Skip to Content

3,429 Results Found

  • Article
  • Open Access
9 Citations
4,344 Views
16 Pages

15 September 2022

To improve the generation quality of image style transfer, this paper proposes a light progressive attention adaptive instance normalization (LPAdaIN) model that combines the adaptive instance normalization (AdaIN) layer and the convolutional block a...

(This article belongs to the Special Issue Machine Learning Applications to Signal Processing)
  • Article
  • Open Access
33 Citations
13,207 Views
19 Pages

17 February 2022

Wafer map inspection is essential for semiconductor manufacturing quality control and analysis. The deep convolutional neural network (DCNN) is the most effective algorithm in wafer defect pattern analysis. Traditional DCNNs rely heavily on high qual...

(This article belongs to the Topic Artificial Intelligence in Smart Industrial Diagnostics and Manufacturing)
  • Article
  • Open Access
2 Citations
2,911 Views
29 Pages

Structure-Preserving Histopathological Stain Normalization via Attention-Guided Residual Learning

  • Nuwan Madusanka,
  • Prathiksha Padmanabha,
  • Kasunika Guruge and
  • Byeong-il Lee

Staining variability in histopathological images compromises automated diagnostic systems by affecting the reliability of computational pathology algorithms. Existing normalization methods prioritize color consistency but often sacrifice critical mor...

(This article belongs to the Section Biosignal Processing)
  • Article
  • Open Access
14 Citations
3,179 Views
19 Pages

7 October 2022

Extracting water bodies is an important task in remote sensing imagery (RSI) interpretation. Deep convolution neural networks (DCNNs) show great potential in feature learning; they are widely used in the water body interpretation of RSI. However, the...

(This article belongs to the Special Issue Computer Vision and Machine Learning Application on Earth Observation)
  • Article
  • Open Access
666 Views
23 Pages

3 July 2026

Relative radiometric normalization (RRN) is fundamental to multi-temporal remote sensing analysis; however, conventional techniques often struggle with nonlinear distortions, outlier contamination, and heterogeneous land-cover conditions. To address...

  • Article
  • Open Access
3 Citations
3,792 Views
13 Pages

13 October 2020

We propose a novel end-to-end image colorization framework which integrates attention mechanism and a learnable adaptive normalization function. In contrast to previous colorization methods that directly generate the whole image, we believe that the...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
16 Citations
4,380 Views
17 Pages

14 February 2020

The primary purpose of the present study was to investigate attentional biases for food-related stimuli in individuals with overweight and normal weight using a flicker paradigm. Specifically, it was tested whether attention allocation processes diff...

  • Article
  • Open Access
3 Citations
2,368 Views
13 Pages

Attention-Based Batch Normalization for Binary Neural Networks

  • Shan Gu,
  • Guoyin Zhang,
  • Chengwei Jia and
  • Yanxia Wu

17 June 2025

Batch normalization (BN) is crucial for achieving state-of-the-art binary neural networks (BNNs). Unlike full-precision neural networks, BNNs restrict activations to discrete values {−1,1}, which requires a renewed understanding and research of...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
4 Citations
3,431 Views
18 Pages

19 April 2023

Fiber-reinforced composites (FRC) are widely used in various fields due to their excellent mechanical properties. The mechanical properties of FRC are significantly governed by the orientation of fibers in the composite. Automated visual inspection i...

(This article belongs to the Section D: Materials and Processing)
  • Article
  • Open Access
10 Citations
3,464 Views
12 Pages

27 October 2023

To address the challenges of detecting a large number of objects and a high proportion of small objects in aerial drone imagery, we proposed an aerial dense small object detection algorithm called Global Normalization Attention Mechanism You Only Loo...

  • Article
  • Open Access
4 Citations
3,236 Views
14 Pages

17 October 2020

One of the most important parts of a text-independent speaker verification system is speaker embedding generation. Previous studies demonstrated that shortcut connections-based multi-layer aggregation improves the representational power of a speaker...

(This article belongs to the Special Issue Human Computer Interaction for Intelligent Systems)
  • Article
  • Open Access
3 Citations
4,066 Views
27 Pages

28 December 2021

Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum D...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
23 Citations
4,819 Views
19 Pages

26 December 2022

In the contemporary world, emotion detection of humans is procuring huge scope in extensive dimensions such as bio-metric security, HCI (human–computer interaction), etc. Such emotions could be detected from various means, such as information i...

(This article belongs to the Special Issue Sensing Technologies for Image/Video Analysis)
  • Article
  • Open Access
46 Citations
8,703 Views
16 Pages

28 August 2022

Earthquakes threaten people, homes, and infrastructure. Early warning systems provide prior warning of oncoming significant shaking to decrease seismic risk by providing location, magnitude, and depth information of the event. Their usefulness depend...

(This article belongs to the Special Issue Automatic Detection of Seismic Signals)
  • Article
  • Open Access
5 Citations
4,335 Views
17 Pages

Objects in aerial images often have arbitrary orientations and variable shapes and sizes. As a result, accurate and robust object detection in aerial images is a challenging problem. In this paper, an arbitrary-oriented object detection method for ae...

(This article belongs to the Special Issue Image and Video Processing Based on Deep Learning)
  • Article
  • Open Access
12 Citations
2,993 Views
23 Pages

Currently, brain tumors are extremely harmful and prevalent. Deep learning technologies, including CNNs, UNet, and Transformer, have been applied in brain tumor segmentation for many years and have achieved some success. However, traditional CNNs and...

(This article belongs to the Special Issue Recent Advances in Artificial Intelligence-Based Medical Image Analysis)
  • Article
  • Open Access
4 Citations
1,128 Views
19 Pages

Background/Objectives: Glaucoma is a leading cause of irreversible blindness worldwide, making accurate and efficient detection methods essential. One primary concern with glaucoma is that it often presents no early symptoms. Vision loss typically be...

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
  • Article
  • Open Access
91 Views
36 Pages

6 November 2026

We investigate a theory-informed attention framework combining Cognitive Load Theory (CLT)-inspired resource regulation with Token–Context Attention (TCA) and a TCA-specific application of root-mean-square (RMS) branch normalization. Seven prim...

(This article belongs to the Special Issue AI, Machine Learning and Optimization)
  • Article
  • Open Access
10 Citations
4,946 Views
24 Pages

11 November 2023

In the prediction of time series, Empirical Mode Decomposition (EMD) generates subsequences and separates short-term tendencies from long-term ones. However, a single prediction model, including attention mechanism, has varying effects on each subseq...

  • Article
  • Open Access
4 Citations
3,611 Views
15 Pages

9 September 2020

Medical image segmentation based on deep learning is a central research issue in the field of computer vision. Many existing segmentation networks can achieve accurate segmentation using fewer data sets. However, they have disadvantages such as poor...

(This article belongs to the Section Applied Biosciences and Bioengineering)
  • Article
  • Open Access
44 Citations
11,009 Views
19 Pages

A New Road Damage Detection Baseline with Attention Learning

  • Hongwei Zhang,
  • Zhaohui Wu,
  • Yuxuan Qiu,
  • Xiangcheng Zhai and ,
  • Zichen Wang,
  • Peng Xu,
  • Zhenzheng Liu,
  • Xiantong Li and
  • Na Jiang
  • + 4 authors+ 0 author

28 July 2022

Automated detection of road damage (ADRD) is a challenging topic in road maintenance. It focuses on automatically detecting road damage and assessing severity by deep learning. Because of the sparse distribution of characteristic pixels, it is more c...

  • Article
  • Open Access
4 Citations
3,801 Views
15 Pages

Unsupervised Anomaly Detection via Normal Feature-Enhanced Reverse Teacher–Student Distillation

  • Xiaodong Wang,
  • Jiangtao Fan,
  • Fei Yan,
  • Hongmin Hu and ,
  • Zhiqiang Zeng,
  • Pengtao Wu,
  • Haiyan Huang and
  • Hangqi Zhang
  • + 3 authors+ 0 author

20 October 2024

In modern industrial production, unsupervised anomaly detection methods have gained significant attention due to their ability to address the challenge posed by the scarcity of labeled anomaly samples. Among them, unsupervised anomaly detection metho...

  • Article
  • Open Access
31 Citations
4,466 Views
17 Pages

Image Classification of Alzheimer’s Disease Based on External-Attention Mechanism and Fully Convolutional Network

  • Mingfeng Jiang,
  • Bin Yan,
  • Yang Li,
  • Jucheng Zhang and ,
  • Tieqiang Li and
  • Wei Ke
  • + 1 author+ 0 author

26 February 2022

Automatic and accurate classification of Alzheimer’s disease is a challenging and promising task. Fully Convolutional Network (FCN) can classify images at the pixel level. Adding an attention mechanism to the Fully Convolutional Network can eff...

(This article belongs to the Topic Age-Related Neurodegenerative Diseases and Stroke)
  • Article
  • Open Access
13 Citations
5,316 Views
16 Pages

Cycle Generative Adversarial Network Based on Gradient Normalization for Infrared Image Generation

  • Xing Yi,
  • Hao Pan,
  • Huaici Zhao,
  • Pengfei Liu and ,
  • Canyu Zhang,
  • Junpeng Wang and
  • Hao Wang
  • + 2 authors+ 0 author

3 January 2023

Image generation technology is currently one of the popular directions in computer vision research, especially regarding infrared imaging, bearing critical applications in the military field. Existing algorithms for generating infrared images from vi...

(This article belongs to the Special Issue Computer Vision and Pattern Recognition Based on Deep Learning)
  • Article
  • Open Access
4 Citations
3,613 Views
11 Pages

Nailfold Microhemorrhage Segmentation with Modified U-Shape Convolutional Neural Network

  • Ruiqi Liu,
  • Jing Tian,
  • Yuemei Li,
  • Na Chen and ,
  • Jianshe Yan,
  • Taihao Li and
  • Shupeng Liu
  • + 2 authors+ 0 author

18 May 2022

Nailfold capillaroscopy is a reliable way to detect and analyze microvascular abnormalities. It is safe, simple, noninvasive, and inexpensive. Among all the capillaroscopic abnormalities, nailfold microhemorrhages are closely associated with early va...

  • Article
  • Open Access
32 Citations
6,416 Views
20 Pages

Surface defects during steel production can severely impact product quality and safety, making defect detection crucial. To improve the precision and performance of conventional approaches, we introduce FMV-YOLO, a model for detecting steel surface d...

  • Article
  • Open Access
5 Citations
1,606 Views
19 Pages

BiLSTM-LN-SA: A Novel Integrated Model with Self-Attention for Multi-Sensor Fire Detection

  • Zhaofeng He,
  • Yu Si,
  • Liyuan Yang,
  • Nuo Xu and ,
  • Xinglong Zhang,
  • Mingming Wang and
  • Xiaoyun Sun
  • + 2 authors+ 0 author

18 October 2025

Multi-sensor fire detection technology has been widely adopted in practical applications; however, existing methods still suffer from high false alarm rates and inadequate adaptability in complex environments due to their limited capacity to capture...

(This article belongs to the Section Sensor Networks)
  • Article
  • Open Access
13 Citations
1,622 Views
24 Pages

HGCS-Det: A Deep Learning-Based Solution for Localizing and Recognizing Household Garbage in Complex Scenarios

  • Houkui Zhou,
  • Chang Chen,
  • Zhongyi Xia,
  • Qifeng Ding and ,
  • Qinqin Liao,
  • Qun Wang,
  • Huimin Yu,
  • Haoji Hu,
  • Guangqun Zhang and
  • Tao He
  • + 6 authors+ 1 author

14 June 2025

With the rise of deep learning technology, intelligent garbage detection provides a new idea for garbage classification management. However, due to the interference of complex environments, coupled with the influence of the irregular features of garb...

(This article belongs to the Special Issue Sensing and Imaging in Computer Vision)
  • Article
  • Open Access
2 Citations
3,532 Views
14 Pages

Enhanced Multi-Scale Attention-Driven 3D Human Reconstruction from Single Image

  • Yong Ren,
  • Mingquan Zhou,
  • Pengbo Zhou,
  • Shibo Wang and ,
  • Yangyang Liu,
  • Guohua Geng,
  • Kang Li and
  • Xin Cao
  • + 3 authors+ 0 author

30 October 2024

Due to the inherent limitations of a single viewpoint, reconstructing 3D human meshes from a single image has long been a challenging task. While deep learning networks enable us to approximate the shape of unseen sides, capturing the texture details...

(This article belongs to the Special Issue Human-Computer Interaction and Artificial Intelligence in VR/AR/MR Application)
  • Article
  • Open Access
146 Views
43 Pages

9 November 2026

Built-in attention is often presented as a free explanation of what a forecasting transformer relies on, but the claim is rarely tested. We test it on MeteoFormer, a patch-based transformer with single-head variable and temporal attention that foreca...

  • Article
  • Open Access
13 Citations
1,964 Views
28 Pages

27 November 2025

Multi-Unmanned Aerial Vehicle (Multi-UAV) cooperative search represents a cutting-edge research direction in the field of unmanned aerial vehicle applications. The use of multi-UAV systems for low-altitude target search and area surveillance has beco...

  • Article
  • Open Access
10 Citations
1,984 Views
25 Pages

This study proposes an improved YOLO11n-seg instance segmentation model to address the limitations of existing models in accurately identifying mature blueberries in complex greenhouse environments. Current methods often lack sufficient accuracy when...

(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
  • Article
  • Open Access
20 Citations
11,364 Views
15 Pages

19 November 2023

Anomalies are infrequent in nature, but detecting these anomalies could be crucial for the proper functioning of any system. The rarity of anomalies could be a challenge for their detection as detection models are required to depend on the relations...

(This article belongs to the Special Issue Application of Semantic Technologies in Sensors and Sensing Systems)
  • Article
  • Open Access
672 Views
32 Pages

Generative Dual-Modal Data Augmentation for Motor Fault Diagnosis Under Sample Imbalance

  • Ganxin Jie,
  • Cailiang Zhang,
  • Junqing Ma,
  • Yang Yang and
  • Chuan Chen

This study investigates class imbalance in motor fault diagnosis. Fault samples, especially those at different severity levels, are often much fewer than healthy samples. To address this issue, a self-attention guided Wasserstein conditional GAN with...

(This article belongs to the Special Issue Intelligent Fault Diagnosis and Control Optimization for Electric Machines)
  • Article
  • Open Access
148 Citations
10,675 Views
14 Pages

29 November 2019

In this paper, we present a new deep learning model to classify hematoxylin–eosin-stained breast biopsy images into four classes (normal tissues, benign lesions, in situ carcinomas, and invasive carcinomas). Our model uses a parallel structure...

(This article belongs to the Collection Application of Bioinformatics in Cancers)
  • Article
  • Open Access
7 Citations
2,803 Views
20 Pages

11 December 2022

Specific to the problem of infrared small-target detection in complex backgrounds, a multimechanism deep feature enhancement network model (MDFENet) was proposed. A lightweight multimechanism attention collaborative fusion module was proposed to effi...

  • Article
  • Open Access
2 Citations
2,551 Views
37 Pages

3 November 2025

The widespread use of leetspeak and dialectal Arabic on social media poses a critical challenge to automated hate speech detection systems. Existing Arabic NLP models, largely trained on Modern Standard Arabic (MSA), struggle with obfuscated, noisy,...

(This article belongs to the Special Issue Natural Language Processing: From Deep Learning to Real-World Solutions)
  • Article
  • Open Access
2 Citations
754 Views
23 Pages

Cross-speed bearing fault diagnosis faces a physical obstacle: bearing characteristic frequencies are proportional to shaft speed, so identical faults shift in the spectrum when source and target speeds differ, and source-trained feature mappings deg...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
582 Views
33 Pages

18 May 2026

Reliable perception of small floating objects is critical for the management of aquatic environments and supports key applications, including the autonomous navigation of Unmanned Surface Vehicles (USVs), waterborne debris monitoring, and Search and...

  • Article
  • Open Access
3 Citations
2,806 Views
20 Pages

12 December 2023

Spiking neural networks (SNNs) have garnered significant attention due to their computational patterns resembling biological neural networks. However, when it comes to deep SNNs, how to focus on critical information effectively and achieve a balanced...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
763 Views
31 Pages

Unsupervised Identification of Driving Styles from Naturalistic Driving Data Through a Context-Normalized Framework

  • Cunzhi Xu,
  • Reuben S.K. Agbozo,
  • Liang Huang,
  • Zheng Zhang and ,
  • Tao Peng and
  • Renzhong Tang
  • + 1 author+ 0 author

7 July 2026

Identifying driving styles is essential for personalizing driving assistance systems and enhancing intelligent transportation services. However, existing approaches predominantly rely on experience-driven feature engineering and annotated data, limit...

(This article belongs to the Special Issue Feature Papers in "Industrial Sensors" Section 2026–2027)
  • Technical Note
  • Open Access
25 Citations
5,256 Views
20 Pages

End-to-End Detail-Enhanced Dehazing Network for Remote Sensing Images

  • Weida Dong,
  • Chunyan Wang,
  • Hao Sun,
  • Yunjie Teng and ,
  • Huan Liu,
  • Yue Zhang,
  • Kailin Zhang,
  • Xiaoyan Li and
  • Xiping Xu
  • + 4 authors+ 0 author

6 January 2024

Space probes are always obstructed by floating objects in the atmosphere (clouds, haze, rain, etc.) during imaging, resulting in the loss of a significant amount of detailed information in remote sensing images and severely reducing the quality of th...

(This article belongs to the Special Issue Advanced Artificial Intelligence Algorithm for the Analysis of Remote Sensing Images II)
  • Article
  • Open Access
5 Citations
6,159 Views
25 Pages

Image Inpainting Algorithm Based on Structure-Guided Generative Adversarial Network

  • Li Zhao,
  • Tongyang Zhu,
  • Chuang Wang,
  • Feng Tian and
  • Hongge Yao

24 July 2025

To address the challenges of image inpainting in scenarios with extensive or irregular missing regions—particularly detail oversmoothing, structural ambiguity, and textural incoherence—this paper proposes an Image Structure-Guided (ISG) f...

  • Article
  • Open Access
72 Citations
6,692 Views
17 Pages

TE-SAGAN: An Improved Generative Adversarial Network for Remote Sensing Super-Resolution Images

  • Yongyang Xu,
  • Wei Luo,
  • Anna Hu,
  • Zhong Xie and ,
  • Xuejing Xie and
  • Liufeng Tao
  • + 1 author+ 0 author

18 May 2022

Resolution is a comprehensive reflection and evaluation index for the visual quality of remote sensing images. Super-resolution processing has been widely applied for extracting information from remote sensing images. Recently, deep learning methods...

  • Article
  • Open Access
2 Citations
2,397 Views
15 Pages

23 March 2023

At present, the non-intrusive load decomposition method for low-frequency sampling data is as yet insufficient within the context of generalization performance, failing to meet the decomposition accuracy requirements when applied to novel scenarios....

(This article belongs to the Topic Smart Electric Energy in Buildings)
  • Article
  • Open Access
17 Citations
4,641 Views
22 Pages

Infrared–Visible Image Fusion through Feature-Based Decomposition and Domain Normalization

  • Weiyi Chen,
  • Lingjuan Miao,
  • Yuhao Wang,
  • Zhiqiang Zhou and
  • Yajun Qiao

10 March 2024

Infrared–visible image fusion is valuable across various applications due to the complementary information that it provides. However, the current fusion methods face challenges in achieving high-quality fused images. This paper identifies a lim...

(This article belongs to the Special Issue Multi-Sensor Systems and Data Fusion in Remote Sensing II)
  • Article
  • Open Access
22 Citations
5,089 Views
13 Pages

STN-GCN: Spatial and Temporal Normalization Graph Convolutional Neural Networks for Traffic Flow Forecasting

  • Chunzhi Wang,
  • Lu Wang,
  • Siwei Wei,
  • Yun Sun and ,
  • Bowen Liu and
  • Lingyu Yan
  • + 1 author+ 0 author

In recent years, traffic forecasting has gradually become a core component of smart cities. Due to the complex spatial-temporal correlation of traffic data, traffic flow prediction is highly challenging. Existing studies are mainly focused on graphic...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
1,851 Views
20 Pages

IAE-KM3D a 3D Object Detection Method Based on an Improved KM3D Network

  • Yang Sun,
  • Song Li,
  • Haiyang Wang,
  • Bin Tian and
  • Yi Li

7 June 2024

Deep learning-based 3D target detection methods need to solve the problem of insufficient 3D target detection accuracy. In this paper, the KM3D network is selected as the benchmark network after the experimental comparison of current mainstream algor...

  • Article
  • Open Access
6 Citations
2,684 Views
22 Pages

NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm

  • Bingyi Li,
  • Andong Xiao,
  • Xing Hu,
  • Sisi Zhu and ,
  • Gang Wan,
  • Kunlun Qi and
  • Pengfei Shi
  • + 2 authors+ 0 author

Steel surface defect detection is a crucial step in ensuring industrial production quality. However, due to significant variations in scale and irregular geometric morphology of steel surface defects, existing detection algorithms show notable defici...

(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)
  • Article
  • Open Access
11 Citations
3,154 Views
22 Pages

10 October 2024

Forest fires pose a significant threat to forest resources and wildlife. To balance accuracy and parameter efficiency in forest fire detection, this study proposes an improved model, Mcan-YOLO, based on YOLOv7. In the Neck section, the asymptotic fea...

(This article belongs to the Special Issue Artificial Intelligence and Machine Learning Applications in Forestry)

of 69