Anomaly detection in videos is a challenging problem in computer vision because only normal events are available in training set. Most previous work handle the problem within a sparse representation framework: a dictionary is learnt to minimize the reconstruction error for normal events and abnormal events would lead to large reconstruction error. However such sparse representation is computationally expensive in the testing phase. Inspired the optimization of sparse representation, we propose to build a special type of deep neural network, which is a counterpart of sparse coding. Then we simplify the network which not only improves the speed but also accuracy. Further, it is worth noting that anomaly detection refers to the identification of events that do not conform to expected behavior, so we propose to solve anomaly detection within future video frame prediction framework. By simultaneously enforcing the spatial and temporal consistency of videos frames of normal videos, we can predict high quality video frames for normal videos. Extensive experiments validates the effectiveness of such video frame prediction framework over feature reconstruction framework for anomaly detection.

Shenghua Gao is a tenure-tracked assistant professor at ShanghaiTech University, China. He received the B.E. degree from the University of Science and Technology of China in 2008, and received the Ph.D. degree from the Nanyang Technological University in 2012. From Jun 2012 to Aug 2014, he worked as a research scientist in UIUC Advanced Digital Sciences Center in Prof Yi Ma's group, Singapore. From Jan 2015 to June 2015, he visited UC Berkeley as a visiting professor, hosted by Prof Jitendra Malik. His research interests include computer vision and machine learning. He has published more than 60 papers on image and video understanding in many top-tier international conferences and journals. He also served as a workshop chair in CVPR2017, ACCV2014, ACCV2016, CVPR2019 and area chair in ICCV2019. He also served as the Associate Editor for IEEE Transactions on Circuites and Systems for Video Technology (IF:3.558) and Neurocomputing (IF:3.224). His work on personalized saliency detection was nominated as outstanding student award (runner-up) in IJCAI 2017. He was awarded the Microsoft Research Fellowship in 2010, and ACM Shanghai Young Research Scientist in 2015, National 1000 Plan (Young Scholars) in 2016.