Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks.

	Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks.
	Wang, Lei; Xu, Yangyang; Cheng, Jun; Xia, Haiying; Yin, Jianqin; Wu, Jiaji
刊名	IEEE ACCESS
	2018
文献子类	期刊论文
英文摘要	Human action recognition is one of the fundamental challenges in robotics systems. In this paper, we propose one lightweight action recognitionarchitecture based on deep neural networks just using RGB data. The proposed architecture consists of convolution neural network (CNN), long short-term memory (LSTM) units, and temporal-wise attention model. First, the CNN is used to extract spatial features to distinguish objects from the background withboth local and semantic characteristics. Second, two kinds of LSTM networks are performed on the spatial feature maps of different CNN layers (pooling layer and fully-connected layer) to extract temporal motion features. Then, one temporal-wise attention model is designed after the LSTM to learn which parts in which frames are more important. Lastly, a joint optimization module is designed to explore intrinsic relations between two kinds of LSTM features. Experimental results demonstrate the efficiency of the proposed method.
URL标识	查看原文
语种	英语
内容类型	期刊论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/13568]
专题	深圳先进技术研究院_集成所
推荐引用方式 GB/T 7714	Wang, Lei,Xu, Yangyang,Cheng, Jun,et al. Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks.[J]. IEEE ACCESS,2018.
APA	Wang, Lei,Xu, Yangyang,Cheng, Jun,Xia, Haiying,Yin, Jianqin,&Wu, Jiaji.(2018).Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks..IEEE ACCESS.
MLA	Wang, Lei,et al."Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks.".IEEE ACCESS (2018).