{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:53:55Z","timestamp":1740099235206,"version":"3.37.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030057152"},{"type":"electronic","value":"9783030057169"}],"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_28","type":"book-chapter","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T14:17:32Z","timestamp":1544451452000},"page":"341-351","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal Action Localization Based on Temporal Evolution Model and Multiple Instance Learning"],"prefix":"10.1007","author":[{"given":"Minglei","family":"Yang","sequence":"first","affiliation":[]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[]},{"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,11]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Cinbis, R.G., Verbeek, J., Schmid, C.: Weakly supervised object localization with multi-fold multiple instance learning. IEEE transactions on pattern analysis and machine intelligence 39(1), 189\u2013203 (2017)","key":"28_CR1","DOI":"10.1109\/TPAMI.2016.2535231"},{"doi-asserted-by":"crossref","unstructured":"Dai, X., Singh, B., Zhang, G., Davis, L.S., Chen, Y.Q.: Temporal context network for activity localization in videos. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5727\u20135736. IEEE (2017)","key":"28_CR2","DOI":"10.1109\/ICCV.2017.610"},{"issue":"1\u20132","key":"28_CR3","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"9","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T.G., Lathrop, R.H., Lozano-P\u00e9rez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 9(1\u20132), 31\u201371 (1997)","journal-title":"Artif. Intell."},{"doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. arXiv preprint arXiv:1705.01180 (2017)","key":"28_CR4","DOI":"10.5244\/C.31.52"},{"doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Sun, C., Chen, K., Nevatia, R.: Turn tap: Temporal unit regression network for temporal action proposals. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3648\u20133656. IEEE (2017)","key":"28_CR5","DOI":"10.1109\/ICCV.2017.392"},{"unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes. http:\/\/crcv.ucf.edu\/THUMOS14\/ (2014)","key":"28_CR6"},{"key":"28_CR7","series-title":"International Encyclopedia of Statistical Science","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1007\/978-3-642-04898-2_455","volume-title":"Principal Component Analysis","author":"I Jolliffe","year":"2011","unstructured":"Jolliffe, I.: Principal Component Analysis. International Encyclopedia of Statistical Science, pp. 1094\u20131096. Springer, New York (2011). https:\/\/doi.org\/10.1007\/978-3-642-04898-2_455"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"28_CR8"},{"issue":"12","key":"28_CR9","doi-asserted-by":"publisher","first-page":"i52","DOI":"10.1093\/bioinformatics\/btw252","volume":"32","author":"OZ Kraus","year":"2016","unstructured":"Kraus, O.Z., Ba, J.L., Frey, B.J.: Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics 32(12), i52\u2013i59 (2016)","journal-title":"Bioinformatics"},{"key":"28_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-319-46448-0_25","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Mallya","year":"2016","unstructured":"Mallya, A., Lazebnik, S.: Learning models for actions and person-object interactions with transfer to question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 414\u2013428. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_25"},{"unstructured":"Montes, A., Salvador, A., Pascual, S., Giro-i Nieto, X.: Temporal activity detection in untrimmed videos with recurrent neural networks. arXiv preprint arXiv:1608.08128 (2016)","key":"28_CR11"},{"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: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1417\u20131426. IEEE (2017)","key":"28_CR12","DOI":"10.1109\/CVPR.2017.155"},{"doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131058 (2016)","key":"28_CR13","DOI":"10.1109\/CVPR.2016.119"},{"unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)","key":"28_CR14"},{"doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. Center for Research in Computer Vision (CRCV), University of Central Florida (UCF) (2018)","key":"28_CR15","DOI":"10.1109\/CVPR.2018.00678"},{"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)","key":"28_CR16","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"crossref","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169\u20133176. IEEE (2011)","key":"28_CR17","DOI":"10.1109\/CVPR.2011.5995407"},{"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)","key":"28_CR18","DOI":"10.1109\/ICCV.2013.441"},{"doi-asserted-by":"crossref","unstructured":"Wu, J., Yu, Y., Huang, C., Yu, K.: Deep multiple instance learning for image classification and auto-annotation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3460\u20133469 (2015)","key":"28_CR19","DOI":"10.1109\/CVPR.2015.7298968"},{"doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-c3d: region convolutional 3D network for temporal activity detection. In: IEEE International Conference on Computer Vision (ICCV), pp. 5794\u20135803 (2017)","key":"28_CR20","DOI":"10.1109\/ICCV.2017.617"},{"issue":"2\u20134","key":"28_CR21","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s11263-017-1013-y","volume":"126","author":"S Yeung","year":"2018","unstructured":"Yeung, S., Russakovsky, O., Jin, N., Andriluka, M., Mori, G., Fei-Fei, L.: Every moment counts: dense detailed labeling of actions in complex videos. Int. J. Comput. Vis. 126(2\u20134), 375\u2013389 (2018)","journal-title":"Int. J. Comput. Vis."},{"doi-asserted-by":"crossref","unstructured":"Yun, K., Honorio, J., Chattopadhyay, D., Berg, T.L., Samaras, D.: Two-person interaction detection using body-pose features and multiple instance learning. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 28\u201335. IEEE (2012)","key":"28_CR22","DOI":"10.1109\/CVPRW.2012.6239234"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: ICCV, October 2 (2017)","key":"28_CR23","DOI":"10.1109\/ICCV.2017.317"}],"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_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,6]],"date-time":"2019-11-06T23:51:55Z","timestamp":1573084315000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05716-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,11]]},"ISBN":["9783030057152","9783030057169"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05716-9_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}