{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:28:02Z","timestamp":1743010082278,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811536502"},{"type":"electronic","value":"9789811536519"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-981-15-3651-9_8","type":"book-chapter","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T12:02:32Z","timestamp":1583496152000},"page":"74-84","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Spatiotemporal Saliency Based Multi-stream Networks for Action Recognition"],"prefix":"10.1007","author":[{"given":"Zhenbing","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeya","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanting","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,7]]},"reference":[{"key":"8_CR1","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (NIPS) (2014)"},{"issue":"11","key":"8_CR2","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Wildes, R.P.: Spatiotemporal residual networks for video action recognition. In: Advances in Neural Information Processing Systems (NIPS) (2016)","DOI":"10.1109\/CVPR.2017.787"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Spatiotemporal pyramid network for video action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR42600.2020.00067"},{"issue":"1","key":"8_CR5","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., et al.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Tran, D., et al.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision (ICCV) (2014)","DOI":"10.1109\/ICCV.2015.510"},{"key":"8_CR7","unstructured":"Diba, A., et al.: Temporal 3D ConvNets: new architecture and transfer learning for video classification. arXiv preprint arXiv:1711.08200 (2017)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Kar, A., et al.: AdaScan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2017.604"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Sun, S., et al.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Xie, S., et al.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: European Conference on Computer Vision (ECCV) (2017)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Jing, L., Ye, Y., Yang, X., Tian, Y.: 3D convolutional neural network with multi-model framework for action recognition. In IEEE International Conference on Image Processing (ICIP) (2017)","DOI":"10.1109\/ICIP.2017.8296599"},{"key":"8_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-030-04167-0_23","volume-title":"Neural Information Processing","author":"X Liu","year":"2018","unstructured":"Liu, X., Yang, X.: Multi-stream with deep convolutional neural networks for human action recognition in videos. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11301, pp. 251\u2013262. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-04167-0_23"},{"key":"8_CR14","unstructured":"Wang, W., Shen, J., Porikli, F.: Saliency-aware geodesic video object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)"},{"issue":"11","key":"8_CR15","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274\u20132281 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR17","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":"8_CR18","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":"8_CR19","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: IEEE International Conference on Computer Vision (ICCV) (2014)","DOI":"10.1109\/ICCV.2013.441"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: Lattice long short-term memory for human action recognition. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.236"},{"key":"8_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-642-33765-9_37","volume-title":"Computer Vision \u2013 ECCV 2012","author":"M Leordeanu","year":"2012","unstructured":"Leordeanu, M., Sukthankar, R., Sminchisescu, C.: Efficient closed-form solution to generalized boundary detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 516\u2013529. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_37"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Kuehne, H., et al.: HMDB51: a large video database for human motion recognition. In: IEEE International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1007\/978-3-642-33374-3_41"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Lei, P., Todorovic, S.: Temporal deformable residual networks for action segmentation in videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00705"},{"key":"8_CR26","unstructured":"Ng, Y.H., et al.: Beyond short snippets: deep networks for video classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)"},{"issue":"6","key":"8_CR27","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","volume":"28","author":"R Poppe","year":"2010","unstructured":"Poppe, R.: A survey on vision-based human action recognition. Image Vis. Comput. 28(6), 976\u2013990 (2010)","journal-title":"Image Vis. Comput."},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Huang, G., et al.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"8_CR29","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1016\/j.neunet.2019.08.022","volume":"121","author":"C Tian","year":"2020","unstructured":"Tian, C., et al.: Image denoising using deep CNN with batch renormalization. Neural Netw. 121, 461\u2013473 (2020)","journal-title":"Neural Netw."}],"container-title":["Communications in Computer and Information Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-3651-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T22:29:54Z","timestamp":1614724194000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-3651-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9789811536502","9789811536519"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-3651-9_8","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 March 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"214","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":"125","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":"58% - 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","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)"}},{"value":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}