{"type":"ScholarlyArticle","title":"Deep Abnormality Detection in Video Data","authors":[{"name":"Hung Vu","slug":"hung-vu","given":"Hung","family":"Vu","affiliation":"Centre for Pattern Recognition and Data Analytics (PRaDA) , Deakin University , Australia"}],"abstract":"Automated detection of anomalous events plays an important role in video surveillance systems in practice. This task, however, requires to deal with three challenging problems of the lack of annotated training data, the inexact description of what to be \"abnormal\" and the expensive feature engineering procedure. Most anomaly detection systems are only able to satisfy some of these challenges. In this work, we propose a deep abnormality detection system to handle all of them simultaneously. Deep abnormality detection is a deep generative network that is an unsupervised probabilistic framework to model the normality and learn feature representation automatically. Furthermore, unlike other existing methods, our system can detect abnormality at multiple levels and be used as a powerful tool for video analysis and scene understanding.","doi":"10.24963/ijcai.2017/768","url":"https://ijcai.org/proceedings/2017/768","pdf":"https://ijcai.org/proceedings/2017/0768.pdf","markdown":"https://ijcai.org/proceedings/2017/768.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/768","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":768,"pages":{"first":5217,"last":5218},"keywords":["Artificial Intelligence: machine learning","Artificial Intelligence: computer vision"],"videos":[],"references":[{"position":1,"raw":"[Freund and Haussler, 1994] Y. Freund and D. Haussler. Un- supervised learning of distributions on binary vectors us- ing two layer networks. Technical report, CA, USA, 1994.","title":"Unsupervised learning of distributions on binary vectors using two layer networks","authors":"Y Freund, D Haussler","year":"1994","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Hasan et al., 2016] M. Hasan, J. Choi, J. Neumann, AK. Roy-Chowdhury, and LS. Davis. Learning temporal regu- larity in video sequences. In CVPR, 2016.","title":"Learning temporal regularity in video sequences","authors":"M Hasan, J Choi, J Neumann, A K Roy-Chowdhury, L S Davis","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Nguyen et al., 2015] TD. Nguyen, T. Tran, D. Phung, and S. Venkatesh. Tensor-variate restricted boltzmann ma- chines. In AAAI, volume 4, pages 2887-2893, Austin Texas, USA, January 25-30 2015.","title":"Tensor-variate restricted boltzmann machines","authors":"Nguyen","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Salakhutdinov and Hinton, 2009] R. Salakhutdinov and G. Hinton. Deep Boltzmann machines. In AISTATS, volume 5, pages 448-455, 2009.","title":"Deep Boltzmann machines","authors":"R Salakhutdinov, G Hinton","year":"2009","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Sodemann et al., 2012] AA. Sodemann, MP. Ross, and BJ. Borghetti. A review of anomaly detection in automated surveillance. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42:1257- 1272, November 2012.","title":"A review of anomaly detection in automated surveillance","authors":"Sodemann","year":"2012","venue":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Xu et al., 2015] D. Xu, E. Ricci, Y. Yan, J. Song, and N. Sebe. Learning deep representations of appearance and motion for anomalous event detection. BMVC, 2015.","title":"Learning deep representations of appearance and motion for anomalous event detection","authors":"D Xu, E Ricci, Y Yan, J Song, N Sebe","year":"2015","venue":"BMVC","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}