Skip to Content

34,426 Results Found

  • Article
  • Open Access
8 Citations
3,634 Views
19 Pages

Hyperspectral images (HSIs) are pivotal in various fields due to their rich spectral–spatial information. While convolutional neural networks (CNNs) have notably enhanced HSI classification, they often generate redundant spatial features. To ad...

(This article belongs to the Special Issue Innovative GIS Models and Approaches for Large Environmental and Urban Applications in the Age of AI)
  • Article
  • Open Access
26 Citations
7,532 Views
25 Pages

Convolutional Neural Network with Spatial-Variant Convolution Kernel

  • Yongpeng Dai,
  • Tian Jin,
  • Yongkun Song,
  • Shilong Sun and
  • Chen Wu

30 August 2020

Radar images suffer from the impact of sidelobes. Several sidelobe-suppressing methods including the convolutional neural network (CNN)-based one has been proposed. However, the point spread function (PSF) in the radar images is sometimes spatially v...

(This article belongs to the Special Issue Advanced Techniques for Ground Penetrating Radar Imaging)
  • Article
  • Open Access
6 Citations
2,342 Views
19 Pages

Number of Convolution Layers and Convolution Kernel Determination and Validation for Multilayer Convolutional Neural Network: Case Study in Breast Lesion Screening of Mammographic Images

  • Feng-Zhou Zhang,
  • Chia-Hung Lin,
  • Pi-Yun Chen,
  • Neng-Sheng Pai and ,
  • Chun-Min Su,
  • Ching-Chou Pai and
  • Hui-Wen Ho
  • + 2 authors+ 0 author

15 September 2022

Mammography is a low-dose X-ray imaging technique that can detect breast tumors, cysts, and calcifications, which can aid in detecting potential breast cancer in the early stage and reduce the mortality rate. This study employed a multilayer convolut...

(This article belongs to the Section Automation Control Systems)
  • Article
  • Open Access
2 Citations
1,978 Views
9 Pages

26 February 2022

Four different types of convolutions of aggregation functions (the upper, the lower, the super-, and the sub-convolution) are examined in the setting of both sub- and super-decomposition integrals defined on a finite space. Examples of the results of...

(This article belongs to the Special Issue Set-Valued Analysis II)
  • Article
  • Open Access
13 Citations
4,571 Views
13 Pages

Matrix Expression of Convolution and Its Generalized Continuous Form

  • Young Hee Geum,
  • Arjun Kumar Rathie and
  • Hwajoon Kim

29 October 2020

In this paper, we consider the matrix expression of convolution, and its generalized continuous form. The matrix expression of convolution is effectively applied in convolutional neural networks, and in this study, we correlate the concept of convolu...

(This article belongs to the Special Issue Integral Equations: Theories, Approximations and Applications)
  • Article
  • Open Access
33 Citations
4,605 Views
25 Pages

1 October 2023

In recent years, convolutional neural networks (CNNs) have been increasingly leveraged for the classification of hyperspectral imagery, displaying notable advancements. To address the issues of insufficient spectral and spatial information extraction...

(This article belongs to the Special Issue New Advances in Hyperspectral–Multispectral Image Classification and Fusion Applications)
  • Article
  • Open Access
1,479 Views
13 Pages

r-Free Convolution and Variance Function

  • Shokrya S. Alshqaq,
  • Raouf Fakhfakh and
  • Fatimah Alshahrani

10 February 2025

The concept of r-free convolution (which is represented by r) was introduced for 0≤r≤1. It is equal to the Boolean additive convolution ⊎ if r=0 and reduced to the free additive convolution ⊞ when r=1. This paper presents certain fe...

(This article belongs to the Section Mathematical Analysis)
  • Article
  • Open Access
1 Citations
1,792 Views
15 Pages

Notes on the Free Additive Convolution

  • Shokrya S. Alshqaq,
  • Raouf Fakhfakh and
  • Fatimah Alshahrani

9 June 2025

The investigation of free additive convolution is a key concept in free probability theory, offering a framework for studying the sum of freely independent random variables. This paper uses free additive convolution and measure dilations to investiga...

(This article belongs to the Section Mathematical Analysis)
  • Article
  • Open Access
10 Citations
5,139 Views
24 Pages

Image Inpainting with Bilateral Convolution

  • Wenli Huang,
  • Ye Deng,
  • Siqi Hui and
  • Jinjun Wang

3 December 2022

Due to sensor malfunctions and poor atmospheric conditions, remote sensing images often miss important information/pixels, which affects downstream tasks, therefore requiring reconstruction. Current image reconstruction methods use deep convolutional...

(This article belongs to the Special Issue Artificial Intelligence Algorithm for Remote Sensing Imagery Processing Ⅱ)
  • Feature Paper
  • Article
  • Open Access
2 Citations
2,371 Views
13 Pages

On a Generalized Convolution Operator

  • Poonam Sharma,
  • Ravinder Krishna Raina and
  • Janusz Sokół

10 November 2021

Recently in the paper [Mediterr. J. Math. 2016, 13, 1535–1553], the authors introduced and studied a new operator which was defined as a convolution of the three popular linear operators, namely the Sǎlǎgean operator, the Ruscheweyh operator and...

  • Article
  • Open Access
904 Views
14 Pages

DROPc-Dynamic Resource Optimization for Convolution Layer

  • Muhammad Ali Akbar,
  • Bo Wang,
  • Samir Brahim Belhaouari and
  • Amine Bermak

The computational complexity of convolutional neural networks (CNNs) becomes challenging for resource-constrained hardware devices. The convolution layer is predominant in the overall CNN architecture, performing the expensive multiplication and accu...

(This article belongs to the Special Issue Research on Key Technologies for Hardware Acceleration)
  • Article
  • Open Access
12 Citations
5,951 Views
21 Pages

Dilated Skip Convolution for Facial Landmark Detection

  • Seyha Chim,
  • Jin-Gu Lee and
  • Ho-Hyun Park

4 December 2019

Facial landmark detection has gained enormous interest for face-related applications due to its success in facial analysis tasks such as facial recognition, cartoon generation, face tracking and facial expression analysis. Many studies have been prop...

(This article belongs to the Special Issue Emotion and Stress Recognition Related Sensors and Machine Learning Technologies)
  • Article
  • Open Access
1 Citations
2,580 Views
11 Pages

Calibrated Convolution with Gaussian of Difference

  • Huoxiang Yang,
  • Chao Li,
  • Yongsheng Liang,
  • Wei Liu and
  • Fanyang Meng

29 June 2022

Attention mechanisms are widely used for Convolutional Neural Networks (CNNs) when performing various visual tasks. Many methods introduce multi-scale information into attention mechanisms to improve their feature transformation performance; however,...

(This article belongs to the Special Issue AI-Based Image Processing)
  • Article
  • Open Access
2 Citations
2,248 Views
16 Pages

A Multiplierless Architecture for Image Convolution in Memory

  • John Reuben,
  • Felix Zeller,
  • Benjamin Seiler and
  • Dietmar Fey

Image convolution is a commonly required task in machine vision and Convolution Neural Networks (CNNs). Due to the large data movement required, image convolution can benefit greatly from in-memory computing. However, image convolution is very comput...

(This article belongs to the Special Issue Energy Consumption Management in Electronic Systems)
  • Article
  • Open Access
9 Citations
2,320 Views
12 Pages

2 November 2020

In this paper, the solvability of a class of convolution equations is discussed by using two-dimensional (2D) fractional Fourier transform (FRFT) in polar coordinates. Firstly, we generalize the 2D FRFT to the polar coordinates setting. The relations...

(This article belongs to the Special Issue Modern Analysis and Partial Differential Equation)
  • Article
  • Open Access
11 Citations
13,055 Views
29 Pages

Live Convolution with Time-Varying Filters

  • Øyvind Brandtsegg,
  • Sigurd Saue and
  • Victor Lazzarini

12 January 2018

The paper presents two new approaches to artefact-free real-time updates of the impulse response in convolution. Both approaches are based on incremental updates of the filter. This can be useful for several applications within digital audio processi...

(This article belongs to the Special Issue Sound and Music Computing)
  • Feature Paper
  • Article
  • Open Access
2,257 Views
28 Pages

On the Inversion of the Mellin Convolution

  • Gabriel Bengochea,
  • Manuel Ortigueira and
  • Fernando Arroyo-Cabañas

28 January 2025

The deconvolution of the Mellin convolution is studied for a great variety of functions that are expressed in terms of α–log-exponential monomials. It is shown that the generation of pairs of functions satisfying a Sonin-like condition ca...

(This article belongs to the Special Issue Fractional Calculus and Mathematical Applications, 2nd Edition)
  • Article
  • Open Access
974 Views
20 Pages

20 October 2025

Deep neural network-based approaches have obtained remarkable progress in monaural speech enhancement. Nevertheless, current cutting-edge approaches remain vulnerable to complex acoustic scenarios. We propose a Symmetric Combined Convolution Network...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
1 Citations
1,900 Views
10 Pages

An Efficient Frequency Encoding Scheme for Optical Convolution Accelerator

  • Gongyu Xia,
  • Jiacheng Liu,
  • Qilin Hong,
  • Pingyu Zhu and ,
  • Ping Xu and
  • Zhihong Zhu
  • + 1 author+ 0 author

31 December 2024

In today’s era where the demand for computational resources by large models is increasingly high, optical computing offers an alternative physical platform for computation. With its high parallelism and the maturation of integrated photonic tec...

(This article belongs to the Topic Machine Learning in Communication Systems and Networks, 2nd Edition)
  • Article
  • Open Access
24 Citations
6,622 Views
14 Pages

Convolution Accelerator Designs Using Fast Algorithms

  • Yulin Zhao,
  • Donghui Wang and
  • Leiou Wang

27 May 2019

Convolutional neural networks (CNNs) have achieved great success in image processing. However, the heavy computational burden it imposes makes it difficult for use in embedded applications that have limited power consumption and performance. Although...

  • Article
  • Open Access
7 Citations
3,493 Views
21 Pages

Generalized Quantum Convolution for Multidimensional Data

  • Mingyoung Jeng,
  • Alvir Nobel,
  • Vinayak Jha,
  • David Levy and ,
  • Dylan Kneidel,
  • Manu Chaudhary,
  • Ishraq Islam,
  • Muhammad Momin Rahman and
  • Esam El-Araby
  • + 4 authors+ 0 author

31 October 2023

The convolution operation plays a vital role in a wide range of critical algorithms across various domains, such as digital image processing, convolutional neural networks, and quantum machine learning. In existing implementations, particularly in qu...

(This article belongs to the Special Issue Advances in Quantum Computing)
  • Article
  • Open Access
1 Citations
1,046 Views
16 Pages

On the t-Transformation of Free Convolution

  • Shokrya S. Alshqaq,
  • Ohud A. Alqasem and
  • Raouf Fakhfakh

18 May 2025

The study of the stability of measure families under measure transformations, as well as the accompanying limit theorems, is motivated by both fundamental and applied probability theory and dynamical systems. Stability analysis tries to uncover invar...

(This article belongs to the Section D1: Probability and Statistics)
  • Article
  • Open Access
11 Citations
2,939 Views
40 Pages

11 August 2024

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have made considerable advances in hyperspectral image (HSI) classification. However, most CNN-based methods learn features at a single-scale in HSI data, which may be insuf...

(This article belongs to the Special Issue Artificial Intelligence Algorithm for Remote Sensing Imagery Processing (4th Edition))
  • Article
  • Open Access
3 Citations
3,174 Views
14 Pages

A Seismic Phase Recognition Algorithm Based on Time Convolution Networks

  • Zhenhua Han,
  • Yu Li,
  • Kai Guo,
  • Gang Li and ,
  • Wen Zheng and
  • Hongfu Liu
  • + 1 author+ 0 author

23 September 2022

Over recent years, frequent earthquakes have caused huge losses in human life and property. Rapid and automatic earthquake detection plays an important role in earthquake warning systems and earthquake operation mechanism research. Temporal convoluti...

(This article belongs to the Special Issue Recent Advances in Big Data Analytics)
  • Article
  • Open Access
9 Citations
4,808 Views
15 Pages

10 January 2022

This paper presents a convolution kernel initialization method based on the local binary patterns (LBP) algorithm and sparse autoencoder. This method can be applied to the initialization of the convolution kernel in the convolutional neural network (...

  • Article
  • Open Access
4 Citations
1,815 Views
13 Pages

The electroencephalogram (EEG), widely used for measuring the brain’s electrophysiological activity, has been extensively applied in the automatic detection of epileptic seizures. However, several challenges remain unaddressed in prior studies...

(This article belongs to the Section Biosignal Processing)
  • Article
  • Open Access
5 Citations
3,843 Views
22 Pages

10 December 2020

In this article, we propose a set of efficient algorithmic solutions for computing short linear convolutions focused on hardware implementation in VLSI. We consider convolutions for sequences of length N= 2, 3, 4, 5, 6, 7, and 8. Hardwired units that...

(This article belongs to the Special Issue Theory and Applications in Digital Signal Processing)
  • Article
  • Open Access
7 Citations
2,546 Views
15 Pages

The convolution product is widely used in many fields, such as signal processing, numerical analysis and so on; however, the convolution theorem in the domain of the windowed metaplectic transformation (WFMT) has not been studied. The primary goal of...

  • Article
  • Open Access
46 Citations
4,828 Views
16 Pages

25 May 2020

In the prognostics health management (PHM) of rotating machinery, the accurate identification of bearing fault is critical. In recent years, various deep learning methods can well identify bearing fault based on monitoring data. However, facing chang...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
474 Views
17 Pages

Convolution of Vector Measures on Locally Compact Groups

  • Keng Wiboonton and
  • Sorravit Phonrakkhet

16 April 2026

We establish two definitions of the convolution of vector measures on locally compact groups by employing injective tensor integration. These two formulations are shown to be isomorphic. We further investigate fundamental properties of the convolutio...

(This article belongs to the Section B: Mathematics)
  • Article
  • Open Access
12 Citations
4,088 Views
26 Pages

2 July 2022

The large intra-class difference and inter-class similarity of scene images bring great challenges to the research of remote-sensing scene image classification. In recent years, many remote-sensing scene classification methods based on convolutional...

(This article belongs to the Special Issue Deep Neural Networks for Remote Sensing Scene Classification)
  • Article
  • Open Access
1 Citations
2,018 Views
21 Pages

A new fractional accumulation technique based on discrete sequence convolution transform was developed. The accumulation system, whose unit impulse response is the accumulation convolution sequence, was constructed; then, the order was extended to fr...

(This article belongs to the Special Issue Fractional-Order Circuits, Systems, and Signal Processing)
  • Article
  • Open Access
8 Citations
3,663 Views
23 Pages

A Dual-Path Small Convolution Network for Hyperspectral Image Classification

  • Lanxue Dang,
  • Peidong Pang,
  • Xianyu Zuo,
  • Yang Liu and
  • Jay Lee

27 August 2021

Convolutional neural network (CNN) has shown excellent performance in hyperspectral image (HSI) classification. However, the structure of the CNN models is complex, requiring many training parameters and floating-point operations (FLOPs). This is oft...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
11 Citations
5,079 Views
20 Pages

A High-Performance FPGA-Based Depthwise Separable Convolution Accelerator

  • Jiye Huang,
  • Xin Liu,
  • Tongdong Guo and
  • Zhijin Zhao

Depthwise separable convolution (DSC) significantly reduces parameter and floating operations with an acceptable loss of accuracy and has been widely used in various lightweight convolutional neural network (CNN) models. In practical applications, ho...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
6 Citations
2,905 Views
20 Pages

10 February 2023

With the rapid advancement of deep learning theory and hardware device computing capacity, computer vision tasks, such as object detection and instance segmentation, have entered a revolutionary phase in recent years. As a result, extremely challengi...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
13 Citations
4,064 Views
20 Pages

Sequence Image Interpolation via Separable Convolution Network

  • Xing Jin,
  • Ping Tang,
  • Thomas Houet,
  • Thomas Corpetti and ,
  • Emilien Gence Alvarez-Vanhard and
  • Zheng Zhang
  • + 1 author+ 0 author

15 January 2021

Remote-sensing time-series data are significant for global environmental change research and a better understanding of the Earth. However, remote-sensing acquisitions often provide sparse time series due to sensor resolution limitations and environme...

(This article belongs to the Special Issue Computer Vision and Deep Learning for Remote Sensing Applications)
  • Article
  • Open Access
24 Citations
3,134 Views
21 Pages

FCNet: Flexible Convolution Network for Infrared Small Ship Detection

  • Feng Guo,
  • Hongbing Ma,
  • Liangliang Li,
  • Ming Lv and
  • Zhenhong Jia

19 June 2024

The automatic monitoring and detection of maritime targets hold paramount significance in safeguarding national sovereignty, ensuring maritime rights, and advancing national development. Among the principal means of maritime surveillance, infrared (I...

(This article belongs to the Topic Ship Dynamics, Stability and Safety)
  • Article
  • Open Access
5 Citations
2,376 Views
14 Pages

10 April 2024

The three-dimensional (3D) reconstruction of Electromagnetic Tomography (EMT) is an important task for many applications, such as the non-destructive testing of inner defects in rail systems. Additionally, image reconstruction algorithms utilizing de...

(This article belongs to the Section Applied Industrial Technologies)
  • Article
  • Open Access
380 Views
24 Pages

If one compares the continuous-time convolution outputs with their sampled discrete counterparts, one may observe slight differences even when the sampling process itself is otherwise straightforward. This issue becomes noticeable when one or both co...

  • Article
  • Open Access
4 Citations
2,825 Views
14 Pages

10 March 2023

The implementation of a brain–computer interface (BCI) using electroencephalography typically entails two phases: feature extraction and classification utilizing a classifier. Consequently, there are numerous disordered combinations of feature...

(This article belongs to the Special Issue Deep Learning for Electroencephalography(EEG) Data Analysis)
  • Article
  • Open Access
2,032 Views
21 Pages

Karatsuba Algorithm Revisited for 2D Convolution Computation Optimization

  • Qi Wang,
  • Jianghan Zhu,
  • Can He,
  • Shihang Wang and ,
  • Xingbo Wang,
  • Yuan Ren and
  • Terry Tao Ye
  • + 2 authors+ 0 author

8 May 2025

Convolution plays a significant role in many scientific and technological computations, such as artificial intelligence and signal processing. Convolutional computations consist of many dot-product operations (multiplication–accumulation, or MA...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
104 Citations
14,088 Views
18 Pages

An FPGA-Based CNN Accelerator Integrating Depthwise Separable Convolution

  • Bing Liu,
  • Danyin Zou,
  • Lei Feng,
  • Shou Feng and ,
  • Ping Fu and
  • Junbao Li
  • + 1 author+ 0 author

The Convolutional Neural Network (CNN) has been used in many fields and has achieved remarkable results, such as image classification, face detection, and speech recognition. Compared to GPU (graphics processing unit) and ASIC, a FPGA (field programm...

(This article belongs to the Special Issue Convolutional Neural Network Design and Hardware Implementation for Real-Time Vision Applications)
  • Article
  • Open Access
6 Citations
3,566 Views
12 Pages

Furniture Image Classification Based on Depthwise Group Over-Parameterized Convolution

  • Han Ye,
  • Xiaodong Zhu,
  • Chengyang Liu,
  • Linlin Yang and
  • Aili Wang

24 November 2022

In this paper, an improved VGG16 combined with depthwise group over-parameterized convolution (DGOVGG16) model is proposed to realize automatic furniture image classification. Firstly, depthwise over-parameterized convolution combined with group conv...

(This article belongs to the Special Issue Deep Learning in Image Processing and Pattern Recognition)
  • Article
  • Open Access
4 Citations
3,397 Views
11 Pages

19 November 2019

We extend a technique recently introduced by Chen Zhuoyu and Qi Lan in order to find convolution formulas for second order linear recurrence polynomials generated by 1 1 + a t + b t 2 x . The case of generating functions containing...

(This article belongs to the Special Issue Differential and Difference Equations: A Themed Issue Dedicated to Prof. Hari M. Srivastava on the Occasion of his 80th Birthday)
  • Article
  • Open Access
1 Citations
3,593 Views
20 Pages

The study of convolutional neural networks for 3D point clouds is becoming increasingly popular, and the difficulty lies mainly in the disorder and irregularity of point clouds. At present, it is straightforward to propose a convolution operation and...

  • Article
  • Open Access
7 Citations
2,910 Views
17 Pages

Object-Aware Adaptive Convolution Kernel Attention Mechanism in Siamese Network for Visual Tracking

  • Dongliang Yuan,
  • Qingdang Li,
  • Xiaohui Yang,
  • Mingyue Zhang and
  • Zhen Sun

12 January 2022

As a classic framework for visual object tracking, the Siamese convolutional neural network has received widespread attention from the research community. This method uses a convolutional neural network to obtain the object features and to match them...

(This article belongs to the Special Issue Selected Papers from FCPAE2021 and 3rd International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2021))
  • Article
  • Open Access
4 Citations
3,504 Views
15 Pages

Lightweight Super-Resolution with Self-Calibrated Convolution for Panoramic Videos

  • Fanjie Shang,
  • Hongying Liu,
  • Wanhao Ma,
  • Yuanyuan Liu and ,
  • Licheng Jiao,
  • Fanhua Shang,
  • Lijun Wang and
  • Zhenyu Zhou
  • + 3 authors+ 0 author

30 December 2022

Panoramic videos are shot by an omnidirectional camera or a collection of cameras, and can display a view in every direction. They can provide viewers with an immersive feeling. The study of super-resolution of panoramic videos has attracted much att...

(This article belongs to the Collection Advances in Deep-Learning-Based Sensing, Imaging, and Video Processing)
  • Article
  • Open Access
14 Citations
3,656 Views
15 Pages

29 March 2022

In this paper, we propose a fully convolutional neural network based on recursive recurrent convolution for monaural speech enhancement in the time domain. The proposed network is an encoder-decoder structure using a series of hybrid dilated modules...

(This article belongs to the Special Issue Automatic Speech Recognition)
  • Article
  • Open Access
2 Citations
1,105 Views
30 Pages

2 April 2026

The accurate detection of epileptic seizures using an electroencephalogram (EEG) is essential for clinical diagnosis and reducing the burden on clinicians but remains challenging due to low detection performance and model interpretability. In this st...

(This article belongs to the Section Biosensors and Healthcare)
  • Article
  • Open Access
879 Views
10 Pages

Horváth Spaces and a Representations of the Fourier Transform and Convolution

  • Emilio R. Negrín,
  • Benito J. González and
  • Jeetendrasingh Maan

28 July 2025

This paper explores the structural representation and Fourier analysis of elements in Horváth distribution spaces Sk′, for k<−n. We prove that any element in Sk′ can be expressed as a finite sum of derivatives of continuou...

(This article belongs to the Special Issue Special Functions with Applications)

of 689