2022
DOI: 10.1109/tits.2021.3072872
|View full text |Cite
|
Sign up to set email alerts
|

Real-Time Tracking Algorithm for Aerial Vehicles Using Improved Convolutional Neural Network and Transfer Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(3 citation statements)
references
References 33 publications
0
2
0
Order By: Relevance
“…If a person makes a wrong decision, then he can reduce the next mistakes through continuous learning, and the neural network is a learning method that simulates people. When the network judges wrong, it can reduce the next mistakes through continuous learning [15][16][17]. To study the nonlinear dynamic properties of neural network, the dynamic system theory, nonlinear programming theory, and statistical theory are mainly used.…”
Section: Neural Network Structure and Fitness Functionmentioning
confidence: 99%
“…If a person makes a wrong decision, then he can reduce the next mistakes through continuous learning, and the neural network is a learning method that simulates people. When the network judges wrong, it can reduce the next mistakes through continuous learning [15][16][17]. To study the nonlinear dynamic properties of neural network, the dynamic system theory, nonlinear programming theory, and statistical theory are mainly used.…”
Section: Neural Network Structure and Fitness Functionmentioning
confidence: 99%
“…is sudden language change plays a subtle and irreplaceable role while shaping and shaping the characters [23,24]. Due to differences in thinking and culture, English and Chinese language expressions are sometimes untranslatable.…”
Section: Corpus Experiments On Code-switching In Novelsmentioning
confidence: 99%
“…This can be achieved by duplicating samples from rare classes, generating synthetic samples, or employing other methods. RCS helps improve the model's performance on imbalanced datasets, reducing classification errors for rare classes, and thus better adapting to real-world applications [14].…”
Section: Rare Class Samplingmentioning
confidence: 99%