Research on 3D Convolutional Neural Network and Its Application to Video Understanding

被引:3
作者
Bai, Jing [1 ,2 ]
Yang, Zhanyuan [1 ]
Peng, Bin [1 ]
Li, Wenjing [1 ]
机构
[1] North Minzu Univ, Sch Comp Sci & Engn, Yinchuan 750021, Peoples R China
[2] Natl Ethn Affairs Commiss, Image Graph Intelligent Proc Lab, Yinahuan 750021, Peoples R China
基金
中国国家自然科学基金;
关键词
Video understanding; Deep learning; 3D Convolutional Neural Network (3D CNN); Network structure;
D O I
10.11999/JEIT220596
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
3D Convolutional Neural Network (3D CNN) has been a hot topic in deep learning research over the last few years and has made great achievements in computer vision. Despite years of research and abundant results, a comprehensive and detailed review of this content is still lacking. In this paper, the 3D convolutional neural network is introduced in the following aspects. Firstly, the rationale and model structure of 3D convolutional neural network are put forward. Then the improvement of 3D convolutional neural network is summarized from the network structure, network interior and optimization methods. After that the application of 3D convolutional neural network to the field of video understanding is explained. Finally, the contents summary of the paper and future development. This paper provides a systematic review of the latest research progress of 3D convolutional neural networks and their applications in the field of video understanding, which is of positive significance to the research and development of 3D convolutional neural network.
引用
收藏
页码:2273 / 2283
页数:11
相关论文
共 48 条
[1]  
ALZUBAIDI L, 2021, J BIG DATE, V8, P88, DOI [10.1186/40587-021-00444-8, DOI 10.1186/40587-021-00444-8]
[2]   Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset [J].
Carreira, Joao ;
Zisserman, Andrew .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :4724-4733
[3]  
[段艳廷 Duan Yanting], 2019, [地球物理学进展, Progress in Geophysiscs], V34, P2256
[4]  
[丰艳 Feng Yan], 2020, [电子学报, Acta Electronica Sinica], V48, P1269
[5]   Pulmonary Nodule Recognition Based on Three-Dimensional Convolution Neural Network [J].
Feng Yu ;
Yi Benshun ;
Wu Chenyue ;
Zhang Yungang .
ACTA OPTICA SINICA, 2019, 39 (06)
[6]   Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification [J].
Han, Yanling ;
Wei, Cong ;
Zhou, Ruyan ;
Hong, Zhonghua ;
Zhang, Yun ;
Yang, Shuhu .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020 (2020)
[7]   Contrastive Embedding for Generalized Zero-Shot Learning [J].
Han, Zongyan ;
Fu, Zhenyong ;
Chen, Shuo ;
Yang, Jian .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :2371-2381
[8]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[9]  
[胡正平 Hu Zhengping], 2020, [电子学报, Acta Electronica Sinica], V48, P1261
[10]   Densely Connected Convolutional Networks [J].
Huang, Gao ;
Liu, Zhuang ;
van der Maaten, Laurens ;
Weinberger, Kilian Q. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269