{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:30:00Z","timestamp":1781584200009,"version":"3.54.5"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197710","type":"print"},{"value":"9783031197727","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19772-7_25","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"422-438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Action Quality Assessment with\u00a0Temporal Parsing Transformer"],"prefix":"10.1007","author":[{"given":"Yang","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Desen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Errui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.B., Laptev, I., Sivic, J., Lacoste-Julien, S.: Joint discovery of object states and manipulation actions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2127\u20132136 (2017)","DOI":"10.1109\/ICCV.2017.234"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Bertasius, G., Soo Park, H., Yu, S.X., Shi, J.: Am i a baller? basketball performance assessment from first-person videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2177\u20132185 (2017)","DOI":"10.1109\/ICCV.2017.239"},{"key":"25_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Doughty, H., Damen, D., Mayol-Cuevas, W.: Who\u2019s better? who\u2019s best? pairwise deep ranking for skill determination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6057\u20136066 (2018)","DOI":"10.1109\/CVPR.2018.00634"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Doughty, H., Mayol-Cuevas, W., Damen, D.: The pros and cons: rank-aware temporal attention for skill determination in long videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7862\u20137871 (2019)","DOI":"10.1109\/CVPR.2019.00805"},{"key":"25_CR7","unstructured":"Gao, Y., et al.: Jhu-isi gesture and skill assessment working set (jigsaws): a surgical activity dataset for human motion modeling. In: MICCAI workshop: M2CAI, vol. 3, p. 3 (2014)"},{"key":"25_CR8","unstructured":"Gordon, A.S.: Automated video assessment of human performance. In: Proceedings of AI-ED, vol. 2 (1995)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Jug, M., Per\u0161, J., De\u017eman, B., Kova\u010di\u010d, S.: Trajectory based assessment of coordinated human activity. In: International Conference on Computer Vision Systems, pp. 534\u2013543. Springer (2003)","DOI":"10.1007\/3-540-36592-3_51"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 780\u2013787 (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6742\u20136751 (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Lei, P., Todorovic, S.: Weakly supervised energy-based learning for action segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6243\u20136251 (2019)","DOI":"10.1109\/ICCV.2019.00634"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional DETR for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"25_CR15","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing systems 30 (2017)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Pan, J.H., Gao, J., Zheng, W.S.: Action assessment by joint relation graphs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6331\u20136340 (2019)","DOI":"10.1109\/ICCV.2019.00643"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.: Action quality assessment across multiple actions. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1468\u20131476. IEEE (2019)","DOI":"10.1109\/WACV.2019.00161"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.T.: What and how well you performed? a multitask learning approach to action quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 304\u2013313 (2019)","DOI":"10.1109\/CVPR.2019.00039"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Parmar, P., Tran Morris, B.: Learning to score olympic events. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 20\u201328 (2017)","DOI":"10.1109\/CVPRW.2017.16"},{"key":"25_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1007\/978-3-319-10599-4_36","volume-title":"Computer Vision \u2013 ECCV 2014","author":"H Pirsiavash","year":"2014","unstructured":"Pirsiavash, H., Vondrick, C., Torralba, A.: Assessing the quality of actions. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 556\u2013571. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_36"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Intra-and inter-action understanding via temporal action parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 730\u2013739 (2020)","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Uncertainty-aware score distribution learning for action quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9839\u20139848 (2020)","DOI":"10.1109\/CVPR42600.2020.00986"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"25_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference On Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"25_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Wang, S., Yang, D., Zhai, P., Chen, C., Zhang, L.: TSA-NET: tube self-attention network for action quality assessment. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4902\u20134910 (2021)","DOI":"10.1145\/3474085.3475438"},{"key":"25_CR28","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. arXiv preprint arXiv:2109.07107 (2021)"},{"issue":"12","key":"25_CR29","doi-asserted-by":"publisher","first-page":"4578","DOI":"10.1109\/TCSVT.2019.2927118","volume":"30","author":"C Xu","year":"2019","unstructured":"Xu, C., Fu, Y., Zhang, B., Chen, Z., Jiang, Y.G., Xue, X.: Learning to score figure skating sport videos. IEEE Trans. Circuits Syst. Video Technol. 30(12), 4578\u20134590 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"25_CR31","unstructured":"Yi, F., Wen, H., Jiang, T.: AsFormer: transformer for action segmentation. arXiv preprint arXiv:2110.08568 (2021)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Zhao, W., Lu, J., Zhou, J.: Group-aware contrastive regression for action quality assessment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7919\u20137928 (2021)","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4486\u20134496 (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"issue":"6","key":"25_CR34","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.1109\/TPAMI.2014.2361121","volume":"37","author":"Q Zhang","year":"2014","unstructured":"Zhang, Q., Li, B.: Relative hidden Markov models for video-based evaluation of motion skills in surgical training. IEEE Trans. Pattern Anal. Mach. Intell. 37(6), 1206\u20131218 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR35","doi-asserted-by":"publisher","unstructured":"\u010cehovin Zajc, L.: A modular toolkit for visual tracking performance evaluation. SoftwareX 12, 100623 (2020). https:\/\/doi.org\/10.1016\/j.softx.2020.100623","DOI":"10.1016\/j.softx.2020.100623"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19772-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:53:47Z","timestamp":1710262427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19772-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197710","9783031197727"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19772-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}