{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:44:46Z","timestamp":1743065086103,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030317225"},{"type":"electronic","value":"9783030317232"}],"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\/978-3-030-31723-2_39","type":"book-chapter","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T00:05:31Z","timestamp":1572480331000},"page":"463-474","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gemini Network for Temporal Action Localization"],"prefix":"10.1007","author":[{"given":"Hongru","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,31]]},"reference":[{"key":"39_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-030-01240-3_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Alwassel","year":"2018","unstructured":"Alwassel, H., Caba Heilbron, F., Ghanem, B.: Action search: spotting actions in videos and its application to temporal action localization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 253\u2013269. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_16"},{"key":"39_CR2","doi-asserted-by":"publisher","unstructured":"Ning, C., Zhou, H., Song, Y., Tang, J.: Inception single shot multibox detector for object detection. In: 2017 IEEE International Conference on Multimedia Expo Workshops (ICMEW), pp. 549\u2013554, July 2017. https:\/\/doi.org\/10.1109\/ICMEW.2017.8026312","DOI":"10.1109\/ICMEW.2017.8026312"},{"key":"39_CR3","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: Proceedings of the British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.93"},{"key":"39_CR4","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":"39_CR5","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: CVPR, pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Dave, A., Russakovsky, O., Ramanan, D.: Predictive-corrective networks for action detection. In: Proceedings of the Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.223"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Cascaded boundary regression for temporal action detection (2017)","DOI":"10.5244\/C.31.52"},{"key":"39_CR8","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 (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"39_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01252-6_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"FC Heilbron","year":"2018","unstructured":"Heilbron, F.C., Lee, J.-Y., Jin, H., Ghanem, B.: What do I annotate next? An empirical study of active learning for action localization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 212\u2013229. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_13"},{"key":"39_CR10","doi-asserted-by":"publisher","unstructured":"Hu, Q., Jiang, F., Mei, C., Shen, R.: CCT: a cross-concat and temporal neural network for multi-label action unit detection. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136, July 2018. https:\/\/doi.org\/10.1109\/ICME.2018.8486516","DOI":"10.1109\/ICME.2018.8486516"},{"key":"39_CR11","doi-asserted-by":"publisher","unstructured":"Huang, S., Li, X., Jiang, Z., Guo, X., Men, A.: Hyper feature fusion pyramid network for object detection. In: 2018 IEEE International Conference on Multimedia Expo Workshops (ICMEW), pp. 1\u20136, July 2018. https:\/\/doi.org\/10.1109\/ICMEW.2018.8551547","DOI":"10.1109\/ICMEW.2018.8551547"},{"key":"39_CR12","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014)"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Khandelwal, U., He, H., Qi, P., Jurafsky, D.: Sharp nearby, fuzzy far away: how neural language models use context. arXiv preprint arXiv:1805.04623 (2018)","DOI":"10.18653\/v1\/P18-1027"},{"key":"39_CR14","doi-asserted-by":"publisher","unstructured":"Li, W., Wang, W., Chen, X., Wang, J., Li, G.: A joint model for action localization and classification in untrimmed video with visual attention. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 619\u2013624, July 2017. https:\/\/doi.org\/10.1109\/ICME.2017.8019335","DOI":"10.1109\/ICME.2017.8019335"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. arXiv preprint arXiv:1806.02964 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: CVPR, pp. 6752\u20136761 (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Action and event recognition with fisher vectors on a compact feature set. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1817\u20131824 (2013)","DOI":"10.1109\/ICCV.2013.228"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. arXiv preprint arXiv:1807.10418 (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"39_CR19","doi-asserted-by":"publisher","first-page":"137","DOI":"10.5201\/ipol.2013.26","volume":"2013","author":"JS P\u00e9rez","year":"2013","unstructured":"P\u00e9rez, J.S., Meinhardt-Llopis, E., Facciolo, G.: TV-L1 optical flow estimation. Image Process. On Line 2013, 137\u2013150 (2013)","journal-title":"Image Process. On Line"},{"key":"39_CR20","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":"39_CR21","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":"39_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":"39_CR23","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":"39_CR24","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: Computer Vision and Pattern Recognition, pp. 1961\u20131970 (2016)","DOI":"10.1109\/CVPR.2016.216"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Tang, K., Yao, B., Fei-Fei, L., Koller, D.: Combining the right features for complex event recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2696\u20132703 (2013)","DOI":"10.1109\/ICCV.2013.335"},{"key":"39_CR26","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)","DOI":"10.1109\/ICCV.2015.510"},{"key":"39_CR27","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":"39_CR28","unstructured":"Xiong, Y., Zhao, Y., Wang, L., Lin, D., Tang, X.: A pursuit of temporal accuracy in general activity detection. arXiv preprint arXiv:1703.02716 (2017)"},{"key":"39_CR29","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)","DOI":"10.1109\/ICCV.2017.617"},{"key":"39_CR30","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":"39_CR31","doi-asserted-by":"crossref","unstructured":"Yuan, Z.H., Stroud, J.C., Lu, T., Deng, J.: Temporal action localization by structured maximal sums. In: CVPR, vol. 2, p. 7 (2017)","DOI":"10.1109\/CVPR.2017.342"},{"key":"39_CR32","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, vol. 2 (2017)","DOI":"10.1109\/ICCV.2017.317"}],"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\/978-3-030-31723-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:26:19Z","timestamp":1730334379000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-31723-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030317225","9783030317232"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31723-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"31 October 2019","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":"Xi'an","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv2019.com\/en\/index.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"412","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":"165","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":"40% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}