":"Huang, K., Tian, Y., Yu, C. & Huang, Y. Dual-referenced assistive network for action quality assessment. Neurocomputing 614, 128786. https:\/\/doi.org\/10.1016\/j.neucom.2024.128786 (2025).","journal-title":"Neurocomputing"},{"key":"36668_CR45","doi-asserted-by":"publisher","unstructured":"Tang, Y. et al. Uncertainty-aware score distribution learning for action quality assessment. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 9839\u20139848. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00986 (2020).","DOI":"10.1109\/CVPR42600.2020.00986"},{"key":"36668_CR46","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1007\/s00521-023-09068-w","volume":"36","author":"B Zhang","year":"2024","unstructured":"Zhang, B. et al. Auto-encoding score distribution regression for action quality assessment. Neural Comput. Appl. 36, 929\u2013942. https:\/\/doi.org\/10.1007\/s00521-023-09068-w (2024).","journal-title":"Neural Comput. Appl."},{"key":"36668_CR47","doi-asserted-by":"publisher","unstructured":"Zhou, C., Huang, Y. & Ling, H. Uncertainty-driven action quality assessment. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2207.14513 (2022).","DOI":"10.48550\/arXiv.2207.14513"},{"key":"36668_CR48","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1007\/s40747-022-00892-6","volume":"9","author":"M-Z Li","year":"2023","unstructured":"Li, M.-Z., Zhang, H.-B., Dong, L.-J., Lei, Q. & Du, J.-X. Gaussian guided frame sequence encoder network for action quality assessment. Complex Intell. Syst. 9, 1963\u20131974. https:\/\/doi.org\/10.1007\/s40747-022-00892-6 (2023).","journal-title":"Complex Intell. Syst."},{"key":"36668_CR49","doi-asserted-by":"publisher","unstructured":"Majeedi, A., Gajjala, V. R., GNVV, S. S. S. N. & Li, Y. RICA: Rubric-informed, calibrated assessment of actions. European Conference on Computer Vision 143\u2013161. https:\/\/doi.org\/10.1007\/978-3-031-73036-8_9 (2024).","DOI":"10.1007\/978-3-031-73036-8_9"},{"key":"36668_CR50","doi-asserted-by":"publisher","unstructured":"Parmar, P. & Morris, B. T. What and how well you performed? A multitask learning approach to action quality assessment. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 304\u2013313. https:\/\/doi.org\/10.1109\/CVPR.2019.00039 (2019).","DOI":"10.1109\/CVPR.2019.00039"},{"key":"36668_CR51","doi-asserted-by":"publisher","unstructured":"Li, H.-Y., Lei, Q., Zhang, H.-B. & Du, J.-X. Skeleton based action quality assessment of figure skating videos. 2021 11th International Conference on Information Technology in Medicine and Education (ITME) 196\u2013200. https:\/\/doi.org\/10.1109\/ITME53901.2021.00048 (2021).","DOI":"10.1109\/ITME53901.2021.00048"},{"key":"36668_CR52","doi-asserted-by":"publisher","first-page":"21692","DOI":"10.1007\/s10489-023-04613-5","volume":"53","author":"Q Lei","year":"2023","unstructured":"Lei, Q., Li, H., Zhang, H., Du, J. & Gao, S. Multi-skeleton structures graph convolutional network for action quality assessment in long videos. Appl. Intell. 53, 21692\u201321705. https:\/\/doi.org\/10.1007\/s10489-023-04613-5 (2023).","journal-title":"Appl. Intell."},{"key":"36668_CR53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103625","volume":"89","author":"H Li","year":"2022","unstructured":"Li, H., Lei, Q., Zhang, H., Du, J. & Gao, S. Skeleton-based deep pose feature learning for action quality assessment on figure skating videos. J. Visual Commun. Image Represent. 89, 103625. https:\/\/doi.org\/10.1016\/j.jvcir.2022.103625 (2022).","journal-title":"J. Visual Commun. Image Represent."},{"key":"36668_CR54","doi-asserted-by":"publisher","first-page":"1916","DOI":"10.1109\/TNSRE.2024.3400790","volume":"32","author":"T He","year":"2024","unstructured":"He, T., Chen, Y., Wang, L. & Cheng, H. An expert-knowledge-based graph convolutional network for skeleton-based physical rehabilitation exercises assessment. IEEE Trans. Neural Syst. Rehabil. Eng. 32, 1916\u20131925. https:\/\/doi.org\/10.1109\/TNSRE.2024.3400790 (2024).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"36668_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3398072","volume":"73","author":"S Zahan","year":"2024","unstructured":"Zahan, S., Hassan, G. M. & Mian, A. Learning sparse temporal video mapping for action quality assessment in floor gymnastics. IEEE Trans. Instrum. Meas. 73, 1\u201311. https:\/\/doi.org\/10.1109\/TIM.2024.3398072 (2024).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"36668_CR56","doi-asserted-by":"publisher","unstructured":"Parmar, P., Reddy, J. & Morris, B. Piano skills assessment. 2021 IEEE 23rd international workshop on multimedia signal processing (MMSP) 1\u20135. https:\/\/doi.org\/10.1109\/MMSP53017.2021.9733638 (2021).","DOI":"10.1109\/MMSP53017.2021.9733638"},{"key":"36668_CR57","doi-asserted-by":"publisher","first-page":"2901","DOI":"10.1609\/aaai.v37i3.25392","volume":"37","author":"J Xia","year":"2023","unstructured":"Xia, J. et al. Skating-mixer: Long-term sport audio-visual modeling with MLPs. Proc. AAAI Conf. Artif. Intell. 37, 2901\u20132909. https:\/\/doi.org\/10.1609\/aaai.v37i3.25392 (2023).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"36668_CR58","doi-asserted-by":"publisher","unstructured":"Ding, Y. et al. 2M-AF: A strong multi-modality framework for human action quality assessment with self-supervised representation learning. Proceedings of the 32nd ACM International Conference on Multimedia 1564\u20131572. https:\/\/doi.org\/10.1145\/3664647.3681084 (2024).","DOI":"10.1145\/3664647.3681084"},{"key":"36668_CR59","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1109\/TIP.2024.3362135","volume":"33","author":"L-A Zeng","year":"2024","unstructured":"Zeng, L.-A. & Zheng, W.-S. Multimodal action quality assessment. IEEE Trans. Image Process. 33, 1600\u20131613. https:\/\/doi.org\/10.1109\/TIP.2024.3362135 (2024).","journal-title":"IEEE Trans. Image Process."},{"key":"36668_CR60","doi-asserted-by":"publisher","unstructured":"Zhang, S. et al. Narrative action evaluation with prompt-guided multimodal interaction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 18430\u201318439. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01744 (2024).","DOI":"10.1109\/CVPR52733.2024.01744"},{"key":"36668_CR61","doi-asserted-by":"publisher","first-page":"4987","DOI":"10.1109\/TMM.2023.3328180","volume":"26","author":"Z Du","year":"2023","unstructured":"Du, Z., He, D., Wang, X. & Wang, Q. Learning semantics-guided representations for scoring figure skating. IEEE Trans. Multimedia 26, 4987\u20134997. https:\/\/doi.org\/10.1109\/TMM.2023.3328180 (2023).","journal-title":"IEEE Trans. Multimedia"},{"key":"36668_CR62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3487242","author":"K Gedamu","year":"2024","unstructured":"Gedamu, K., Ji, Y., Yang, Y., Shao, J. & Shen, H. T. Visual-semantic alignment temporal parsing for action quality assessment. IEEE Trans. Circuits Syst. Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2024.3487242 (2024).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR63","doi-asserted-by":"publisher","unstructured":"Parmar, P. & Morris, B. Action quality assessment across multiple actions. 2019 IEEE winter conference on applications of computer vision (WACV) 1468\u20131476. https:\/\/doi.org\/10.1109\/WACV.2019.00161 (2019).","DOI":"10.1109\/WACV.2019.00161"},{"key":"36668_CR64","doi-asserted-by":"publisher","unstructured":"Dadashzadeh, A., Duan, S., Whone, A. & Mirmehdi, M. PECOP: Parameter efficient continual pretraining for action quality assessment. Proceedings of the IEEE\/CVF Winter Conference on applications of computer vision 42\u201352. https:\/\/doi.org\/10.1109\/WACV57701.2024.00012 (2024).","DOI":"10.1109\/WACV57701.2024.00012"},{"key":"36668_CR65","doi-asserted-by":"publisher","first-page":"9112","DOI":"10.1109\/TCSVT.2024.3396692","volume":"34","author":"Y-M Li","year":"2024","unstructured":"Li, Y.-M., Zeng, L.-A., Meng, J.-K. & Zheng, W.-S. Continual action assessment via task-consistent score-discriminative feature distribution modeling. IEEE Trans. Circuits Syst. Video Technol. 34, 9112\u20139124. https:\/\/doi.org\/10.1109\/TCSVT.2024.3396692 (2024).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR66","doi-asserted-by":"publisher","unstructured":"Zhou, K. et al. MAGR: Manifold-aligned graph regularization for continual action quality assessment. European Conference on Computer Vision 375\u2013392. https:\/\/doi.org\/10.1007\/978-3-031-73247-8_22 (2024).","DOI":"10.1007\/978-3-031-73247-8_22"},{"key":"36668_CR67","doi-asserted-by":"publisher","unstructured":"Matsuyama, H., Kawaguchi, N. & Lim, B. Y. IRIS: Interpretable rubric-informed segmentation for action quality assessment. Proceedings of the 28th International Conference on Intelligent User Interfaces 368\u2013378. https:\/\/doi.org\/10.1145\/3581641.3584048 (2023).","DOI":"10.1145\/3581641.3584048"},{"key":"36668_CR68","doi-asserted-by":"publisher","unstructured":"Okamoto, L. & Parmar, P. Hierarchical neurosymbolic approach for comprehensive and explainable action quality assessment. Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition 3204\u20133213. https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00326 (2024).","DOI":"10.1109\/CVPRW63382.2024.00326"},{"key":"36668_CR69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.11687","author":"X Dong","year":"2024","unstructured":"Dong, X., Liu, X., Li, W., Adeyemi-Ejeye, A. & Gilbert, A. Interpretable long-term action quality assessment. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2408.11687 (2024).","journal-title":"Preprint at"},{"key":"36668_CR70","doi-asserted-by":"publisher","first-page":"6017","DOI":"10.1109\/TCSVT.2022.3143549","volume":"32","author":"S-J Zhang","year":"2022","unstructured":"Zhang, S.-J., Pan, J.-H., Gao, J. & Zheng, W.-S. Semi-supervised action quality assessment with self-supervised segment feature recovery. IEEE Trans. Circuits Syst. Video Technol. 32, 6017\u20136028. https:\/\/doi.org\/10.1109\/TCSVT.2022.3143549 (2022).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR71","doi-asserted-by":"publisher","unstructured":"Parmar, P., Peh, E. & Fernando, B. Learning to visually connect actions and their effects. 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) 1477\u20131487. https:\/\/doi.org\/10.1109\/WACV61041.2025.00151 (2025).","DOI":"10.1109\/WACV61041.2025.00151"},{"key":"36668_CR72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3468870","author":"K Gedamu","year":"2024","unstructured":"Gedamu, K., Ji, Y., Yang, Y., Shao, J. & Shen, H. T. Self-supervised subaction parsing network for semi-supervised action quality assessment. IEEE Trans. Image Process. https:\/\/doi.org\/10.1109\/TIP.2024.3468870 (2024).","journal-title":"IEEE Trans. Image Process."},{"key":"36668_CR73","doi-asserted-by":"publisher","unstructured":"Yun, W., Qi, M., Peng, F. & Ma, H. Semi-supervised teacher-reference-student architecture for action quality assessment. European Conference on Computer Vision 161\u2013178. https:\/\/doi.org\/10.1007\/978-3-031-72904-1_10 (2024).","DOI":"10.1007\/978-3-031-72904-1_10"},{"key":"36668_CR74","doi-asserted-by":"publisher","unstructured":"Doughty, H., Damen, D. & Mayol-Cuevas, W. Who\u2019s better? who\u2019s best? Pairwise deep ranking for skill determination. Proceedings of the IEEE conference on computer vision and pattern recognition 6057\u20136066. https:\/\/doi.org\/10.1109\/CVPR.2018.00634 (2018).","DOI":"10.1109\/CVPR.2018.00634"},{"key":"36668_CR75","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1109\/TCSVT.2020.3017727","volume":"31","author":"H Jain","year":"2020","unstructured":"Jain, H., Harit, G. & Sharma, A. Action quality assessment using siamese network-based deep metric learning. IEEE Trans. Circuits Syst. Video Technol. 31, 2260\u20132273. https:\/\/doi.org\/10.1109\/TCSVT.2020.3017727 (2020).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR76","doi-asserted-by":"publisher","unstructured":"Doughty, H., Mayol-Cuevas, W. & Damen, D. The pros and cons: Rank-aware temporal attention for skill determination in long videos. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 7862\u20137871. https:\/\/doi.org\/10.1109\/CVPR.2019.00805 (2019).","DOI":"10.1109\/CVPR.2019.00805"},{"key":"36668_CR77","doi-asserted-by":"publisher","unstructured":"Bai, Y. et al. Action quality assessment with temporal parsing transformer. European conference on computer vision 422\u2013438. https:\/\/doi.org\/10.1007\/978-3-031-19772-7_25 (2022).","DOI":"10.1007\/978-3-031-19772-7_25"},{"key":"36668_CR78","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3459938","author":"Z Luo","year":"2024","unstructured":"Luo, Z., Xiao, Y., Yang, F., Zhou, J. T. & Fang, Z. Rhythmer: Ranking-based skill assessment with rhythm-aware transformer. IEEE Trans. Circuits Syst. Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2024.3459938 (2024).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"36668_CR79","doi-asserted-by":"publisher","first-page":"6386","DOI":"10.1109\/TIP.2023.3331212","volume":"32","author":"K Gedamu","year":"2023","unstructured":"Gedamu, K., Ji, Y., Yang, Y., Shao, J. & Shen, H. T. Fine-grained spatio-temporal parsing network for action quality assessment. IEEE Trans. Image Process. 32, 6386\u20136400. https:\/\/doi.org\/10.1109\/TIP.2023.3331212 (2023).","journal-title":"IEEE Trans. Image Process."},{"key":"36668_CR80","doi-asserted-by":"publisher","unstructured":"Xu, J., Yin, S., Zhao, G., Wang, Z. & Peng, Y. Fineparser: A fine-grained spatio-temporal action parser for human-centric action quality assessment. Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition 14628\u201314637. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01386 (2024).","DOI":"10.1109\/CVPR52733.2024.01386"},{"key":"36668_CR81","doi-asserted-by":"publisher","first-page":"6069","DOI":"10.1007\/s11263-024-02146-z","volume":"132","author":"J Xu","year":"2024","unstructured":"Xu, J., Rao, Y., Zhou, J. & Lu, J. Procedure-aware action quality assessment: Datasets and performance evaluation. Int. J. Comput. Vis. 132, 6069\u20136090. https:\/\/doi.org\/10.1007\/s11263-024-02146-z (2024).","journal-title":"Int. J. Comput. Vis."},{"key":"36668_CR82","doi-asserted-by":"publisher","first-page":"96","DOI":"10.26555\/ijain.v9i1.919","volume":"9","author":"I Hipiny","year":"2023","unstructured":"Hipiny, I., Ujir, H., Alias, A. A., Shanat, M. & Ishak, M. K. Who danced better? Ranked TikTok dance video dataset and pairwise action quality assessment method. Int. J. Adv. Intell. Inform. 9, 96\u2013107. https:\/\/doi.org\/10.26555\/ijain.v9i1.919 (2023).","journal-title":"Int. J. Adv. Intell. Inform."},{"key":"36668_CR83","doi-asserted-by":"publisher","unstructured":"Yu, X., Rao, Y., Zhao, W., Lu, J. & Zhou, J. Group-aware contrastive regression for action quality assessment. Proceedings of the IEEE\/CVF international conference on computer vision 7919\u20137928. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00782 (2021).","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"36668_CR84","doi-asserted-by":"publisher","unstructured":"Li, M.-Z. et al. Pairwise contrastive learning network for action quality assessment. European Conference on Computer Vision 457\u2013473. https:\/\/doi.org\/10.1007\/978-3-031-19772-7_27 (2022).","DOI":"10.1007\/978-3-031-19772-7_27"},{"key":"36668_CR85","doi-asserted-by":"publisher","unstructured":"An, Q., Qi, M. & Ma, H. Multi-stage contrastive regression for action quality assessment. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 4110\u20134114. https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447069 (2024).","DOI":"10.1109\/ICASSP48485.2024.10447069"},{"key":"36668_CR86","doi-asserted-by":"publisher","unstructured":"Fang, M. et al. Which is the better teacher action? A new ranking model and dataset. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 7695\u20137699. https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448158 (2024).","DOI":"10.1109\/ICASSP48485.2024.10448158"},{"key":"36668_CR87","doi-asserted-by":"publisher","first-page":"8779","DOI":"10.1109\/TPAMI.2021.3126534","volume":"44","author":"J-H Pan","year":"2021","unstructured":"Pan, J.-H., Gao, J. & Zheng, W.-S. Adaptive action assessment. IEEE Trans. Pattern Anal. Mach. Intell. 44, 8779\u20138795. https:\/\/doi.org\/10.1109\/TPAMI.2021.3126534 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36668_CR88","doi-asserted-by":"publisher","first-page":"4061","DOI":"10.1109\/TMM.2023.3294800","volume":"26","author":"S-J Zhang","year":"2023","unstructured":"Zhang, S.-J., Pan, J.-H., Gao, J. & Zheng, W.-S. Adaptive stage-aware assessment skill transfer for skill determination. IEEE Trans. Multimedia 26, 4061\u20134072. https:\/\/doi.org\/10.1109\/TMM.2023.3294800 (2023).","journal-title":"IEEE Trans. Multimedia"},{"key":"36668_CR89","doi-asserted-by":"publisher","unstructured":"Tao, L. et al. Sparse hidden markov models for surgical gesture classification and skill evaluation. International conference on information processing in computer-assisted interventions 167\u2013177. https:\/\/doi.org\/10.1007\/978-3-642-30618-1_17 (2012).","DOI":"10.1007\/978-3-642-30618-1_17"},{"key":"36668_CR90","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1007\/s11548-018-1735-5","volume":"13","author":"A Zia","year":"2018","unstructured":"Zia, A. & Essa, I. Automated surgical skill assessment in RMIS training. Int. J. Comput. Assist. Radiol. Surg. 13, 731\u2013739. https:\/\/doi.org\/10.1007\/s11548-018-1735-5 (2018).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"36668_CR91","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s11548-018-1704-z","volume":"13","author":"A Zia","year":"2018","unstructured":"Zia, A., Sharma, Y., Bettadapura, V., Sarin, E. L. & Essa, I. Video and accelerometer-based motion analysis for automated surgical skills assessment. Int. J. Comput. Assist. Radiol. Surg. 13, 443\u2013455. https:\/\/doi.org\/10.1007\/s11548-018-1704-z (2018).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"36668_CR92","doi-asserted-by":"publisher","unstructured":"Li, C., Ling, X. & Xia, S. A graph convolutional siamese network for the assessment and recognition of physical rehabilitation exercises. International conference on artificial neural networks 229\u2013240. https:\/\/doi.org\/10.1007\/978-3-031-44216-2_19 (2023).","DOI":"10.1007\/978-3-031-44216-2_19"},{"key":"36668_CR93","doi-asserted-by":"publisher","first-page":"2612","DOI":"10.1109\/TNSRE.2023.3282675","volume":"31","author":"K Zheng","year":"2023","unstructured":"Zheng, K., Wu, J., Zhang, J. & Guo, C. A skeleton-based rehabilitation exercise assessment system with rotation invariance. IEEE Trans. Neural Syst. Rehabil. Eng. 31, 2612\u20132621. https:\/\/doi.org\/10.1109\/TNSRE.2023.3282675 (2023).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"36668_CR94","doi-asserted-by":"publisher","first-page":"6471","DOI":"10.1109\/TPAMI.2024.3378753","volume":"46","author":"XB Bruce","year":"2024","unstructured":"Bruce, X. B., Liu, Y., Chan, K. C. C. & Chen, C. W. EGCN++: A new fusion strategy for ensemble learning in skeleton-based rehabilitation exercise assessment. IEEE Trans. Pattern Anal. Mach. Intell. 46, 6471\u20136485. https:\/\/doi.org\/10.1109\/TPAMI.2024.3378753 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36668_CR95","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.13999","author":"K Zhou","year":"2024","unstructured":"Zhou, K. et al. Cofinal: Enhancing action quality assessment with coarse-to-fine instruction alignment. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2404.13999 (2024).","journal-title":"Preprint at"},{"key":"36668_CR96","doi-asserted-by":"publisher","unstructured":"Sarfraz, S. et al. Temporally-weighted hierarchical clustering for unsupervised action segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 11225\u201311234. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01107 (2021).","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"36668_CR97","unstructured":"Paszke, A. et al. Automatic differentiation in PyTorch. In Advances in Neural Information Processing Systems 30(2017)."},{"key":"36668_CR98","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","author":"DP Kingma","year":"2014","unstructured":"Kingma, D. P. & Ba, J. A method for stochastic optimization. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1412.6980 (2014).","journal-title":"Preprint at"},{"key":"36668_CR99","unstructured":"Kay, W. et al. The kinetics human action video dataset. Preprint at arXiv:1705.06950 (2017)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36668-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36668-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36668-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T22:02:44Z","timestamp":1771365764000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36668-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":99,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["36668"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-36668-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"28 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6670"}}