{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:17:14Z","timestamp":1751948234112,"version":"3.41.2"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030007669"},{"type":"electronic","value":"9783030007676"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-030-00767-6_28","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T07:54:58Z","timestamp":1537257298000},"page":"296-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Three-Stream Action Tubelet Detector for Spatiotemporal Action Detection in Videos"],"prefix":"10.1007","author":[{"given":"Yutang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"28_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume-title":"Computer Vision - ECCV 2004","author":"T Brox","year":"2004","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25\u201336. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24673-2_3"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 759\u2013768 (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J.: Towards understanding action recognition. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 3192\u20133199. IEEE (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Action tubelet detector for spatio-temporal action localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4405\u20134413 (2017)","DOI":"10.1109\/ICCV.2017.472"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Lan, T., Wang, Y., Mori, G.: Discriminative figure-centric models for joint action localization and recognition. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2003\u20132010 (2011)","DOI":"10.1109\/ICCV.2011.6126472"},{"key":"28_CR8","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":"28_CR9","doi-asserted-by":"crossref","unstructured":"Oliveira, G.L., Burgard, W., Brox, T.: Efficient deep models for monocular road segmentation. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4885\u20134891 (2016)","DOI":"10.1109\/IROS.2016.7759717"},{"key":"28_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-319-46493-0_45","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 744\u2013759. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517\u20136525 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"28_CR13","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"28_CR14","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Fast R-CNN: Towards real-time object detection with region proposal networks. In: 2015 Advances in Neural Information Processing Systems (NIPS), pp. 91\u201399 (2015)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Saha, S., Singh, G., Sapienza, M., Torr, P.H., Cuzzolin, F.: Deep learning for detecting multiple space-time action tubes in videos. arXiv preprint arXiv:1608.01529 (2016)","DOI":"10.5244\/C.30.58"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3637\u20133646 (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"28_CR17","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":"28_CR18","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Oliveira, G.L., Sedaghat, N., Brox, T.: Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2923\u20132932 (2017)","DOI":"10.1109\/ICCV.2017.316"}],"container-title":["Lecture Notes in Computer Science","Advances in Multimedia Information Processing \u2013 PCM 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00767-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T18:23:52Z","timestamp":1751912632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-00767-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030007669","9783030007676"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00767-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"19 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PCM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim Conference on Multimedia","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pcm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/pcm2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}