模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2022, Vol. 35 Issue (6): 562-570    DOI: 10.16451/j.cnki.issn1003-6059.202206008
Deep Learning Based Object Detection and Recognition Current Issue| Next Issue| Archive| Adv Search |
Composite Deep Neural Network for Human Activities Recognition in Video
HUANG Min1, SHANG Ruixing1, QIAN Huimin1
1. College of Energy and Electrical Engineering, Hohai University, Nanjing 211100

Download: PDF (640 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Aiming at the deficiencies of 3D convolutional neural network and two-stream convolutional neural network for human activities recognition in video, a composite deep neural network combining two-stream convolutional network and 3D convolutional network is proposed. The improved residual(2+1)D convolutional neural network is utilized in both the temporal sub-network and the spatial sub-network of two-stream architecture. Behavioral representation and classification methods are learned from RGB and optical flow of video, respectively. The classification results of temporal stream and spatial stream sub-networks are combined. Furthermore, in the process of network training, stochastic gradient descent with the momentum improved by gradient centralization algorithm is proposed to improve the network generalization performance without varying the network structure. Experimental results show that the proposed network achieves higher accuracy on UCF101 and HMDB51.
Key wordsHuman Activity Recognition      Two-Stream Convolutional Network      3D Convolution Neural Network      Gradient Centralization     
Received: 08 March 2022     
ZTFLH: TP 391.41  
Corresponding Authors: QIAN Huimin, Ph.D., associate professor. Her research interests include computer vision and machine learning.   
About author:: HUANG Min, master student. Her research interests include human activity recognition.
SHANG Ruixing, master student. Her research interests include human activity recognition.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
HUANG Min
SHANG Ruixing
QIAN Huimin
Cite this article:   
HUANG Min,SHANG Ruixing,QIAN Huimin. Composite Deep Neural Network for Human Activities Recognition in Video[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(6): 562-570.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202206008      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2022/V35/I6/562
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