{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:30:37Z","timestamp":1775190637235,"version":"3.50.1"},"reference-count":25,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2025,3,1]]},"DOI":"10.1587\/transfun.2024smp0003","type":"journal-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T22:11:48Z","timestamp":1724105508000},"page":"332-341","source":"Crossref","is-referenced-by-count":5,"title":["A Hierarchical Joint Training Based Replay-Guided Contrastive Transformer for Action Quality Assessment of Figure Skating"],"prefix":"10.1587","volume":"E108.A","author":[{"given":"Yanchao","family":"LIU","sequence":"first","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xina","family":"CHENG","sequence":"additional","affiliation":[{"name":"Xidian University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeshi","family":"IKENAGA","sequence":"additional","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. Xu, Y. Rao, X. Yu, G. Chen, J. Zhou, and J. Lu, \u201cFineDiving: A fine-grained dataset for procedure-aware action quality assessment,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.2949-2958, 2022. 10.1109\/cvpr52688.2022.00296","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] D. Liu, Q. Li, T. Jiang, Y. Wang, R. Miao, F. Shan, and Z. Li, \u201cTowards unified surgical skill assessment,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.9522-9531, 2021. 10.1109\/cvpr46437.2021.00940","DOI":"10.1109\/CVPR46437.2021.00940"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] C. Yang, Y. Xu, J. Shi, B. Dai, and B. Zhou, \u201cTemporal pyramid network for action recognition,\u201d 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp.588-597, IEEE, June 2020. 10.1109\/cvpr42600.2020.00067","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] R. Li, L. Yan, Y. Peng, and L. Qing, \u201cLighter transformer for online action detection,\u201d Proc. 2023 6th International Conference on Image and Graphics Processing, Chongqing China, pp.161-167, ACM, Jan. 2023. 10.1145\/3582649.3582656","DOI":"10.1145\/3582649.3582656"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] Y. Tang, Z. Ni, J. Zhou, D. Zhang, J. Lu, Y. Wu, and J. Zhou, \u201cUncertainty-aware score distribution learning for action quality assessment,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.9839-9848, 2020. 10.1109\/cvpr42600.2020.00986","DOI":"10.1109\/CVPR42600.2020.00986"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] S. Wang, D. Yang, P. Zhai, C. Chen, and L. Zhang, \u201cTSA-Net: Tube self-attention network for action quality assessment,\u201d Proc. 29th ACM International Conference on Multimedia, pp.4902-4910, 2021. 10.1145\/3474085.3475438","DOI":"10.1145\/3474085.3475438"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Y. Bai, D. Zhou, S. Zhang, J. Wang, E. Ding, Y. Guan, Y. Long, and J. Wang, \u201cAction quality assessment with temporal parsing transformer,\u201d Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, Oct. 2022, Proceedings, Part IV, pp.422-438, Springer, 2022. 10.1007\/978-3-031-19772-7_25","DOI":"10.1007\/978-3-031-19772-7_25"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] M. Li, H.B. Zhang, Q. Lei, Z. Fan, J. Liu, and J.X. Du, \u201cPairwise contrastive learning network for action quality assessment,\u201d Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, Oct. 2022, Proceedings, Part IV, pp.457-473, Springer, 2022. 10.1007\/978-3-031-19772-7_27","DOI":"10.1007\/978-3-031-19772-7_27"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] X. Yu, Y. Rao, W. Zhao, J. Lu, and J. Zhou, \u201cGroup-aware contrastive regression for action quality assessment,\u201d Proc. IEEE\/CVF International Conference on Computer Vision, pp.7919-7928, 2021. 10.1109\/iccv48922.2021.00782","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] Y. Liu, X. Cheng, and T. Ikenaga, \u201cA figure skating jumping dataset for replay-guided action quality assessment,\u201d ACM Multimedia (MM2023), pp.2437-2445, 2023. 10.1145\/3581783.3613774","DOI":"10.1145\/3581783.3613774"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] H. Pirsiavash, C. Vondrick, and A. Torralba, \u201cAssessing the quality of actions,\u201d Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, Sept. 2014, Proceedings, Part VI 13, pp.556-571, Springer, 2014. 10.1007\/978-3-319-10599-4_36","DOI":"10.1007\/978-3-319-10599-4_36"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] P. Parmar and B. Tran Morris, \u201cLearning to score olympic events,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.20-28, 2017. 10.1109\/cvprw.2017.16","DOI":"10.1109\/CVPRW.2017.16"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] P. Parmar and B.T. Morris, \u201cWhat and how well you performed? A multitask learning approach to action quality assessment,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.304-313, 2019. 10.1109\/cvpr.2019.00039","DOI":"10.1109\/CVPR.2019.00039"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] G. Bertasius, H. Soo Park, S.X. Yu, and J. Shi, \u201cAm I a baller? Basketball performance assessment from first-person videos,\u201d Proc. IEEE International Conference on Computer Vision, pp.2177-2185, 2017. 10.1109\/iccv.2017.239","DOI":"10.1109\/ICCV.2017.239"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] C. Xu, Y. Fu, B. Zhang, Z. Chen, Y.G. Jiang, and X. Xue, \u201cLearning to score figure skating sport videos,\u201d IEEE Trans. Circuits Syst. Video Technol., vol.30, no.12, pp.4578-4590, 2019. 10.1109\/tcsvt.2019.2927118","DOI":"10.1109\/TCSVT.2019.2927118"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] H. Doughty, D. Damen, and W. Mayol-Cuevas, \u201cWho\u2019s better? Who\u2019s best? Pairwise deep ranking for skill determination,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.6057-6066, 2018. 10.1109\/cvpr.2018.00634","DOI":"10.1109\/CVPR.2018.00634"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] H. Doughty, W. Mayol-Cuevas, and D. Damen, \u201cThe pros and cons: Rank-aware temporal attention for skill determination in long videos,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.7862-7871, 2019. 10.1109\/cvpr.2019.00805","DOI":"10.1109\/CVPR.2019.00805"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] S. Vyas, Y.S. Rawat, and M. Shah, \u201cMulti-view action recognition using cross-view video prediction,\u201d Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, Aug. 2020, Proceedings, Part XXVII 16, pp.427-444, Springer, 2020. 10.1007\/978-3-030-58583-9_26","DOI":"10.1007\/978-3-030-58583-9_26"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] S. Yan, X. Xiong, A. Arnab, Z. Lu, M. Zhang, C. Sun, and C. Schmid, \u201cMultiview transformers for video recognition,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.3333-3343, 2022. 10.1109\/cvpr52688.2022.00333","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"20","unstructured":"[20] C.Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, \u201cDeeply-supervised nets,\u201d Artificial Intelligence and Statistics, pp.562-570, PMLR, 2015."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] C. Li, M. Zeeshan Zia, Q.H. Tran, X. Yu, G.D. Hager, and M. Chandraker, \u201cDeep supervision with shape concepts for occlusion-aware 3D object parsing,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.5465-5474, 2017. 10.1109\/cvpr.2017.49","DOI":"10.1109\/CVPR.2017.49"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] Y. Zhang and A.C. Chung, \u201cDeep supervision with additional labels for retinal vessel segmentation task,\u201d Medical Image Computing and Computer Assisted Intervention-MICCAI 2018: 21st International Conference, Granada, Spain, Sept. 2018, Proceedings, Part II 11, pp.83-91, Springer, 2018. 10.1007\/978-3-030-00934-2_10","DOI":"10.1007\/978-3-030-00934-2_10"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] J. Carreira and A. Zisserman, \u201cQuo vadis, action recognition? A new model and the kinetics dataset,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.6299-6308, 2017. 10.1109\/cvpr.2017.502","DOI":"10.1109\/CVPR.2017.502"},{"key":"24","unstructured":"[24] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems, vol.30, 2017."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] L. Zhang, X. Chen, J. Zhang, R. Dong, and K. Ma, \u201cContrastive deep supervision,\u201d European Conference on Computer Vision, pp.1-19, Springer, 2022. 10.1007\/978-3-031-19809-0_1","DOI":"10.1007\/978-3-031-19809-0_1"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E108.A\/3\/E108.A_2024SMP0003\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T03:30:46Z","timestamp":1740799846000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E108.A\/3\/E108.A_2024SMP0003\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,1]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2024smp0003","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,1]]},"article-number":"2024SMP0003"}}