{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T22:49:31Z","timestamp":1767998971279,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208691","type":"print"},{"value":"9783030208707","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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\/978-3-030-20870-7_44","type":"book-chapter","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T16:14:21Z","timestamp":1558714461000},"page":"712-728","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Dynamic Temporal Pyramid Network: A Closer Look at Multi-scale Modeling for Activity Detection"],"prefix":"10.1007","author":[{"given":"Da","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiyang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Fang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,25]]},"reference":[{"issue":"6","key":"44_CR1","first-page":"33","volume":"29","author":"EH Adelson","year":"1984","unstructured":"Adelson, E.H., Anderson, C.H., Bergen, J.R., Burt, P.J., Ogden, J.M.: Pyramid methods in image processing. RCA Eng. 29(6), 33\u201341 (1984)","journal-title":"RCA Eng."},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Ghanem, B., Fei-Fei, L., Niebles, J.: End-to-end, single-stream temporal action detection in untrimmed videos. In: BMVC (2017)","DOI":"10.5244\/C.31.93"},{"key":"44_CR3","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":"44_CR4","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":"44_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/978-3-319-46493-0_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Cai","year":"2016","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354\u2013370. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_22"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733. IEEE (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"44_CR9","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":"44_CR10","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection. In: BMVC (2017)","DOI":"10.5244\/C.31.52"},{"key":"44_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":"44_CR12","unstructured":"Jiang, Y., et al.: Thumos challenge: action recognition with a large number of classes (2014)"},{"key":"44_CR13","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":"44_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944. IEEE (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"44_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":"44_CR16","unstructured":"Mahasseni, B., Yang, X., Molchanov, P., Kautz, J.: Budget-aware activity detection with a recurrent policy network. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)"},{"key":"44_CR17","doi-asserted-by":"crossref","unstructured":"Mettes, P., van Gemert, J.C., Cappallo, S., Mensink, T., Snoek, C.G.: Bag-of-fragments: selecting and encoding video fragments for event detection and recounting. In: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, pp. 427\u2013434. ACM (2015)","DOI":"10.1145\/2671188.2749404"},{"key":"44_CR18","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":"44_CR19","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"44_CR20","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":"44_CR21","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":"44_CR22","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":"44_CR23","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection-snip. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3578\u20133587 (2018)","DOI":"10.1109\/CVPR.2018.00377"},{"key":"44_CR24","doi-asserted-by":"crossref","unstructured":"Dai, X., Southall, B., Trinh, N., Matei, B.: Efficient fine-grained classification and part localization using one compact network. In: 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), pp. 996\u20131004 (2017)","DOI":"10.1109\/ICCVW.2017.122"},{"key":"44_CR25","unstructured":"Singh, G., Cuzzolin, F.: Untrimmed video classification for activity detection: submission to activitynet challenge. arXiv preprint arXiv:1607.01979 (2016)"},{"key":"44_CR26","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":"44_CR27","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"44_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"44_CR29","unstructured":"Wang, R., Tao, D.: Uts at activitynet 2016. AcitivityNet Large Scale Activity Recognition Challenge 2016, 8 (2016)"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"44_CR31","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), vol. 6, p. 8 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Dai, X., Signh, B., Ng, J.Y., Davis, L.S.: TAN: temporal aggregation network for dense multi-label action recognition. In: WACV (2019)","DOI":"10.1109\/WACV.2019.00022"},{"key":"44_CR33","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"44_CR34","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.F.: S3D: single shot multi-span detector via fully 3D convolutional network. In: BMVC (2018)"},{"key":"44_CR35","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2933\u20132942. IEEE (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"44_CR36","doi-asserted-by":"crossref","unstructured":"Dai, X., Ng J.Y., Davis, L.S.: FASON: first and second order information fusion network for texture recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7352\u20137360 (2017)","DOI":"10.1109\/CVPR.2017.646"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20870-7_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T11:56:31Z","timestamp":1633434991000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20870-7_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208691","9783030208707"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20870-7_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"979","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":"274","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":"28% - 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":"2.7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}