模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2019, Vol. 32 Issue (10): 892-900    DOI: 10.16451/j.cnki.issn1003-6059.201910003
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Temporal Group Deep Network Action Recognition Algorithm Based on Attention Mechanism
HU Zhengping1,2, DIAO Pengcheng1, ZHANG Ruixue1, LI Shufang1, ZHAO Mengyao1
1.School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004;
2.Hebei Key Laboratory of Information Transmission and Signal Processing, Yanshan University, Qinhuangdao 066004

Download: PDF (1180 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Inspired by the mechanism of human visual perception, a temporal group deep network action recognition algorithm based on attention mechanism is proposed under the framework of deep learning. Aiming at the deficiency of local temporal information in describing complex actions with a long duration, the video packet sparse sampling strategy is employed to conduct video level time modeling at a lower cost. In the recognition stage, channel attention mapping is introduced to further utilize global feature information and capture classified interest points, and channel feature recalibration is performed to improve the expression ability of the network. Experimental results on UCF101 and HMDB51 datasets show that the recognition accuracy of the proposed algorithm is high.
Key wordsAction Recognition      Deep Learning      Convolutional Neural Network      Attention     
Received: 17 June 2018     
ZTFLH: TP 391.4  
Fund:Supported by General Program of National Natural Science Foundation of China(No.61771420), Natural Science Foundation of Hebei Province(No.F2016203422)
Corresponding Authors: HU Zhengping(, Ph.D., professor. His research interests include pattern recognition.   
About author:: DIAO Pengcheng, master student. His research interests include action recognition;ZHANG Ruixue, master student. Her research interests include video classification;LI Shufang, Ph.D. candidate. Her resear-ch interests include pattern recognition;ZHAO Mengyao, Ph.D. candidate. Her research interests include video anomaly detection.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
HU Zhengping
DIAO Pengcheng
ZHANG Ruixue
LI Shufang
ZHAO Mengyao
Cite this article:   
HU Zhengping,DIAO Pengcheng,ZHANG Ruixue等. Temporal Group Deep Network Action Recognition Algorithm Based on Attention Mechanism[J]. , 2019, 32(10): 892-900.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201910003      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I10/892
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn