相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Gianni Brauwers et al.
Summary: Attention is a vital mechanism in various domains and tasks of deep learning. This survey offers an overview of the important attention mechanisms proposed in literature. The mechanisms are explained using a framework comprising a general attention model, uniform notation, and a comprehensive taxonomy. Additionally, it reviews evaluation measures and methods to characterize the structure of attention models based on the framework. Future work in the field of attention models is also considered.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Shun Li et al.
Summary: This paper proposes TC-YOLOv5, an improved object detection algorithm that enhances detection accuracy by integrating convolutional block attention module and vision transformer. To ensure efficiency and low resource consumption, this algorithm selectively removes some convolutional layers and reduces redundant calculations. The performance of TC-YOLOv5 was evaluated on a dataset with multiple species of floating debris, achieving an average processing time of 1.18s per image on a Raspberry Pi 4B and a mean average precision (mAP@0.5) of 84.2%. TC-YOLOv5 outperforms other algorithms of the YOLOv5 series in terms of detection accuracy, speed, and floating-point operations (FLOPs).
JOURNAL OF REAL-TIME IMAGE PROCESSING
(2023)
Article
Automation & Control Systems
Chenglong Xiong et al.
Summary: This paper proposes an improved deep learning method based on YOLOV5 to address the low efficiency and high cost issues in manual plate defect detection. The improved method incorporates a new attention module, a simplified BottleneckCSP module, and an enhanced loss function, resulting in improved detection capability for small targets and overall detection performance.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Chemistry, Analytical
Chen Zhang et al.
Summary: This paper proposes an image recognition method of wind turbine blade defects using attention-based MobileNetv1-YOLOv4 and transfer learning. By replacing the backbone convolution neural network with the lightweight MobileNetv1 and introducing attention-based feature refinement modules, higher detection accuracy, faster response speed, and lower computational complexity are achieved.
Article
Multidisciplinary Sciences
Hong Li et al.
Summary: This paper presents an improved lightweight real-time convolutional neural network, Alpha-SGANet, based on YOLOv5. By adding prediction heads, designing a lightweight feature extraction network, reducing information loss, and employing GAFPN and CBAM modules, higher accuracy and real-time speed are achieved.
Article
Engineering, Electrical & Electronic
Linkai Liu et al.
Summary: In this study, a fast inference framework for object detection in large-scale remote sensing images is proposed. By introducing alpha-IoU loss and gradient, adaptive weighted loss and gradient are achieved, surpassing existing algorithms in terms of accuracy and speed. Moreover, a distributed inference framework is built to enable fast inference on large-scale remote sensing images and reduce dependence on expensive hardware resources.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Rafael Padilla et al.
Summary: This study provides an overview of evaluation methods used in object detection competitions, examines the influence of different annotation formats on evaluation results, and offers an open-source toolkit supporting various annotation formats and performance metrics for researchers to evaluate their detection algorithms. Furthermore, it introduces a new metric for evaluating object detection in videos based on spatio-temporal overlap.
Article
Multidisciplinary Sciences
Jianming Zhang et al.
Summary: In this paper, we propose a Siamese-based anchor-free object tracking algorithm with multiscale spatial attentions to capture spatial information effectively. Experimental results demonstrate the effectiveness of our proposed tracker on challenging tracking benchmarks.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Artificial Intelligence
Tsung-Yi Lin et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Asifullah Khan et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2020)
Article
Computer Science, Artificial Intelligence
Jie Hu et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Yong Li et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Theory & Methods
Connor Shorten et al.
JOURNAL OF BIG DATA
(2019)
Review
Mathematical & Computational Biology
Athanasios Voulodimos et al.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Juan Du
2ND INTERNATIONAL CONFERENCE ON MACHINE VISION AND INFORMATION TECHNOLOGY (CMVIT 2018)
(2018)
Proceedings Paper
Energy & Fuels
Tao Lin et al.
2018 IEEE INTERNATIONAL CONFERENCE ON HIGH VOLTAGE ENGINEERING AND APPLICATION (ICHVE)
(2018)
Article
Computer Science, Artificial Intelligence
Shaoqing Ren et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Engineering, Industrial
Daniel Weimer et al.
CIRP ANNALS-MANUFACTURING TECHNOLOGY
(2016)
Review
Automation & Control Systems
Ajay Kumar
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2008)
