Title
Pose-based multisource networks using convolutional neural network and long short-term memory for action recognition.
Abstract
Pose-based action recognition has aroused increasing attention for its broad application prospects and excellent performance. Though the pose-based action recognition methods have been significantly advanced, pose-based action recognition remains a challenging task for various human action categories and subtle changes in human poses. To solve those problems, we propose pose-based multisource networks. First, human pose features are extracted from the raw video, followed by a filtration. Then, using a convolutional neural network (CNN) and long short-term memory (LSTM), the extracted pose sequence is fed into the proposed multisource networks. Subsequently, the CNN-based spatial model processes the relative position in each frame, and the LSTM-based temporal model is built to learn the temporal correlation of pose sequence. Afterward, the temporal model contains three sublevels to fully exploit the subtle information in the temporal domain. Finally, the experimental results verify the effectiveness of the proposed approach on SUBJHMDB, MPII Cooking Activities, SYSU 3D Human-Object Interaction, and NTU RGB+D. (C) 2019 SPIE and IS&T
Year
DOI
Venue
2019
10.1117/1.JEI.28.4.043018
JOURNAL OF ELECTRONIC IMAGING
Keywords
Field
DocType
action recognition,pose estimation,convolutional neural network,long short-term memory
Pattern recognition,Convolutional neural network,Computer science,Action recognition,Long short term memory,Speech recognition,Artificial intelligence
Journal
Volume
Issue
ISSN
28
4
1017-9909
Citations 
PageRank 
References 
0
0.34
0
Authors
6
Name
Order
Citations
PageRank
Fangqiang Hu102.70
Qianyu Wu241.44
Sai Zhang3186.41
Aichun Zhu4168.10
Zixuan Wang5912.65
Yaping Bao621.72