Skip to Content

318 Results Found

  • Article
  • Open Access
2,494 Views
14 Pages

11 September 2023

Few-shot object detection (FSOD) aims to detect objects belonging to novel classes with few training samples. With the small number of novel class samples, the visual information extracted is insufficient to accurately represent the object itself, pr...

(This article belongs to the Special Issue Application of Machine Learning in Graphics and Images)
  • Article
  • Open Access
6 Citations
4,321 Views
16 Pages

4 October 2022

Weakly supervised object detection (WSOD) has received increasing attention in object detection field, because it only requires image-level annotations to indicate the presence or absence of target objects, which greatly reduces the labeling costs. E...

(This article belongs to the Special Issue Deep Learning Technology and Image Sensing)
  • Article
  • Open Access
2 Citations
2,037 Views
12 Pages

Efficient Implementation of Multilayer Perceptrons: Reducing Execution Time and Memory Consumption

  • Francisco Cedron,
  • Sara Alvarez-Gonzalez,
  • Ana Ribas-Rodriguez,
  • Santiago Rodriguez-Yañez and
  • Ana Belen Porto-Pazos

7 September 2024

A technique is presented that reduces the required memory of neural networks through improving weight storage. In contrast to traditional methods, which have an exponential memory overhead with the increase in network size, the proposed method stores...

(This article belongs to the Special Issue Computational and Mathematical Methods for Neuroscience)
  • Article
  • Open Access
203 Views
32 Pages

28 October 2026

Video class-incremental learning retains old knowledge while learning new actions under limited replay memory. Temporal compression stores more videos but may lose temporal details and introduce discrepancies between compressed and original videos. W...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
3,244 Views
23 Pages

3 December 2020

The key challenges of manycore systems are the large amount of memory and high bandwidth required to run many applications. Three-dimesnional integrated on-chip memory is a promising candidate for addressing these challenges. The advent of on-chip me...

(This article belongs to the Special Issue Storage Systems with Non-volatile Memory Devices)
  • Article
  • Open Access
9 Citations
3,239 Views
28 Pages

A Contrastive-Augmented Memory Network for Anti-UAV Tracking in TIR Videos

  • Ziming Wang,
  • Yuxin Hu,
  • Jianwei Yang,
  • Guangyao Zhou and ,
  • Fangjian Liu and
  • Yuhan Liu
  • + 1 author+ 0 author

21 December 2024

With the development of unmanned aerial vehicle (UAV) technology, the threat of UAV intrusion is no longer negligible. Therefore, drone perception, especially anti-UAV tracking technology, has gathered considerable attention. However, both traditiona...

(This article belongs to the Special Issue Artificial Intelligence-Driven Methods for Remote Sensing Target and Object Detection II)
  • Article
  • Open Access
846 Views
22 Pages

Resistive random-access memory (RRAM) crossbar architectures are constrained by the limited number of word lines that can be activated simultaneously, thereby restricting the degree of parallelism achievable in computing-in-memory systems. To allevia...

(This article belongs to the Special Issue Resistive Random Access Memory Devices: Mechanisms, Materials, Devices, and Applications)
  • Article
  • Open Access
44 Citations
10,743 Views
26 Pages

Memory Forensics-Based Malware Detection Using Computer Vision and Machine Learning

  • Syed Shakir Hameed Shah,
  • Abd Rahim Ahmad,
  • Norziana Jamil and
  • Atta ur Rehman Khan

18 August 2022

Malware has recently grown exponentially in recent years and poses a serious threat to individual users, corporations, banks, and government agencies. This can be seen from the growth of Advanced Persistent Threats (APTs) that make use of advance and...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
166 Views
24 Pages

SDD: Synergistic Dual-Memory Debiasing for Semi-Supervised Continual Learning

  • Qiang Wang,
  • Zeyu Peng,
  • Bin Lu,
  • Ning Zhang and ,
  • Shuang Wei,
  • Hui Wang and
  • Wenjin Xu
  • + 2 authors+ 0 author

20 October 2026

Semi-Supervised Continual Learning (SSCL) aims to enable deep learning models to learn incrementally from label-scarce streaming data without catastrophic forgetting. Existing SSCL methods face two core issues: severe overfitting to limited labeled s...

  • Article
  • Open Access
1 Citations
1,061 Views
23 Pages

Multi-modal Magnetic Resonance Imaging (MRI) provides complementary information for clinical diagnosis, yet its large-scale storage, privacy sensitivity, and annotation cost pose significant challenges. Inspired by biological vision systems, which in...

(This article belongs to the Special Issue Artificial Intelligence-Based Bio-Inspired Computer Vision System)
  • Article
  • Open Access
8 Citations
6,230 Views
8 Pages

22 October 2021

In contrast to conventional 2-dimensional (2D) NAND flash memory, in 3D NAND flash memory, cell-to-cell interference stemming from parasitic capacitance between the word-lines (WLs) is difficult to control because the number of WLs, achieved for bett...

(This article belongs to the Special Issue Hybrid Organic Electronics: Material, Structure and Application)
  • Article
  • Open Access
1 Citations
1,233 Views
16 Pages

At present, some aging populations, such as those in Japan, face an underlying risk of inadequate medical resources. Using neural networks to assist doctors in locating the aorta in patients via computed tomography (CT) before surgery is a task with...

(This article belongs to the Special Issue Artificial Intelligence-Based Medical Imaging Processing)
  • Article
  • Open Access
5 Citations
3,238 Views
18 Pages

26 October 2024

SegContrast first paved the way for contrastive learning on outdoor point clouds. Its original formulation targeted individual scans in applications like autonomous driving and object detection. However, mobile mapping purposes such as digital twin c...

(This article belongs to the Special Issue Advances in Understanding and 3D Semantic Modeling of Large-Scale Urban Scenes from Point Clouds (Second Edition))
  • Article
  • Open Access
1,678 Views
14 Pages

Optimizing Contrastive Learning with Semi-Online Triplet Mining

  • Przemysław Buczkowski,
  • Marek Kozłowski and
  • Piotr Brzeziński

14 July 2025

Contrastive learning is a machine learning technique in which models learn by contrasting similar and dissimilar data points. Its goal is to learn a representation of data in such a way that similar instances are close together in the representation...

  • Review
  • Open Access
25 Citations
5,329 Views
25 Pages

28 September 2023

This paper reviews recent advancements in all-optical memory components, particularly focusing on various types of all-optical flip-flops (FFs) based on photonic crystal (PC) structures proposed in recent years. PCs, with their unique optical propert...

(This article belongs to the Section Optical and Photonic Materials)
  • Article
  • Open Access
12 Citations
3,413 Views
36 Pages

13 November 2024

Urban memory involves the re-creation of a city’s physical, historical, social, and cultural elements in the memories of its inhabitants. However, urban transformation and commercial tourism-oriented projects may threaten the continuity of this...

(This article belongs to the Special Issue Resident Well-Being and Sustainable Tourism Development)
  • Article
  • Open Access
371 Views
21 Pages

15 June 2026

This study investigates the Mittag–Leffler-type stability properties of fractional perturbed systems with respect to their unperturbed counterparts by incorporating initial time differences into the analysis. In contrast to many existing studie...

(This article belongs to the Section C1: Difference and Differential Equations)
  • Review
  • Open Access
765 Views
23 Pages

14 May 2026

Trauma-related autobiographical memories can manifest as involuntary, vivid, emotionally charged intrusions that perpetuate avoidance, negative emotions, and functional impairment. While these memories are central to post-traumatic stress disorder (P...

  • Article
  • Open Access
17 Citations
4,344 Views
12 Pages

12 November 2021

Chalcogenide phase-change materials (PCMs) based random access memory (PCRAM) enter the global memory market as storage-class memory (SCM), holding great promise for future neuro-inspired computing and non-volatile photonic applications. The thermal...

(This article belongs to the Special Issue Synthesis, Properties and Applications of Germanium Chalcogenides)
  • Article
  • Open Access
11 Citations
7,540 Views
16 Pages

Increased X-ray Visualization of Shape Memory Polymer Foams by Chemical Incorporation of Iodine Motifs

  • Landon D. Nash,
  • Mary Beth Browning Monroe,
  • Yong-Hong Ding,
  • Kendal P. Ezell and ,
  • Anthony J. Boyle,
  • Ramanathan Kadirvel,
  • David F. Kallmes and
  • Duncan J. Maitland
  • + 3 authors+ 0 author

20 August 2017

Shape memory polymers can be programmed into a secondary geometry and recovered to their primary geometry with the application of a controlled stimulus. Porous shape memory polymer foam scaffolds that respond to body temperature show particular promi...

(This article belongs to the Special Issue Shape Memory Polymers)
  • Article
  • Open Access
610 Views
13 Pages

17 July 2026

Spatial working memory (SWM) has been characterised as a flexible resource that determines the precision with which memoranda are stored. The ‘cortical map’ proposal predicts that resource allocation, and therefore mnemonic precision, is...

(This article belongs to the Section Visual Neuroscience)
  • Article
  • Open Access
1 Citations
3,174 Views
29 Pages

External Stimuli on Neural Networks: Analytical and Numerical Approaches

  • Evaldo M. F. Curado,
  • Nilo B. Melgar and
  • Fernando D. Nobre

11 August 2021

Based on the behavior of living beings, which react mostly to external stimuli, we introduce a neural-network model that uses external patterns as a fundamental tool for the process of recognition. In this proposal, external stimuli appear as an addi...

(This article belongs to the Special Issue Memory Storage Capacity in Recurrent Neural Networks)
  • Article
  • Open Access
5 Citations
1,847 Views
24 Pages

Memory-Based Temporal Transformer U-Net for Multi-Frame Infrared Small Target Detection

  • Zicheng Feng,
  • Wenlong Zhang,
  • Donghui Liu,
  • Xingfu Tao and ,
  • Ang Su and
  • Yixin Yang
  • + 1 author+ 0 author

23 November 2025

In the field of infrared small target detection (ISTD), single-frame ISTD (SISTD), using only spatial features, cannot deal well with dim targets in cluttered backgrounds. In contrast, multi-frame ISTD (MISTD), utilizing spatio-temporal information f...

(This article belongs to the Section AI Remote Sensing)
  • Article
  • Open Access
9 Citations
4,472 Views
13 Pages

Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation

  • Xuejun Zhao,
  • Rafal Stanislawski,
  • Paolo Gardoni,
  • Maciej Sulowicz and ,
  • Adam Glowacz,
  • Grzegorz Krolczyk and
  • Zhixiong Li
  • + 2 authors+ 0 author

2 June 2022

Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy iss...

(This article belongs to the Special Issue Artificial Intelligence for Fault Diagnostics and Prognostics)
  • Article
  • Open Access
1 Citations
3,036 Views
13 Pages

Asymmetric Graph Contrastive Learning

  • Xinglong Chang,
  • Jianrong Wang,
  • Rui Guo,
  • Yingkui Wang and
  • Weihao Li

31 October 2023

Learning effective graph representations in an unsupervised manner is a popular research topic in graph data analysis. Recently, contrastive learning has shown its success in unsupervised graph representation learning. However, how to avoid collapsin...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
4 Citations
3,118 Views
12 Pages

An Effective Multi-Task Two-Stage Network with the Cross-Scale Training Strategy for Multi-Scale Image Super Resolution

  • Jucheng Yang,
  • Feng Wei,
  • Yaxin Bai,
  • Meiran Zuo and ,
  • Xiao Sun and
  • Yarui Chen
  • + 1 author+ 0 author

7 October 2021

Convolutional neural networks and the per-pixel loss function have shown their potential to be the best combination for super-resolving severely degraded images. However, there are still challenges, such as the massive number of parameters requiring...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
889 Views
22 Pages

MemGanomaly: Memory-Augmented Ganomaly for Frost- and Heat-Damaged Crop Detection

  • Jun Park,
  • Sung-Wook Park,
  • Yong-Seok Kim,
  • Se-Hoon Jung and
  • Chun-Bo Sim

28 September 2025

Climate change poses significant challenges to agriculture, leading to increased crop damage owing to extreme weather conditions. Detecting and analyzing such damage is crucial for mitigating its effects on crop yield. This study proposes a novel aut...

(This article belongs to the Special Issue Advanced Agricultural Technologies: Monitoring, Modeling, and Machine Learning Techniques)
  • Article
  • Open Access
6 Citations
3,809 Views
20 Pages

22 January 2024

Unsupervised person re-identification (Re-ID) aims to match the query image of a person with images in the gallery without the use of supervision labels. Most existing methods usually generate pseudo-labels through clustering algorithms for contrasti...

(This article belongs to the Special Issue Unmanned Aerial Vehicles (UAV): New Solutions and Applications for Real-Life Tasks)
  • Article
  • Open Access
4 Citations
1,850 Views
39 Pages

Over the last decade, convolutional neural networks (CNNs) have demonstrated significant potential in assisting medical diagnosis. Research has focused on implementing such networks, particularly in the context of embedded medical systems. This can b...

(This article belongs to the Special Issue Image Processing Based on Convolution Neural Network: 2nd Edition)
  • Article
  • Open Access
1 Citations
1,359 Views
20 Pages

22 August 2025

This study examines two proximate yet theologically and spatially disparate religious spaces in Seoul: the Jeoldusan Martyrs’ Shrine (Korean: 절두산 순교 성지; hereafter “Jeoldusan Martyrs’...

(This article belongs to the Special Issue Religion and Politics: Interactions and Boundaries)
  • Article
  • Open Access

Deep Unfolding with Target Confidence and Cross-Stage Memory for Infrared Small Target Detection

  • Yiwen Wang,
  • Yiming Zhao,
  • Xiaoguang Shao,
  • Wei Zheng and ,
  • Jingyu Li and
  • Xiang Li
  • + 1 author+ 0 author

19 November 2026

Infrared small targets occupy few pixels and often exhibit weak contrast, making them difficult to distinguish from bright edges, background clutter, and noise. Deep unfolding provides an interpretable framework for background–target decomposit...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
3 Citations
4,609 Views
16 Pages

15 May 2023

Information systems play an important role in business management, especially in personnel, budget, and financial management. If an anomaly ensues in an information system, all operations are paralyzed until their recovery. In this study, we propose...

(This article belongs to the Special Issue Disruptive Technologies and Wireless Sensor Network Communication Algorithms)
  • Article
  • Open Access
33 Citations
5,317 Views
23 Pages

Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network

  • Shaoqian Pei,
  • Hui Qin,
  • Liqiang Yao,
  • Yongqi Liu and ,
  • Chao Wang and
  • Jianzhong Zhou
  • + 1 author+ 0 author

10 August 2020

Short-term load forecasting (STLF) plays an important role in the economic dispatch of power systems. Obtaining accurate short-term load can greatly improve the safety and economy of a power grid operation. In recent years, a large number of short-te...

(This article belongs to the Section A1: Smart Grids and Microgrids)
  • Article
  • Open Access
271 Views
16 Pages

A Two-Stage and Hierarchical Contrastive Learning Method for Power Equipment Defect Detection

  • Mengyu Li,
  • Minghui Li,
  • Zhongqiang Zhou,
  • Jincun Zhang and ,
  • Xujie Zhuang,
  • Chaoxin Zhang,
  • Baidong Li and
  • Xiaojin Gong
  • + 3 authors+ 0 author

31 August 2026

Power equipment defect detection is essential for ensuring reliable power grid operation. Existing power equipment defect detection methods typically formulate the task as multi-class object detection, but their performance is limited by long-tailed...

  • Article
  • Open Access
1,244 Views
18 Pages

10 November 2025

In embedded real-time operating systems, memory protection mechanisms are critical for ensuring system security. However, for closed-source platforms like VxWorks, widely used in critical domains such as aerospace and industrial control, existing met...

  • Article
  • Open Access
19 Citations
4,938 Views
14 Pages

Retinal OCTA Image Segmentation Based on Global Contrastive Learning

  • Ziping Ma,
  • Dongxiu Feng,
  • Jingyu Wang and
  • Hu Ma

14 December 2022

The automatic segmentation of retinal vessels is of great significance for the analysis and diagnosis of retinal related diseases. However, the imbalanced data in retinal vascular images remain a great challenge. Current image segmentation methods ba...

(This article belongs to the Special Issue Advances in Artificial Intelligence for Biomedical Signal and Image Analysis)
  • Review
  • Open Access
57 Citations
10,593 Views
19 Pages

Is Sleep Disruption a Cause or Consequence of Alzheimer’s Disease? Reviewing Its Possible Role as a Biomarker

  • Maria-Angeles Lloret,
  • Ana Cervera-Ferri,
  • Mariana Nepomuceno,
  • Paloma Monllor and ,
  • Daniel Esteve and
  • Ana Lloret
  • + 1 author+ 0 author

10 February 2020

In recent years, the idea that sleep is critical for cognitive processing has gained strength. Alzheimer’s disease (AD) is the most common form of dementia worldwide and presents a high prevalence of sleep disturbances. However, it is difficult...

(This article belongs to the Special Issue Peripheral Biomarkers in Neurodegenerative Diseases)
  • Article
  • Open Access
11 Citations
4,278 Views
20 Pages

Cross-Modal Contrastive Hashing Retrieval for Infrared Video and EEG

  • Jianan Han,
  • Shaoxing Zhang,
  • Aidong Men and
  • Qingchao Chen

14 November 2022

It is essential to estimate the sleep quality and diagnose the clinical stages in time and at home, because they are closely related to and important causes of chronic diseases and daily life dysfunctions. However, the existing “gold-standard&r...

(This article belongs to the Special Issue EEG Signal Processing for Sensing Technologies in Biomedical Engineering Applications)
  • Article
  • Open Access
1 Citations
1,252 Views
18 Pages

23 January 2026

This paper presents the design and feasibility evaluation of a low-cost, head-mounted pupil dilation tracking system based on computer vision. The proposed solution employs a standard webcam and active infrared illumination, enabling stable eye image...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
10 Citations
3,942 Views
14 Pages

Trajectory prediction of surrounding vehicles is a critical task for connected and autonomous vehicles (CAVs), helping them to realize potential dangers in the traffic environment and make the most appropriate decisions. In a practical traffic enviro...

(This article belongs to the Special Issue Emerging Communication, Computing and Control Technologies for Internet of Vehicles)
  • Article
  • Open Access
2 Citations
3,395 Views
14 Pages

This study proposes an effective method for identifying human movement direction in indoor environments by leveraging a low-resolution time-of-flight (ToF) sensor and a long short-term memory (LSTM) neural network model. While previous studies have e...

(This article belongs to the Special Issue Security and Smart Applications in IoT and Wireless Sensor and Actuator Networks)
  • Review
  • Open Access
18 Citations
5,657 Views
15 Pages

17 September 2020

From the time of Thucydides in the 5th century BC, it has been known that specific recognition of pathogens and memory formation are critical components of immune functions. In contrast to the immune system of jawed vertebrates, such as humans and mi...

(This article belongs to the Special Issue Immune Mechanisms in Plants)
  • Article
  • Open Access
7 Citations
4,210 Views
16 Pages

Graph Clustering with High-Order Contrastive Learning

  • Wang Li,
  • En Zhu,
  • Siwei Wang and
  • Xifeng Guo

10 October 2023

Graph clustering is a fundamental and challenging task in unsupervised learning. It has achieved great progress due to contrastive learning. However, we find that there are two problems that need to be addressed: (1) The augmentations in most graph c...

(This article belongs to the Special Issue Pattern Recognition and Data Clustering in Information Theory)
  • Article
  • Open Access
5 Citations
2,370 Views
24 Pages

Local Contrast Learning for One-Shot Learning

  • Yang Zhang,
  • Xinghai Yuan,
  • Ling Luo,
  • Yulu Yang and ,
  • Shihao Zhang and
  • Chuanyun Xu
  • + 1 author+ 0 author

15 June 2024

Learning a deep model from small data is an opening and challenging problem. In high-dimensional spaces, few samples only occupy an extremely small portion of the space, often exhibiting sparsity issues. Classifying in this globally sparse sample spa...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
4 Citations
2,765 Views
12 Pages

In this work, we propose a fast scheme based on higher order discretizations on graded meshes for resolving the temporal-fractional partial differential equation (PDE), which benefits the memory feature of fractional calculus. To avoid excessively in...

(This article belongs to the Topic Fractal and Design of Multipoint Iterative Methods for Nonlinear Problems)
  • Article
  • Open Access
1 Citations
2,591 Views
16 Pages

19 September 2024

Semi-supervised medical image segmentation models often face challenges such as empirical mismatch and data imbalance. Traditional methods, like the two-stream perturbation model, tend to over-rely on strong perturbation, leaving weak perturbation an...

  • Review
  • Open Access
18 Citations
6,127 Views
30 Pages

A Review of Additively Manufactured Iron-Based Shape Memory Alloys

  • Qian Sun,
  • Xiaojun Tan,
  • Mingjun Ding,
  • Bo Cao and
  • Takeshi Iwamoto

29 August 2024

Iron-based shape memory alloys (Fe-SMAs), traditionally manufactured, are favored in engineering applications owing to their cost-effectiveness and ease of fabrication. However, the conventional manufacturing process of Fe-SMAs is time-consuming and...

(This article belongs to the Section Crystalline Metals and Alloys)
  • Article
  • Open Access
30 Citations
7,831 Views
13 Pages

Interoperability Benefits and Challenges in Smart City Services: Blockchain as a Solution

  • Sujit Biswas,
  • Zigang Yao,
  • Lin Yan,
  • Abdulmajeed Alqhatani and ,
  • Anupam Kumar Bairagi,
  • Fatima Asiri and
  • Mehedi Masud
  • + 2 authors+ 0 author

19 February 2023

The widespread usage of smart devices with various city-centric services speeds up and improves civic life, in contrast to growing privacy and security concerns. Security issues are exacerbated when e-government service providers trade their services...

(This article belongs to the Special Issue Internet of Things for Smart City: Challenges and Solutions)
  • Article
  • Open Access
3 Citations
3,278 Views
19 Pages

3 August 2023

Numerous deep learning methods for acoustic scene classification (ASC) have been proposed to improve the classification accuracy of sound events. However, only a few studies have focused on continual learning (CL) wherein a model continually learns t...

(This article belongs to the Special Issue Advances in Acoustic Sensors and Deep Audio Pattern Recognition)
  • Article
  • Open Access
1,612 Views
18 Pages

SATrack: Semantic-Aware Alignment Framework for Visual–Language Tracking

  • Yangyang Tian,
  • Liusen Xu,
  • Zhe Li,
  • Liang Jiang and ,
  • Cen Chen and
  • Huanlong Zhang
  • + 1 author+ 0 author

4 October 2025

Visual–language tracking often faces challenges like target deformation and confusion caused by similar objects. These issues can disrupt the alignment between visual inputs and their textual descriptions, leading to cross-modal semantic drift...

(This article belongs to the Section Electrical and Autonomous Vehicles)

of 7