{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T22:43:06Z","timestamp":1760395386254,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030606381"},{"type":"electronic","value":"9783030606398"}],"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_4","type":"book-chapter","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T10:04:02Z","timestamp":1602669842000},"page":"41-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-level Temporal Pyramid Network for Action Detection"],"prefix":"10.1007","author":[{"given":"Xiang","family":"Wang","sequence":"first","affiliation":[]},{"given":"Changxin","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Shiwei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Nong","family":"Sang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,15]]},"reference":[{"unstructured":"Jiang, Y.-G., et al.: THUMOS challenge: action recognition with a large number of classes (2014)","key":"4_CR1"},{"issue":"2","key":"4_CR2","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 Recognit. Challenge 1(2), 2 (2014)","journal-title":"THUMOS14 Action Recognit. Challenge"},{"unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (2014)","key":"4_CR3"},{"doi-asserted-by":"crossref","unstructured":"Long, F., et al.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","key":"4_CR4","DOI":"10.1109\/CVPR.2019.00043"},{"doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Deep Concept-wise Temporal Convolutional Networks for Action Localization. arXiv preprint arXiv:1908.09442 (2019)","key":"4_CR5","DOI":"10.1145\/3394171.3413860"},{"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 (2016)","key":"4_CR6","DOI":"10.1109\/CVPR.2016.119"},{"doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","key":"4_CR7","DOI":"10.1109\/ICCV.2017.617"},{"doi-asserted-by":"crossref","unstructured":"Chao, Y.-W., et al.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","key":"4_CR8","DOI":"10.1109\/CVPR.2018.00124"},{"doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: BSN: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","key":"4_CR9","DOI":"10.1007\/978-3-030-01225-0_1"},{"doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: Proceedings of the 25th ACM International Conference on Multimedia (2017)","key":"4_CR10","DOI":"10.1145\/3123266.3123343"},{"doi-asserted-by":"crossref","unstructured":"Yeung, S., et al.: End-to-end learning of action detection from frame glimpses in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","key":"4_CR11","DOI":"10.1109\/CVPR.2016.293"},{"doi-asserted-by":"crossref","unstructured":"Buch, S., et al.: End-to-end, single-stream temporal action detection in untrimmed videos. In: BMVC, vol. 2 (2017)","key":"4_CR12","DOI":"10.5244\/C.31.93"},{"unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)","key":"4_CR13"},{"key":"4_CR14","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"},{"doi-asserted-by":"crossref","unstructured":"Buch, S., et al.: SST: single-stream temporal action proposals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"4_CR15","DOI":"10.1109\/CVPR.2017.675"},{"doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Turn tap: temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","key":"4_CR16","DOI":"10.1109\/ICCV.2017.392"},{"doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, K., Nevatia, R.: CTAP: complementary temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","key":"4_CR17","DOI":"10.1007\/978-3-030-01216-8_5"},{"doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: Temporal context network for activity localization in videos. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","key":"4_CR18","DOI":"10.1109\/ICCV.2017.610"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision (2017)","key":"4_CR19","DOI":"10.1109\/ICCV.2017.317"},{"unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)","key":"4_CR20"},{"doi-asserted-by":"crossref","unstructured":"Shou, Z., et al.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"4_CR21","DOI":"10.1109\/CVPR.2017.155"},{"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":"4_CR22","DOI":"10.5244\/C.31.52"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: M2Det: a single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33 (2019)","key":"4_CR23","DOI":"10.1609\/aaai.v33i01.33019259"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Multi-granularity generator for temporal action proposal. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","key":"4_CR24","DOI":"10.1109\/CVPR.2019.00372"},{"doi-asserted-by":"crossref","unstructured":"Singh, B., et al.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","key":"4_CR25","DOI":"10.1109\/CVPR.2016.216"},{"doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","key":"4_CR26","DOI":"10.1109\/ICCV.2019.00719"},{"doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","key":"4_CR27","DOI":"10.1109\/ICCV.2019.00399"},{"doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: Temporal action localization by structured maximal sums. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"4_CR28","DOI":"10.1109\/CVPR.2017.342"},{"doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., et al.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","key":"4_CR29","DOI":"10.1109\/CVPR.2015.7298698"},{"unstructured":"Singh, G., Cuzzolin, F.: Untrimmed video classification for activity detection: submission to activitynet challenge. arXiv preprint arXiv:1607.01979 (2016)","key":"4_CR30"},{"unstructured":"Xiong, Y., et al.: A pursuit of temporal accuracy in general activity detection. arXiv preprint arXiv:1703.02716 (2017)","key":"4_CR31"},{"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 (2016)","key":"4_CR32","DOI":"10.1109\/CVPR.2016.341"},{"doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Carlos Niebles, J., Ghanem, B.: Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","key":"4_CR33","DOI":"10.1109\/CVPR.2016.211"},{"key":"4_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":"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"},{"doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., et al.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","key":"4_CR35","DOI":"10.1109\/CVPR.2019.00075"},{"unstructured":"Oneata, D., Verbeek, J., Schmid, C.: The lear submission at thumos 2014 (2014)","key":"4_CR36"},{"doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","key":"4_CR37","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"crossref","unstructured":"Yuan, J., et al.: Temporal action localization with pyramid of score distribution features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","key":"4_CR38","DOI":"10.1109\/CVPR.2016.337"},{"unstructured":"Wang, R., Tao, D.: UTS at activitynet 2016. AcitivityNet Large Scale Activity Recognition Challenge 8, 2016 (2016)","key":"4_CR39"},{"unstructured":"Lin, T., Zhao, X., Shou, Z.: Temporal convolution based action proposal: submission to activitynet 2017. arXiv preprint arXiv:1707.06750 (2017)","key":"4_CR40"},{"key":"4_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-540-74936-3_22","volume-title":"Pattern Recognition","author":"C Zach","year":"2007","unstructured":"Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L$$^{1}$$ optical flow. In: Hamprecht, F.A., Schn\u00f6rr, C., J\u00e4hne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214\u2013223. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74936-3_22"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","key":"4_CR42","DOI":"10.1109\/CVPR.2018.00745"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"4_CR43"},{"unstructured":"Zhao, Y., et al.: Cuhk & ethz & siat submission to activitynet challenge 2017. arXiv preprint arXiv:1710.08011 8 (2017)","key":"4_CR44"}],"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_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T22:04:11Z","timestamp":1760393051000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60639-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030606381","9783030606398"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60639-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}