北京交通大学学报2017，Vol.41Issue(6)：8-12,5.DOI:10.11860/j.issn.1673-0291.2017.06.002
利用深度神经网络的无监督视频表示
Deep neural network based unsupervised video representation
摘要
Abstract
Most video representation methods are supervised in the field of computer vision,requi-ring large amounts of labeled training video sets which is expensive to scale up to rapidly growing data.To solve this problem,this paper proposes an unsupervised video representation method u-sing deep convolutional neural network.The improved dense trajectory (iDT )is utilized to extract the video blocks which alternately train the convolutional neural network and clusters. The deep convolutional neural network model is trained by iteratively algorithm to get the unsu-pervised video representations.The proposed model is applied to extract features in HMDB 51 and CCV datasets for tasks of motion recognition and event detection respectively.In the experi-ments,a 62.6％ mean accuracy and a 43.6％ mean average prevision (mAP)are obtained respec-tively which proves the effectiveness of the proposed method.关键词
无监督学习/卷积神经网络/视频表示Key words
unsupervised learning/convolution neural networks/video representation分类
信息技术与安全科学引用本文复制引用
吴心筱,伍堃..利用深度神经网络的无监督视频表示[J].北京交通大学学报,2017,41(6):8-12,5.基金项目
国家自然科学基金(61673062,61472038) Foundation items:Natimol Natural Science Foundation of China (61673062,61472038) （61673062,61472038）
