{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:09:34Z","timestamp":1765303774286,"version":"3.41.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T00:00:00Z","timestamp":1532563200000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1007\/s00138-018-0961-8","type":"journal-article","created":{"date-parts":[[2018,7,26]],"date-time":"2018-07-26T13:41:21Z","timestamp":1532612481000},"page":"1157-1170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Joint representation learning of appearance and motion for abnormal event detection"],"prefix":"10.1007","volume":"29","author":[{"given":"Jongmin","family":"Yu","sequence":"first","affiliation":[]},{"given":"Kin Choong","family":"Yow","sequence":"additional","affiliation":[]},{"given":"Moongu","family":"Jeon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,7,26]]},"reference":[{"issue":"3","key":"961_CR1","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1109\/TPAMI.2007.70825","volume":"30","author":"A Adam","year":"2008","unstructured":"Adam, A., Rivlin, E., Shimshoni, I., Reinitz, D.: Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans. Pattern Anal. Mach. Intell. 30(3), 555\u2013560 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Basharat, A., Gritai, A., Shah, M.: Learning object motion patterns for anomaly detection and improved object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008, IEEE, pp. 1\u20138 (2008)","key":"961_CR2"},{"doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 4724\u20134733 (2017)","key":"961_CR3","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"crossref","unstructured":"Chong, Y.S., Tay, Y.H.: Abnormal event detection in videos using spatiotemporal autoencoder. In: International Symposium on Neural Networks, Springer, pp. 189\u2013196 (2017)","key":"961_CR4","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"961_CR5","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1016\/j.patcog.2012.11.021","volume":"46","author":"Y Cong","year":"2013","unstructured":"Cong, Y., Yuan, J., Liu, J.: Abnormal event detection in crowded scenes using sparse representation. Pattern Recogn. 46, 1851\u20131864 (2013)","journal-title":"Pattern Recogn."},{"unstructured":"Cui, X., Liu, Q., Gao, M., Metaxas, D.N.: Abnormal detection using interaction energy potentials. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, IEEE, pp. 3161\u20133167 (2011)","key":"961_CR6"},{"doi-asserted-by":"crossref","unstructured":"Dahl, G.E., Sainath, T.N., Hinton, G.E.: Improving deep neural networks for LVCSR using rectified linear units and dropout. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 8609\u20138613 (2013)","key":"961_CR7","DOI":"10.1109\/ICASSP.2013.6639346"},{"doi-asserted-by":"crossref","unstructured":"Du, D., Qi, H., Huang, Q., Zeng, W., Zhang, C.: Abnormal event detection in crowded scenes based on structural multi-scale motion interrelated patterns. In: 2013 IEEE International Conference on Multimedia and Expo (ICME), IEEE, pp. 1\u20136 (2013)","key":"961_CR8","DOI":"10.1109\/ICME.2013.6607499"},{"doi-asserted-by":"crossref","unstructured":"Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132154 (2014)","key":"961_CR9","DOI":"10.1109\/CVPR.2014.276"},{"doi-asserted-by":"crossref","unstructured":"Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A.K., Davis, L.S.: Learning temporal regularity in video sequences. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 733\u2013742 (2016)","key":"961_CR10","DOI":"10.1109\/CVPR.2016.86"},{"doi-asserted-by":"crossref","unstructured":"Jain, M., Jegou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 2555\u20132562 (2013)","key":"961_CR11","DOI":"10.1109\/CVPR.2013.330"},{"doi-asserted-by":"crossref","unstructured":"Javed, O., Shah, M.: Tracking and object classification for automated surveillance. In: European Conference on Computer Vision, Springer, pp. 343\u2013357 (2002)","key":"961_CR12","DOI":"10.1007\/3-540-47979-1_23"},{"issue":"1","key":"961_CR13","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 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."},{"issue":"11","key":"961_CR14","doi-asserted-by":"publisher","first-page":"3781","DOI":"10.1109\/TIP.2015.2456412","volume":"24","author":"YG Jiang","year":"2015","unstructured":"Jiang, Y.G., Dai, Q., Liu, W., Xue, X., Ngo, C.W.: Human action recognition in unconstrained videos by explicit motion modeling. IEEE Trans. Image Process. 24(11), 3781\u20133795 (2015)","journal-title":"IEEE Trans. Image Process."},{"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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","key":"961_CR15","DOI":"10.1109\/CVPR.2014.223"},{"unstructured":"Kim, J., Grauman, K.: Observe locally, infer globally: a space-time mrf for detecting abnormal activities with incremental updates. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009 (CVPR 2009), IEEE, pp. 2921\u20132928 (2009)","key":"961_CR16"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"961_CR17"},{"doi-asserted-by":"crossref","unstructured":"Klaser, A., Marsza\u0142ek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: BMVC 2008\u201419th British Machine Vision Conference, British Machine Vision Association, pp. 275-1 (2008)","key":"961_CR18","DOI":"10.5244\/C.22.99"},{"unstructured":"Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009 (CVPR 2009), IEEE, pp. 1446\u20131453 (2009)","key":"961_CR19"},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, pp. 1097\u20131105. Curran Associates, Inc. (2012)","key":"961_CR20"},{"key":"961_CR21","first-page":"396","volume-title":"Advances in Neural Information Processing Systems","author":"Y LeCun","year":"1990","unstructured":"LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, pp. 396\u2013404. MIT Press, Cambridge (1990)"},{"doi-asserted-by":"crossref","unstructured":"Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in matlab. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2720\u20132727 (2013)","key":"961_CR22","DOI":"10.1109\/ICCV.2013.338"},{"unstructured":"Mahadevan, V., Li, W., Bhalodia, V., Vasconcelos, N.: Anomaly detection in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp 1975\u20131981","key":"961_CR23"},{"doi-asserted-by":"crossref","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: International Conference on Artificial Neural Networks, Springer, pp. 52\u201359 (2011)","key":"961_CR24","DOI":"10.1007\/978-3-642-21735-7_7"},{"doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.: Voxnet: A 3D convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 922\u2013928 (2015)","key":"961_CR25","DOI":"10.1109\/IROS.2015.7353481"},{"unstructured":"Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009 (CVPR 2009), IEEE, pp. 935\u2013942 (2009)","key":"961_CR26"},{"doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., Kim, K., Tyree, S., Kautz, J.: Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4207\u20134215 (2016)","key":"961_CR27","DOI":"10.1109\/CVPR.2016.456"},{"doi-asserted-by":"crossref","unstructured":"Mousavi, H., Mohammadi, S., Perina, A., Chellali, R., Murino, V.: Analyzing tracklets for the detection of abnormal crowd behavior. In: 2015 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, pp. 148\u2013155 (2015)","key":"961_CR28","DOI":"10.1109\/WACV.2015.27"},{"doi-asserted-by":"crossref","unstructured":"Sabokrou, M., Fathy, M., Hoseini, M., Klette, R.: Real-time anomaly detection and localization in crowded scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 56\u201362 (2015)","key":"961_CR29","DOI":"10.1109\/CVPRW.2015.7301284"},{"key":"961_CR30","first-page":"568","volume-title":"Advances in Neural Information Processing Systems","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems, pp. 568\u2013576. MIT Press, Cambridge (2014a)"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014b)","key":"961_CR31"},{"doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), IEEE, pp. 4489\u20134497 (2015)","key":"961_CR32","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: 2013 IEEE International Conference on Computer Vision (ICCV), IEEE, pp. 3551\u20133558 (2013)","key":"961_CR33","DOI":"10.1109\/ICCV.2013.441"},{"doi-asserted-by":"crossref","unstructured":"Wang, X., Tieu, K., Grimson, E.: Learning semantic scene models by trajectory analysis. In: European Conference on Computer Vision, Springer, pp. 110\u2013123 (2006)","key":"961_CR34","DOI":"10.1007\/11744078_9"},{"unstructured":"Wang, X., Ma, X., Grimson, E.: Unsupervised activity perception by hierarchical bayesian models. In: IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR\u201907, IEEE, pp. 1\u20138 (2007)","key":"961_CR35"},{"issue":"3","key":"961_CR36","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TPAMI.2008.87","volume":"31","author":"X Wang","year":"2009","unstructured":"Wang, X., Ma, X., Grimson, W.E.L.: Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models. IEEE Trans. Pattern Anal. Mach. Intell. 31(3), 539\u2013555 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"961_CR37","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.cviu.2007.06.004","volume":"111","author":"T Xiang","year":"2008","unstructured":"Xiang, T., Gong, S.: Incremental and adaptive abnormal behaviour detection. Comput. Vis. Image Underst. 111(1), 59\u201373 (2008)","journal-title":"Comput. Vis. Image Underst."},{"doi-asserted-by":"crossref","unstructured":"Xu, D., Ricci, E., Yan, Y., Song, J., Sebe, N.: Learning deep representations of appearance and motion for anomalous event detection. arXiv preprint arXiv:1510.01553 (2015)","key":"961_CR38","DOI":"10.5244\/C.29.8"},{"unstructured":"Y\u00a0Cong, Y., Yuan, J., Liu, J.: Sparse reconstruction cost for abnormal event detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, IEEE, pp. 3449\u20133456 (2011)","key":"961_CR39"},{"unstructured":"Zhang, Y., Qin, L., Yao, H., Huang, Q.: Abnormal crowd behavior detection based on social attribute-aware force model. In: 19th IEEE International Conference on Image Processing (ICIP), 2012, IEEE, pp. 2689\u20132692 (2012)","key":"961_CR40"},{"unstructured":"Zhao, B., Fei-Fei, L., Xing, E.P.: Online detection of unusual events in videos via dynamic sparse coding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, IEEE, pp. 3313\u20133320 (2011)","key":"961_CR41"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-018-0961-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-018-0961-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-018-0961-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T01:49:57Z","timestamp":1751766597000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-018-0961-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,26]]},"references-count":41,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["961"],"URL":"https:\/\/doi.org\/10.1007\/s00138-018-0961-8","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2018,7,26]]},"assertion":[{"value":"16 August 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}