Overview of behavior recognition based on deep learning

被引：54
作者：
Hu, Kai [1 ,2 ]
Jin, Junlan [1 ,2 ]
Zheng, Fei [2 ,3 ]
Weng, Liguo [1 ,2 ]
Ding, Yiwu [1 ,2 ]
机构：
[1] Nanjing Univ Informat Sci & Technol, Sch Automat, 219 Ningliu Rd, Nanjing 210044, Jiangsu, Peoples R China
[2] Nanjing Univ Informat Sci & Technol, Jiangsu Collaborat Innovat Ctr Atmospher Environm, 219 Ningliu Rd, Nanjing 210044, Jiangsu, Peoples R China
[3] Innovat Dept Ind Internet, China Telecom Ningbo Branch, 96 HeYi Rd, Ningbo 315000, Zhejiang, Peoples R China
来源：
ARTIFICIAL INTELLIGENCE REVIEW | 2023年 / 56卷 / 03期
基金：
中国国家自然科学基金;
关键词：
Behavior recognition; Deep learning; Skeleton data; NETWORK; LSTM;
D O I：
10.1007/s10462-022-10210-8
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Human behavior recognition has always been a hot spot for research in computer vision. With the wide application of behavior recognition in virtual reality and short video in recent years and the rapid development of deep learning algorithms, behavior recognition algorithms based on deep learning have emerged. Compared with traditional methods, behavior recognition algorithms based on deep learning have the advantages of strong robustness and high accuracy. This paper systemizes and introduces behavior recognition algorithms based on deep learning proposed in recent years, then focuses on a series of behavior recognition algorithms based on image and bone data; deeply analyzes their theories and performance, and finally, puts forward further prospects.
引用
收藏
页码：1833 / 1865
页数：33
相关论文
共 76 条
[11]  
Du Y, 2015, PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, P579, DOI 10.1109/ACPR.2015.7486569
[12]   Spatio-Temporal VLAD Encoding for Human Action Recognition in Videos [J].
Duta, Ionut C. ;
Ionescu, Bogdan ;
Aizawa, Kiyoharu ;
Sebe, Nicu .
MULTIMEDIA MODELING (MMM 2017), PT I, 2017, 10132 :365-378
[13]   SlowFast Networks for Video Recognition [J].
Feichtenhofer, Christoph ;
Fan, Haoqi ;
Malik, Jitendra ;
He, Kaiming .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :6201-6210
[14]  
Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
[15]   DB-LSTM: Densely-connected Bi-directional LSTM for human action recognition [J].
He, Jun-Yan ;
Wu, Xiao ;
Cheng, Zhi-Qi ;
Yuan, Zhaoquan ;
Jiang, Yu-Gang .
NEUROCOMPUTING, 2021, 444 :319-331
[16]   Identity Mappings in Deep Residual Networks [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 :630-645
[17]  
HE KM, 2016, PROC CVPR IEEE, P770, DOI [DOI 10.1109/CVPR.2016.90, 10.1109/CVPR.2016.90]
[18]  
Huang J, 2016, CHINESE WORD SEGMENT
[19]   A DNA image encryption based on a new hyperchaotic system [J].
Hui, Yuanyuan ;
Liu, Han ;
Fang, Pengfei .
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (14) :21983-22007
[20]   SLOW-FAST AUDITORY STREAMS FOR AUDIO RECOGNITION [J].
Kazakos, Evangelos ;
Nagrani, Arsha ;
Zisserman, Andrew ;
Damen, Dima .
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, :855-859
12345678