{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T10:18:23Z","timestamp":1778408303278,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030208929","type":"print"},{"value":"9783030208936","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\/978-3-030-20893-6_23","type":"book-chapter","created":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T07:25:52Z","timestamp":1559028352000},"page":"363-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":115,"title":["Hidden Two-Stream Convolutional Networks for Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6482-6712","authenticated-orcid":false,"given":"Yi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4763-6148","authenticated-orcid":false,"given":"Zhenzhong","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6803-5291","authenticated-orcid":false,"given":"Shawn","family":"Newsam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2123-0684","authenticated-orcid":false,"given":"Alexander","family":"Hauptmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,29]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"23_CR2","unstructured":"Diba, A., Pazandeh, A.M., Van Gool, L.: Efficient two-stream motion and appearance 3D CNNs for video classification. In: European Conference on Computer Vision (ECCV) Workshops (2016)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Fernando, B., Gavves, E., Oramas, J.M., Ghodrati, A., Tuytelaars, T.: Modeling video evolution for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"23_CR4","unstructured":"Fischer, P., et al.: FlowNet: learning optical flow with convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)"},{"key":"23_CR5","unstructured":"Gorban, A., et al.: THUMOS challenge: action recognition with a large number of classes (2015). http:\/\/www.thumos.info\/"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Gu, B., Xin, M., Huo, Z., Huang, H.: Asynchronous doubly stochastic sparse kernel learning. In: Association for the Advancement of Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.11803"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"23_CR9","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer network. In: Neural Information Processing Systems (NIPS) (2015)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Kantorov, V., Laptev, I.: Efficient feature extraction, encoding and classification for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.332"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: International Conference on Computer Vision (ICCV) (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Lan, Z., Zhu, Y., Hauptmann, A.G., Newsam, S.: Deep local video feature for action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPRW.2017.161"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Miao, X., Zhen, X., Liu, X., Deng, C., Athitsos, V., Huang, H.: Direct shape regression networks for end-to-end face alignment. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00529"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Ng, J.Y.H., Choi, J., Neumann, J., Davis, L.S.: ActionFlowNet: learning motion representation for action recognition. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00179"},{"key":"23_CR16","unstructured":"Ng, J.Y.H., Hausknecht, M., Vijay., S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"23_CR18","unstructured":"Sedaghat, N.: Next-flow: hybrid multi-tasking with next-frame prediction to boost optical-flow estimation in the wild. arXiv:1612.03777 (2016)"},{"key":"23_CR19","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Neural Information Processing Systems (NIPS) (2014)"},{"key":"23_CR20","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild. In: CRCV-TR-12-01 (2012)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"23_CR22","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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"23_CR24","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream ConvNets. arXiv:1507.02159 (2015)"},{"key":"23_CR25","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":"23_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Zaheer, M., Hu, H., Manmatha, R., Smola, A.J., Kr\u00e4henb\u00fchl, P.: Compressed video action recognition. arXiv:1712.00636 (2017)","DOI":"10.1109\/CVPR.2018.00631"},{"key":"23_CR28","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning for video understanding. arXiv:1712.04851 (2017)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Xue, J., Zhang, H., Dana, K.: Deep texture manifold for ground terrain recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00065"},{"key":"23_CR30","unstructured":"Xue, T., Chen, B., Wu, J., Wei, D., Freeman, W.T.: Video enhancement with task-oriented flow. arXiv:1711.09078 (2017)"},{"key":"23_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-49409-8_1","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"JJ Yu","year":"2016","unstructured":"Yu, J.J., Harley, A.W., Derpanis, K.G.: Back to basics: unsupervised learning of optical flow via brightness constancy and motion smoothness. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 3\u201310. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_1"},{"key":"23_CR32","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-L1 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"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.297"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Long, Y., Guan, Y., Newsam, S., Shao, L.: Towards universal representation for unseen action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00983"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Newsam, S.: DenseNet for dense flow. In: IEEE International Conference on Image Processing (ICIP) (2017)","DOI":"10.1109\/ICIP.2017.8296389"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Newsam, S.: Learning optical flow via dilated networks and occlusion reasoning. In: IEEE International Conference on Image Processing (ICIP) (2018)","DOI":"10.1109\/ICIP.2018.8451790"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20893-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T18:46:42Z","timestamp":1663526802000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20893-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208929","9783030208936"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20893-6_23","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":"29 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"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"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"}},{"value":"274","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":"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"}},{"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"}},{"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"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}