Hierarchical recurrent neural network for skeleton based action recognition

CASIA OpenIR > 智能感知与计算研究中心

	Hierarchical recurrent neural network for skeleton based action recognition
	Du, Yong1,2 ; Wang, Wei1,2 ; Wang, Liang1,2
	2015-06
会议名称	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议录名称	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议日期	2015-6
会议地点	Boston, MA, USA
摘要	Human actions can be represented by the trajectories of skeleton joints. Traditional methods generally model the spatial structure and temporal dynamics of human skeleton with hand-crafted features and recognize human actions by well-designed classifiers. In this paper, considering that recurrent neural network (RNN) can model the long-term contextual information of temporal sequences well, we propose an end-to-end hierarchical RNN for skeleton based action recognition. Instead of taking the whole skeleton as the input, we divide the human skeleton into five parts according to human physical structure, and then separately feed them to five subnets. As the number of layers increases, the representations extracted by the subnets are hierarchically fused to be the inputs of higher layers. The final representations of the skeleton sequences are fed into a single-layer perceptron, and the temporally accumulated output of the perceptron is the final decision. We compare with five other deep RNN architectures derived from our model to verify the effectiveness of the proposed network, and also compare with several other methods on three publicly available datasets. Experimental results demonstrate that our model achieves the state-of-the-art performance with high computational efficiency.
关键词	Hierarchical Recurrent Neural Network Action Recognition Skeleton Lstm
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11093
专题	智能感知与计算研究中心
通讯作者	Wang, Liang
作者单位	1.Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition 2.Nat’l Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Du, Yong,Wang, Wei,Wang, Liang. Hierarchical recurrent neural network for skeleton based action recognition[C],2015.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
HRNN.pdf（393KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载