{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:42:15Z","timestamp":1742913735502,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030057091"},{"type":"electronic","value":"9783030057107"}],"license":[{"start":{"date-parts":[[2018,12,8]],"date-time":"2018-12-08T00:00:00Z","timestamp":1544227200000},"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\/978-3-030-05710-7_3","type":"book-chapter","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T12:48:55Z","timestamp":1544186935000},"page":"29-41","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["STMP: Spatial Temporal Multi-level Proposal Network for Activity Detection"],"prefix":"10.1007","author":[{"given":"Guang","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,8]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: Region convolutional 3D network for temporal activity detection. In: The IEEE International Conference on Computer Vision (ICCV), p. 8. (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. arXiv preprint arXiv:1504.08083 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: Proceedings of the 2017 ACM on Multimedia Conference, pp. 988\u2013996. ACM (2017)","DOI":"10.1145\/3123266.3123343"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"3_CR6","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: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"3_CR7","doi-asserted-by":"crossref","first-page":"187","DOI":"10.3233\/FI-2000-411207","volume":"41","author":"JB Roerdink","year":"2000","unstructured":"Roerdink, J.B., Meijster, A.: The watershed transform: definitions, algorithms and parallelization strategies. Fundamenta informaticae 41, 187\u2013228 (2000)","journal-title":"Fundamenta informaticae"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Niebles, J.C.: SST: Single-stream temporal action proposals. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6373\u20136382. IEEE (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 3551\u20133558. IEEE (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"3_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal multiplier networks for video action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7445\u20137454. IEEE (2017)","DOI":"10.1109\/CVPR.2017.787"},{"key":"3_CR13","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":"3_CR14","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5534\u20135542. IEEE (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"3_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"3_CR16","unstructured":"Jiang, Y., et al.: THUMOS challenge: action recognition with a large number of classes (2014)"},{"key":"3_CR17","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Ma, S., Sigal, L., Sclaroff, S.: Learning activity progression in LSTMs for activity detection and early detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1942\u20131950 (2016)","DOI":"10.1109\/CVPR.2016.214"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1961\u20131970. IEEE (2016)","DOI":"10.1109\/CVPR.2016.216"},{"key":"3_CR20","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2678\u20132687 (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3093\u20133102 (2016)","DOI":"10.1109\/CVPR.2016.337"},{"key":"3_CR22","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)","DOI":"10.1109\/CVPR.2016.119"},{"key":"3_CR23","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":"3_CR24","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: The LEAR submission at Thumos 2014 (2014)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Richard, A., Gall, J.: Temporal action detection using a statistical language model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3131\u20133140 (2016)","DOI":"10.1109\/CVPR.2016.341"},{"key":"3_CR26","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)","DOI":"10.1109\/CVPR.2017.155"},{"key":"3_CR27","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)","DOI":"10.1109\/ICCV.2017.610"},{"key":"3_CR28","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":"3_CR29","unstructured":"Wang, R., Tao, D.: UTS at activitynet 2016. AcitivityNet Large Scale Activity Recognition Challenge 2016, 8 (2016)"},{"key":"3_CR30","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":"V Escorcia","year":"2016","unstructured":"Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05710-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T02:35:39Z","timestamp":1605580539000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05710-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,8]]},"ISBN":["9783030057091","9783030057107"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05710-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,12,8]]},"assertion":[{"value":"8 December 2018","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":"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"}}]}}