{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:41:13Z","timestamp":1742992873527,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377304"},{"type":"electronic","value":"9783030377311"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-37731-1_42","type":"book-chapter","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T01:02:51Z","timestamp":1577408571000},"page":"519-531","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grain Level Sports Video Search Engine"],"prefix":"10.1007","author":[{"given":"Zikai","family":"Song","sequence":"first","affiliation":[]},{"given":"Junqing","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Hengyou","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Yangliu","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yi-Ping Phoebe","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"issue":"6","key":"42_CR1","first-page":"734","volume":"4","author":"P Geetha","year":"2008","unstructured":"Geetha, P., Narayanan, V.: A survey of content-based video retrieval. J. Comput. Sci. 4(6), 734 (2008)","journal-title":"J. Comput. Sci."},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., et al.: Rethinking the faster R-CNN architecture for temporal action localization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"42_CR3","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Tianwei Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., et al.: BSN: boundary sensitive network for temporal action proposal generation. In: European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)"},{"key":"42_CR4","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., Huang, J., Abu-El-Haija, S., et al.: Detecting events and key actors in multi-person videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3043\u20133053 (2016)","DOI":"10.1109\/CVPR.2016.332"},{"key":"42_CR5","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.S., Muralidharan, S., Deng, Z., et al.: A hierarchical deep temporal model for group activity recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1971\u20131980 (2016)","DOI":"10.1109\/CVPR.2016.217"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M.D., Vidal, R., et al.: Temporal convolutional networks for action segmentation and detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1003\u20131012 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., et al.: Dense-captioning events in videos. In: IEEE International Conference on Computer Vision (ICCV), pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"issue":"6","key":"42_CR8","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TMM.2005.858397","volume":"7","author":"A. Hanjalic","year":"2005","unstructured":"Hanjalic, A.: Adaptive extraction of highlights from a sport video based on excitement modeling. IEEE Trans. Multimedia 7(6), 1114\u20131122 (2005)","journal-title":"IEEE Transactions on Multimedia"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in video. In: IEEE International Conference on Computer Vision (ICCV), pp. 1470\u20131477 (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"42_CR10","doi-asserted-by":"crossref","unstructured":"Jegou, H., Douze, M., Schmid, C., et al.: Aggregating local descriptors into a compact image representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3304\u20133311 (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Wengert, C., Douze, M., Jegou, H.: Bag-of-colors for improved image search. In: 19th ACM International Conference on Multimedia, pp. 1437\u20131440 (2011)","DOI":"10.1145\/2072298.2072034"},{"issue":"1","key":"42_CR12","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2011","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Tavenard, R., Jegou, H., Amsaleg, L.: Balancing clusters to reduce response time variability in large scale image search. In: 9th International Workshop on Content-Based Multimedia Indexing (CBMI), pp. 19\u201324 (2011)","DOI":"10.1109\/CBMI.2011.5972514"},{"key":"42_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \narXiv:1409.1556\n\n (2014)"},{"key":"42_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint \narXiv:1502.03167\n\n (2015)"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep Residual Learning for Image Recognition. arXiv preprint \narXiv:1512.03385\n\n (2015)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"42_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(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"42_CR18","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: neural image caption generation with visual attention. arXiv preprint \narXiv:1502.03044\n\n (2015)"},{"key":"42_CR19","unstructured":"Yu, J., Wang, N.: Shot classification for soccer video based on sub-window region. J. Image Graph.\u00a01006\u20138961 (2008). 07-1347-06"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Gan, C., et al.: DevNet: a deep event network for multimedia event detection and evidence recounting. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Buch, S., et al.: SST: single-stream temporal action proposals. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Yu, J.Q., Lei, A.P., Song, Z.K., et al.: Comprehensive dataset of broadcast soccer videos. In: IEEE International Conference on Multimedia Information Processing and Retrieval (2018)","DOI":"10.1109\/MIPR.2018.00090"},{"key":"42_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1007\/978-3-540-88682-2_24","volume-title":"Computer Vision \u2013 ECCV 2008","author":"H Jegou","year":"2008","unstructured":"Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 304\u2013317. Springer, Heidelberg (2008). \nhttps:\/\/doi.org\/10.1007\/978-3-540-88682-2_24"},{"key":"42_CR25","unstructured":"Herve, J., Matthijs, D., Cordelia, S., et al.: Aggregating local descriptors into a compact image representation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3304\u20133311 (2010)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37731-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T11:22:54Z","timestamp":1580988174000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37731-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377304","9783030377311"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37731-1_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"171","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":"40","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":"23% - 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":"5","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)"}},{"value":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS 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 (provided by the conference organizers)"}}]}}