{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T04:10:04Z","timestamp":1773115804314,"version":"3.50.1"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030057152","type":"print"},{"value":"9783030057169","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,12,11]],"date-time":"2018-12-11T00:00:00Z","timestamp":1544486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05716-9_31","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:17:32Z","timestamp":1544451452000},"page":"377-389","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Soccer Video Event Detection Based on Deep Learning"],"prefix":"10.1007","author":[{"given":"Junqing","family":"Yu","sequence":"first","affiliation":[]},{"given":"Aiping","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Yangliu","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"D\u2019Orazio, T., Leo, M.: A review of vision-based systems for soccer video analysis. Pattern Recognition (2010)","DOI":"10.1016\/j.patcog.2010.03.009"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, S. Shetty, T. Leung, R. Sukthankar, Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"31_CR3","unstructured":"Jiang, Y.-G., Liu, J., Roshan Zamir, A., Toderici, G., Laptev, I., Shah, M., Sukthankar, R.: THUMOS Challenge: Action Recognition with a Large Number of Classes (2014). http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"31_CR4","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles. J.: Activitynet: a large-scale video benchmark for human activity understanding. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: The IEEE International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"31_CR7","unstructured":"Over, P., Fiscus, J., Sanders, G., Joy, D., Michel, M., Awad, G., Smeaton, A., Kraaij, W., Qu\u00e9not, G.: Trecvid 2014\u2013an overview of the goals, tasks, data, evaluation mechanisms and metrics. In: Proceedings of TRECVID (2014)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Huang, J., Abu-El-Haija, S., Gorban, A., Murphy, K., Fei-Fei, L.: Detecting events and key actors in multi-person videos. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.332"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.368"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Xu, Z., Yang, Y., Hauptmann, A.G.: A discriminative CNN video representation for event detection. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Yang, X., Molchanov, P., Kautz, J.: Multilayer and multimodal fusion of deep neural networks for video classification. In: Proceedings of the 2016 ACM on Multimedia Conference (2016)","DOI":"10.1145\/2964284.2964297"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Yeung, D.-Y., Shi, B.E.: Human action recognition using factorized spatio-temporal convolutional networks. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.522"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., Long, M., Wang, J., Yu, P.S.: Spatiotemporal pyramid network for video action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.226"},{"issue":"1","key":"31_CR15","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"31_CR17","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: C3D: generic features for video analysis. CoRR, abs\/1412.0767 (2014)"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Li, Q., Qiu, Z., Yao, T., Mei, T., Rui, Y., Luo, J.: Action recognition by learning deep multi-granular spatio-temporal video representation. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval (2016)","DOI":"10.1145\/2964284.2984061"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"31_CR21","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using lstms. CoRR, abs\/1502.04681 (2015)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Doman, K., Tomita, T., Ide, I., Deguchi, D., Murase, H.: Event detection based on twitter enthusiasm degree for generating a sports highlight video. In: Proceedings of the 22nd ACM International Conference on Multimedia (2014)","DOI":"10.1145\/2647868.2654973"},{"issue":"2","key":"31_CR24","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/TCSVT.2013.2243640","volume":"24","author":"M Tavassolipour","year":"2014","unstructured":"Tavassolipour, M., Karimian, M., Kasaei, S.: Event detection and summarization in soccer videos using bayesian network and copula. IEEE Trans. Circuits Syst. Video Technol. 24(2), 291\u2013304 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"31_CR25","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/TBC.2015.2424011","volume":"61","author":"MH Kolekar","year":"2015","unstructured":"Kolekar, M.H., Sengupta, S.: Bayesian network-based customized highlight generation for broadcast soccer videos. IEEE Trans. Broadcast. 61(2), 195\u2013209 (2015)","journal-title":"IEEE Trans. Broadcast."},{"issue":"5","key":"31_CR26","first-page":"282","volume":"3","author":"S Arbat","year":"2014","unstructured":"Arbat, S., Sinha, S.K., Shikha, B.K.: Event detection in broadcast soccer video by detecting replays. Int. J. Sci. Technol. Res. 3(5), 282\u2013285 (2014)","journal-title":"Int. J. Sci. Technol. Res."},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.S., Muralidharan, S., Deng, Z., Vahdat, A., Mori: A hierarchical deep temporal model for group activity recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.217"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang: Temporal action localization in untrimmed videos via multi-stage CNNs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.119"},{"issue":"2","key":"31_CR29","first-page":"2","volume":"1","author":"L Wang","year":"2014","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recogn. Challenge 1(2), 2 (2014)","journal-title":"THUMOS14 Action Recogn. Challenge"},{"key":"31_CR30","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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.-F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: single-stream temporal action proposals. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"31_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Victor Escorcia","year":"2016","unstructured":"Escorcia, Victor, Caba Heilbron, Fabian, Niebles, J.C., Ghanem, Bernard: DAPs: deep action proposals for action understanding. In: Leibe, Bastian, Matas, Jiri, Sebe, Nicu, Welling, Max (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Yao, T., Mei, T., Rui, Y.: Highlight detection with pairwise deep ranking for first-person video summarization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.112"},{"key":"31_CR37","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"31_CR38","unstructured":"Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Li, F.-F.: Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos. CoRR (2015)"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Gan, C., Wang, N., Yang, Y., Yeung, D.-Y., Hauptmann, A.G.: Devnet: a deep event network for multimedia event detection and evidence recounting. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298872"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05716-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,6]],"date-time":"2019-11-06T23:52:09Z","timestamp":1573084329000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,11]]},"assertion":[{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - 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"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}