{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T13:45:20Z","timestamp":1772459120646,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"28-29","license":[{"start":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T00:00:00Z","timestamp":1623283200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T00:00:00Z","timestamp":1623283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2016R1D1A1B01016071"],"award-info":[{"award-number":["2016R1D1A1B01016071"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s11042-021-10795-2","type":"journal-article","created":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T07:07:21Z","timestamp":1623308841000},"page":"35697-35720","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Binary dense sift flow based two stream CNN for human action recognition"],"prefix":"10.1007","volume":"80","author":[{"given":"Sang Kyoo","family":"Park","sequence":"first","affiliation":[]},{"given":"Jun Ho","family":"Chung","sequence":"additional","affiliation":[]},{"given":"Tae Koo","family":"Kang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2990-8066","authenticated-orcid":false,"given":"Myo Taeg","family":"Lim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,10]]},"reference":[{"issue":"1","key":"10795_CR1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/BF01420984","volume":"12","author":"J Barron","year":"1994","unstructured":"Barron J, Fleet D, Beauchemin S (1994) System and experiment performance of optical flow techniques. Int J Comput Vision 12(1):43\u201377","journal-title":"Int J Comput Vision"},{"issue":"1","key":"10795_CR2","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/cviu.1996.0006","volume":"63","author":"MJ Black","year":"1996","unstructured":"Black MJ, Anandan P (1996) The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comput Vision Image Understand 63(1):75\u2013104","journal-title":"Comput Vision Image Understand"},{"key":"10795_CR3","unstructured":"Blunsden S, Fisher RB (2010) The behave video dataset ground truthed video for multi-person behavior classification. In: Annals of the BMVA, vol 4, pp 1\u201312"},{"key":"10795_CR4","doi-asserted-by":"crossref","unstructured":"Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. In: European conference on computer vision. Springer, pp 25\u201336","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"10795_CR5","doi-asserted-by":"crossref","unstructured":"Calonder M, Lepetit V, Ozuysal M, Trzcinski T, Strecha C, Fua P (2012) Brief:computing a local binary descriptor very fast. In: IEEE Transactions on pattern analysis and machine intelligence, vol 34, pp 1281\u20131298,","DOI":"10.1109\/TPAMI.2011.222"},{"key":"10795_CR6","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. arXiv:1405.3531","DOI":"10.5244\/C.28.6"},{"issue":"3","key":"10795_CR7","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1049\/iet-cvi.2018.5088","volume":"13","author":"VA Chenarlogh","year":"2018","unstructured":"Chenarlogh VA, Razzazi F (2018) Multi-stream 3d cnn structure for human action recognition trained by limited data. IET Comput Vis 13(3):338\u2013344","journal-title":"IET Comput Vis"},{"key":"10795_CR8","doi-asserted-by":"crossref","unstructured":"Cong G, Domeniconi G, Shapiro J, Yang CC, Chen B (2019) Video action recognition with an additional end-to-end trained temporal stream. In: 2019 IEEE Winter conference on applications of computer vision (WACV). IEEE, pp 51\u201360","DOI":"10.1109\/WACV.2019.00013"},{"key":"10795_CR9","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection"},{"key":"10795_CR10","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. In: European conference on computer vision. Springer, pp 428\u2013441","DOI":"10.1007\/11744047_33"},{"key":"10795_CR11","doi-asserted-by":"crossref","unstructured":"Dawar N, Chen C, Jafari R, Kehtarnavaz N (2017) Real-time continuous action detection and recognition using depth images and inertial signals. In: 2017 IEEE 26th international symposium on industrial electronics (ISIE). IEEE, pp 1342\u20131347","DOI":"10.1109\/ISIE.2017.8001440"},{"key":"10795_CR12","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"10795_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition. In: Advances in neural information processing systems, pp 3468\u20133476","DOI":"10.1109\/CVPR.2017.787"},{"key":"10795_CR14","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"issue":"3","key":"10795_CR15","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/TCSVT.2016.2615443","volume":"27","author":"H Fradi","year":"2016","unstructured":"Fradi H, Luvison B, Pham QC (2016) Crowd behavior analysis using local mid-level visual descriptors. IEEE Trans Circ Syst Video Technol 27 (3):589\u2013602","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"10795_CR16","doi-asserted-by":"crossref","unstructured":"Hariyono J, Jo KH (2015) Pedestrian action recognition using motion type classification. In: 2015 IEEE 2nd international conference on cybernetics (CYBCONF). IEEE, pp 129\u2013132","DOI":"10.1109\/CYBConf.2015.7175919"},{"key":"10795_CR17","doi-asserted-by":"crossref","unstructured":"Hu Y, Lu M, Lu X (2018) Spatial-temporal fusion convolutional neural network for simulated driving behavior recognition. In: 2018 15th international conference on control, automation, robotics and vision (ICARCV). IEEE, pp 1271\u20131277","DOI":"10.1109\/ICARCV.2018.8581201"},{"key":"10795_CR18","doi-asserted-by":"crossref","unstructured":"Huang CD, Wang CY, Wang JC (2015) Human action recognition system for elderly and children care using three stream convnet. In: 2015 International conference on orange technologies (ICOT). IEEE, pp 5\u20139","DOI":"10.1109\/ICOT.2015.7498476"},{"issue":"1","key":"10795_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji S, Xu W, Yang M (2012) Yu, k.: 3d convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10795_CR20","doi-asserted-by":"crossref","unstructured":"Jin CB, Li S, Kim H (2017) Real-time action detection in video surveillance using sub-action descriptor with multi-cnn. arXiv:1710.03383","DOI":"10.5302\/J.ICROS.2018.17.0243"},{"key":"10795_CR21","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"issue":"2","key":"10795_CR22","doi-asserted-by":"publisher","first-page":"627","DOI":"10.3390\/s18020627","volume":"18","author":"H Kataoka","year":"2018","unstructured":"Kataoka H, Satoh Y, Aoki Y, Oikawa S, Matsui Y (2018) Temporal and fine-grained pedestrian action recognition on driving recorder database. Sensors 18(2):627","journal-title":"Sensors"},{"key":"10795_CR23","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"10795_CR24","unstructured":"Lan Z, Lin M, Li X, Hauptmann AG, Raj B (2015) Beyond gaussian pyramid: Multi-skip feature stacking for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 204\u2013212"},{"key":"10795_CR25","doi-asserted-by":"crossref","unstructured":"Li Y, Li W, Mahadevan V, Vasconcelos N (2016) Vlad3: Encoding dynamics of deep features for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1951\u20131960","DOI":"10.1109\/CVPR.2016.215"},{"issue":"5","key":"10795_CR26","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2010","unstructured":"Liu C, Yuen J, Torralba A (2010) Sift flow: Dense correspondence across scenes and its applications. IEEE Trans Pattern Anal Mach Intell 33(5):978\u2013994","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10795_CR27","doi-asserted-by":"crossref","unstructured":"Liu J, Kuipers B, Savarese S (2011) Recognizing human actions by attributes. In: CVPR 2011. IEEE, pp 3337\u20133344","DOI":"10.1109\/CVPR.2011.5995353"},{"issue":"6","key":"10795_CR28","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1109\/LSP.2018.2823910","volume":"25","author":"Y Liu","year":"2018","unstructured":"Liu Y, Lu Z, Li J, Yang T, Yao C (2018) Global temporal representation based cnns for infrared action recognition. IEEE Signal Process Lett 25 (6):848\u2013852","journal-title":"IEEE Signal Process Lett"},{"key":"10795_CR29","unstructured":"Lucas BD, Kanade T et al (1981) An iterative image registration technique with an application to stereo vision"},{"key":"10795_CR30","unstructured":"Negin F, Bremond F (2016) Human action recognition in videos: A survey. In: INRIA Technical report"},{"issue":"3","key":"10795_CR31","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TCSVT.2018.2808685","volume":"29","author":"Y Peng","year":"2018","unstructured":"Peng Y, Zhao Y, Zhang J (2018) Two-stream collaborative learning with spatial-temporal attention for video classification. IEEE Trans Circ Syst Video Technol 29(3):773\u2013786","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"10795_CR32","doi-asserted-by":"crossref","unstructured":"Pienaar SW, Malekian R (2019) Human activity recognition using lstm-rnn deep neural network architecture. In: arXiv:1905.00599","DOI":"10.1109\/AFRICA.2019.8843403"},{"key":"10795_CR33","doi-asserted-by":"crossref","unstructured":"Richter J, Wiede C, Dayangac E, Shahenshah A, Hirtz G (2016) Activity recognition for elderly care by evaluating proximity to objects and human skeleton data. In: International conference on pattern recognition applications and methods. Springer, pp 139\u2013155","DOI":"10.1007\/978-3-319-53375-9_8"},{"key":"10795_CR34","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: A local svm approach. In: Pattern recognition, vol 3","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"10795_CR35","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems, pp 568\u2013576"},{"key":"10795_CR36","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"10795_CR37","doi-asserted-by":"crossref","unstructured":"Sun L, Jia K, Yeung DY, Shi BE (2015) Human action recognition using factorized spatio-temporal convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 4597\u20134605","DOI":"10.1109\/ICCV.2015.522"},{"key":"10795_CR38","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. In: Proceedings of the IEEE international conference on computer vision, pp 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"10795_CR39","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patrec.2017.04.004","volume":"92","author":"L Wang","year":"2017","unstructured":"Wang L, Ge L, Li R, Fang Y (2017) Three-stream cnns for action recognition. Pattern Recogn Lett 92:33\u201340","journal-title":"Pattern Recogn Lett"},{"key":"10795_CR40","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2013) Motionlets: Mid-level 3d parts for human motion recognition. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 2674\u20132681","DOI":"10.1109\/CVPR.2013.345"},{"key":"10795_CR41","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2015) Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"issue":"3","key":"10795_CR42","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1109\/TMM.2017.2749159","volume":"20","author":"X Wang","year":"2017","unstructured":"Wang X, Gao L, Wang P, Sun X, Liu X (2017) Two-stream 3-d convnet fusion for action recognition in videos with arbitrary size and length. IEEE Trans Multimed 20(3):634\u2013644","journal-title":"IEEE Trans Multimed"},{"key":"10795_CR43","doi-asserted-by":"crossref","unstructured":"Wei H, Xiao Y, Li R, Liu X (2018) Crowd abnormal detection using two-stream fully convolutional neural networks. In: 2018 10th international conference on measuring technology and mechatronics automation (ICMTMA). IEEE, pp 332\u2013336","DOI":"10.1109\/ICMTMA.2018.00087"},{"key":"10795_CR44","doi-asserted-by":"crossref","unstructured":"Wu Z, Jiang YG, Wang X, Ye H, Xue X (2016) Multi-stream multi-class fusion of deep networks for video classification. In: Proceedings of the 24th ACM international conference on Multimedia. ACM, pp 791\u2013800","DOI":"10.1145\/2964284.2964328"},{"key":"10795_CR45","doi-asserted-by":"crossref","unstructured":"Wu Z, Wang X, Jiang YG, Ye H, Xue X (2015) Modeling spatial-temporal clues in a hybrid deep learning framework for video classification. In: Proceedings of the 23rd ACM international conference on Multimedia. ACM, pp 461\u2013470","DOI":"10.1145\/2733373.2806222"},{"issue":"8","key":"10795_CR46","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1049\/iet-cvi.2017.0005","volume":"11","author":"S Yu","year":"2017","unstructured":"Yu S, Cheng Y, Xie L, Li SZ (2017) Fully convolutional networks for action recognition. IET Comput Vis 11(8):744\u2013749","journal-title":"IET Comput Vis"},{"key":"10795_CR47","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: Deep networks for video classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4694\u20134702","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"10795_CR48","doi-asserted-by":"crossref","unstructured":"Zhang B, Wang L, Wang Z, Qiao Y, Wang H (2016) Real-time action recognition with enhanced motion vector cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2718\u20132726","DOI":"10.1109\/CVPR.2016.297"},{"issue":"8","key":"10795_CR49","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1109\/TCSVT.2017.2682196","volume":"28","author":"S Zhao","year":"2017","unstructured":"Zhao S, Liu Y, Han Y, Hong R, Hu Q, Tian Q (2017) Pooling the convolutional layers in deep convnets for video action recognition. IEEE Trans Circ Syst Video Technol 28(8):1839\u20131849","journal-title":"IEEE Trans Circ Syst Video Technol"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10795-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-10795-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10795-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,30]],"date-time":"2021-11-30T17:36:50Z","timestamp":1638293810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-10795-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,10]]},"references-count":49,"journal-issue":{"issue":"28-29","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["10795"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10795-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,10]]},"assertion":[{"value":"3 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}