报告嘉宾:罗伟鑫(上海科技大学) 报告时间:2017年08月02日(星期三)下午15:00-16:00(北京时间) 报告题目:Deep Learning based Anomaly Detection 主持人:高盛华(上海科技大学) 报告摘要: Motivated by the capability of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC) where we enforce similar neighboring frames be encoded with similar econstruction coefficients. Then we map the TSC with a special type of stacked Recurrent Neural Network (sRNN). By taking advantage of sRNN in learning all parameters simultaneously, the nontrivial hyper-parameter selection to TSC can be avoided, meanwhile with a shallow sRNN, the reconstruction coefficients can be inferred within a forward pass, which re-duces the computational cost for learning sparse coefficients. The contributions of this paper are two-fold: i) We propose a TSC, which can be mapped to a sRNN which facilitates the parameter optimization and accelerates the anomaly prediction. ii) We build a very large dataset which is even larger than the summation of all existing dataset for anomaly detection in terms of both the volume of data and the diversity of scenes. Extensive experiments on both a toy dataset and real datasets demonstrate that our TSC based and sRNN based method consistently outperform existing methods, which validates the effectiveness of our method. 报告人简介: 罗伟鑫,上海科技大学信息学院在读二年级博士,指导老师为高盛华教授,研究方向为深度学习在视频理解中的应用等。相关工作发表于或投稿于AAAI, ICCV, TNNLS, ICME等会议或期刊。 特别鸣谢本次Webinar主要组织者: VOOC责任委员:高盛华(上海科技大学) VODB协调理事:董乐(电子科技大学) |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2024-11-22 17:16 , Processed in 0.012926 second(s), 15 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.