欢迎访问广东工业大学数据挖掘与信息检索实验室!

上海科技大学高盛华博士学术讲座预告

作者:DMIR    来自:    发表时间:2018-01-08    浏览量:106


报告时间2018年01月10日(周三)1430

报告地点:广工大学城校园工学一号馆216室(学术报告厅)

报告题目:Anomaly detection in videos: from feature reconstruction to future prediction

报告人:上海科技大学 高盛华博士

报告人简介:  

    Shenghua Gao is an assistant professor in 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 about 50 papers on image and video understanding in many top-tier international conferences and journals, including TPAMI,IJCV, TIP, TNNLS, CVPR, ICCV, etc.

报告摘要:       

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 by 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 validate the effectiveness of such video frame prediction framework over feature reconstruction framework for anomaly detection.  

本次学术报告机会难得,欢迎感兴趣的师生前来参加。请提前10分钟入场入座完毕!