@article{ART002554051},
author={Kim, JeeHyun and Young Im Cho},
title={A New Residual Attention Network based on Attention Models for Human Action Recognition in Video},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2020},
volume={25},
number={1},
pages={55-61},
doi={10.9708/jksci.2020.25.01.055}
TY - JOUR
AU - Kim, JeeHyun
AU - Young Im Cho
TI - A New Residual Attention Network based on Attention Models for Human Action Recognition in Video
JO - Journal of The Korea Society of Computer and Information
PY - 2020
VL - 25
IS - 1
PB - The Korean Society Of Computer And Information
SP - 55
EP - 61
SN - 1598-849X
AB - With the development of deep learning technology and advances in computing power, video-based research is now gaining more and more attention. Video data contains a large amount of temporal and spatial information, which is the biggest difference compared with image data. It has a larger amount of data. It has attracted intense attention in computer vision. Among them, motion recognition is one of the research focuses. However, the action recognition of human in the video is extremely complex and challenging subject. Based on many research in human beings, we have found that artificial intelligence-like attention mechanisms are an efficient model for cognition. This efficient model is ideal for processing image information and complex continuous video information. We introduce this attention mechanism into video action recognition, paying attention to human actions in video and effectively improving recognition efficiency. In this paper, we propose a new 3D residual attention network using convolutional neural network based on two attention models to identify human action behavior in the video. An evaluation result of our model showed up to 90.7% accuracy.
KW - Deep Learning;Convolution Neural Network;Attention Mechanism;Video Processing;Action Recognition
DO - 10.9708/jksci.2020.25.01.055
ER -
Kim, JeeHyun and Young Im Cho. (2020). A New Residual Attention Network based on Attention Models for Human Action Recognition in Video. Journal of The Korea Society of Computer and Information, 25(1), 55-61.
Kim, JeeHyun and Young Im Cho. 2020, "A New Residual Attention Network based on Attention Models for Human Action Recognition in Video", Journal of The Korea Society of Computer and Information, vol.25, no.1 pp.55-61. Available from: doi:10.9708/jksci.2020.25.01.055
Kim, JeeHyun, Young Im Cho "A New Residual Attention Network based on Attention Models for Human Action Recognition in Video" Journal of The Korea Society of Computer and Information 25.1 pp.55-61 (2020) : 55.
Kim, JeeHyun, Young Im Cho. A New Residual Attention Network based on Attention Models for Human Action Recognition in Video. 2020; 25(1), 55-61. Available from: doi:10.9708/jksci.2020.25.01.055
Kim, JeeHyun and Young Im Cho. "A New Residual Attention Network based on Attention Models for Human Action Recognition in Video" Journal of The Korea Society of Computer and Information 25, no.1 (2020) : 55-61.doi: 10.9708/jksci.2020.25.01.055
Kim, JeeHyun; Young Im Cho. A New Residual Attention Network based on Attention Models for Human Action Recognition in Video. Journal of The Korea Society of Computer and Information, 25(1), 55-61. doi: 10.9708/jksci.2020.25.01.055
Kim, JeeHyun; Young Im Cho. A New Residual Attention Network based on Attention Models for Human Action Recognition in Video. Journal of The Korea Society of Computer and Information. 2020; 25(1) 55-61. doi: 10.9708/jksci.2020.25.01.055
Kim, JeeHyun, Young Im Cho. A New Residual Attention Network based on Attention Models for Human Action Recognition in Video. 2020; 25(1), 55-61. Available from: doi:10.9708/jksci.2020.25.01.055
Kim, JeeHyun and Young Im Cho. "A New Residual Attention Network based on Attention Models for Human Action Recognition in Video" Journal of The Korea Society of Computer and Information 25, no.1 (2020) : 55-61.doi: 10.9708/jksci.2020.25.01.055