CASIA OpenIR  > 智能感知与计算研究中心
Skeleton Based Action Recognition with Convolutional Neural Network
Du, Yong1,3; Fu, Yun4; Wang, Liang1,2,3
Conference NameAsian Conference on Pattern Recognition
Source PublicationAsian Conference on Pattern Recognition
Conference Date2015-11
Conference PlaceKuala Lumpur, Malaysia
AbstractTemporal dynamics of postures over time is crucial for sequence-based action recognition. Human actions can be represented by the corresponding motions of articulated skeleton. Most of the existing approaches for skeleton based action recognition model the spatial-temporal evolution of actions based on hand-crafted features. As a kind of hierarchically adaptive filter banks, Convolutional Neural Network (CNN) performs well in representation learning. In this paper, we propose an end-to-end hierarchical architecture for skeleton based action recognition with CNN. Firstly, we represent a skeleton sequence as a matrix by concatenating the joint coordinates in each instant and arranging those vector representations in a chronological order. Then the matrix is quantified into an image and normalized to handle the variable-length problem. The final image is fed into a CNN model for feature extraction and recognition. For the specific structure of such images, the simple max-pooling plays an important role on spatial feature selection as well as temporal frequency adjustment, which can obtain more discriminative joint information for different actions and meanwhile address the variable-frequency problem. Experimental results demonstrate that our method achieves the state-of-art performance with high computational efficiency, especially surpassing the existing result by more than 15 percentage on the challenging ChaLearn gesture recognition dataset.
KeywordSkeleton Based Action Recognition Convolutional Neural Network
Document Type会议论文
Corresponding AuthorWang, Liang
Affiliation1.Center for Research on Intelligent Perception and Computing, CRIPAC
2.Center for Excellence in Brain Science and Intelligence Technology, CEBSIT
3.Nat’l Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
4.College of Engineering, College of Computer and Information Science, Northeastern University, USA
Recommended Citation
GB/T 7714
Du, Yong,Fu, Yun,Wang, Liang. Skeleton Based Action Recognition with Convolutional Neural Network[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
ACPR.pdf(487KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Du, Yong]'s Articles
[Fu, Yun]'s Articles
[Wang, Liang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Du, Yong]'s Articles
[Fu, Yun]'s Articles
[Wang, Liang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Du, Yong]'s Articles
[Fu, Yun]'s Articles
[Wang, Liang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ACPR.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.