CASIA OpenIR  > 智能感知与计算研究中心
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks
Wang Hongsong(王洪松)1,2,3,4; Wang Liang(王亮)1,2,3,4; Liang Wang
2017
Conference NameIEEE Computer Vision and Pattern Recognition (CVPR)
Conference DateJuly 22 - July 25 2017
Conference PlaceHonolulu, Hawai
AbstractRecently, skeleton based action recognition gains more popularity due to cost-effective depth sensors coupled with real-time skeleton estimation algorithms. Traditional approaches based on handcrafted features are limited to represent the complexity of motion patterns. Recent methods that use Recurrent Neural Networks (RNN) to handle raw skeletons only focus on the contextual dependency in the temporal domain and neglect the spatial configurations of articulated skeletons. In this paper, we propose a novel two-stream RNN architecture to model both temporal dynamics and spatial configurations for skeleton based action recognition. We explore two different structures for the temporal stream: stacked RNN and hierarchical RNN. Hierarchical RNN is designed according to human body kinematics. We also propose two effective methods to model the spatial structure by converting the spatial graph into a sequence of joints. To improve generalization of our model, we further exploit 3D transformation based data augmentation techniques including rotation and scaling transformation to transform the 3D coordinates of skeletons during training. Experiments on 3D action recognition benchmark datasets show that our method brings a considerable improvement for a variety of actions, i.e., generic actions, interaction activities and gestures.
KeywordAction Recognition Temporal Dynamics Spatial Configurations
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19624
Collection智能感知与计算研究中心
Corresponding AuthorLiang Wang
Affiliation1.Center for Research on Intelligent Perception and Computing (CRIPAC)
2.National Laboratory of Pattern Recognition (NLPR)
3.Institute of Automation, Chinese Academy of Sciences (CASIA)
4.University of Chinese Academy of Sciences (UCAS)
Recommended Citation
GB/T 7714
Wang Hongsong,Wang Liang,Liang Wang. Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
Modeling Temporal Dy(934KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang Hongsong(王洪松)]'s Articles
[Wang Liang(王亮)]'s Articles
[Liang Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang Hongsong(王洪松)]'s Articles
[Wang Liang(王亮)]'s Articles
[Liang Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang Hongsong(王洪松)]'s Articles
[Wang Liang(王亮)]'s Articles
[Liang Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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