{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T09:00:44Z","timestamp":1773738044805,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030606381","type":"print"},{"value":"9783030606398","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60639-8_1","type":"book-chapter","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T10:04:02Z","timestamp":1602669842000},"page":"3-16","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Assessing Action Quality via Attentive Spatio-Temporal Convolutional Networks"],"prefix":"10.1007","author":[{"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhengyin","family":"Du","sequence":"additional","affiliation":[]},{"given":"Annan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,15]]},"reference":[{"key":"1_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"1_CR2","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A., Gould, S.: Dynamic image networks for action recognition. In: CVPR, pp. 3034\u20133042 (2016)","DOI":"10.1109\/CVPR.2016.331"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1_CR5","unstructured":"Chollet, F., et al.: Keras: the python deep learning library. Astrophysics Source Code Library (2018)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR7","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. arXiv preprint arXiv:1502.04623 (2015)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"1_CR9","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(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR10","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/978-3-642-75988-8_28","volume-title":"Wavelets","author":"M Holschneider","year":"1990","unstructured":"Holschneider, M., Kronland-Martinet, R., Morlet, J., Tchamitchian, P.: A real-time algorithm for signal analysis with the help of the wavelet transform. In: Combes, J.M., Grossmann, A., Tchamitchian, P. (eds.) Wavelets, pp. 286\u2013297. Springer, Heidelberg (1990). https:\/\/doi.org\/10.1007\/978-3-642-75988-8_28"},{"key":"1_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"1_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NeurIPS, pp. 1097\u20131105 (2012)"},{"issue":"2\u20133","key":"1_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vision 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: CVPR, pp. 3361\u20133368 (2011)","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"1_CR16","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: CVPR, pp. 1003\u20131012 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Chai, X., Chen, X.: End-to-end learning for action quality assessment. In: PCM, pp. 125\u2013134 (2018)","DOI":"10.1007\/978-3-030-00767-6_12"},{"key":"1_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-3-030-20876-9_10","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Y Li","year":"2019","unstructured":"Li, Y., Chai, X., Chen, X.: ScoringNet: learning key fragment for action quality assessment with ranking loss in skilled sports. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11366, pp. 149\u2013164. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20876-9_10"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Park, D., Ramanan, D.: N-best maximal decoders for part models. In: ICCV, pp. 2627\u20132634 (2011)","DOI":"10.1109\/ICCV.2011.6126552"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Parmar, P., Morris, B.T.: Learning to score olympic events. In: CVPRW, pp. 76\u201384 (2017)","DOI":"10.1109\/CVPRW.2017.16"},{"key":"1_CR21","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":"1_CR22","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: ICCV, pp. 5534\u20135542 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"issue":"3","key":"1_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR24","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurIPS, pp. 568\u2013576 (2014)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Venkataraman, V., Vlachos, I., Turaga, P.K.: Dynamical regularity for action analysis. In: BMVC, pp. 67\u20131 (2015)","DOI":"10.5244\/C.29.67"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Wang, J., Du, Z., Li, A., Wang, Y.: Atrous temporal convolutional network for video action segmentation. In: ICIP, pp. 1585\u20131589 (2019)","DOI":"10.1109\/ICIP.2019.8803088"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Xiang, X., Tian, Y., Reiter, A., Hager, G.D., Tran, T.D.: S3D: stacking segmental P3D for action quality assessment. In: ICIP, pp. 928\u2013932 (2018)","DOI":"10.1109\/ICIP.2018.8451364"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Xu, B., Ye, H., Zheng, Y., Wang, H., Luwang, T., Jiang, Y.G.: Dense dilated network for few shot action recognition. In: ICMR, pp. 379\u2013387 (2018)","DOI":"10.1145\/3206025.3206028"},{"key":"1_CR31","unstructured":"Zhu, Y., Lan, Z., Newsam, S., Hauptmann, A.G.: Hidden two-stream convolutional networks for action recognition. arXiv preprint arXiv:1704.00389 (2017)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60639-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T22:03:23Z","timestamp":1760393003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60639-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030606381","9783030606398"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60639-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"15 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/index_en.html","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":"Microsoft CMT system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"402","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":"158","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":"39% - 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","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":"4","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)"}}]}}