Human Action Recognition Using Spatio-Temporal Multiplier Network and Attentive Correlated Temporal Feature

2021 ◽  
Author(s):  
C. Indhumathi ◽  
V. Murugan ◽  
G. Muthulakshmii
Keyword(s):  
Action Recognition ◽  
State Of The Art ◽  
Human Action Recognition ◽  
Human Action ◽  
Regional Correlation ◽  
Temporal Features ◽  
Adaptive Motion ◽  
Spatio Temporal ◽  
Inter Frame ◽  
Temporal Feature

Nowadays, action recognition has gained more attention from the computer vision community. Normally for recognizing human actions, spatial and temporal features are extracted. Two-stream convolutional neural network is used commonly for human action recognition in videos. In this paper, Adaptive motion Attentive Correlated Temporal Feature (ACTF) is used for temporal feature extractor. The temporal average pooling in inter-frame is used for extracting the inter-frame regional correlation feature and mean feature. This proposed method has better accuracy of 96.9% for UCF101 and 74.6% for HMDB51 datasets, respectively, which are higher than the other state-of-the-art methods.

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

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 17913-17922 ◽  
Author(s):  
Lei Wang ◽  
Yangyang Xu ◽  
Jun Cheng ◽  
Haiying Xia ◽  
Jianqin Yin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Action Recognition ◽  
Deep Neural Networks ◽  
Human Action Recognition ◽  
Human Action ◽  
Temporal Features ◽  
Spatio Temporal

scholarly journals Mutually Reinforced Spatio-Temporal Convolutional Tube for Human Action Recognition

2019 ◽  
Author(s):  
Haoze Wu ◽  
Jiawei Liu ◽  
Zheng-Jun Zha ◽  
Zhenzhong Chen ◽  
Xiaoyan Sun
Keyword(s):  
Action Recognition ◽  
Computational Cost ◽  
Human Action Recognition ◽  
Human Action ◽  
Temporal Information ◽  
Temporal Features ◽  
Temporal Decomposition ◽  
Spatio Temporal ◽  
Different Order ◽  
High Computational Cost

Recent works use 3D convolutional neural networks to explore spatio-temporal information for human action recognition. However, they either ignore the correlation between spatial and temporal features or suffer from high computational cost by spatio-temporal features extraction. In this work, we propose a novel and efficient Mutually Reinforced Spatio-Temporal Convolutional Tube (MRST) for human action recognition. It decomposes 3D inputs into spatial and temporal representations, mutually enhances both of them by exploiting the interaction of spatial and temporal information and selectively emphasizes informative spatial appearance and temporal motion, meanwhile reducing the complexity of structure. Moreover, we design three types of MRSTs according to the different order of spatial and temporal information enhancement, each of which contains a spatio-temporal decomposition unit, a mutually reinforced unit and a spatio-temporal fusion unit. An end-to-end deep network, MRST-Net, is also proposed based on the MRSTs to better explore spatio-temporal information in human actions. Extensive experiments show MRST-Net yields the best performance, compared to state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document