Results 61 to 70 of about 3,613,102 (160)

Attention‐Guided Lightweight CNN‐Transformer Fusion for Real‐Time Traffic Sign Recognition in Adverse Environments: HACTNet

open access: yesIET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
This paper proposes HACTNet, a low‐complexity CNN‐transformer hybrid model that pushes the state‐of‐art in TSR by making a noteworthy set of contributions including (i) efficient convaps to model parts of the image, (ii) transformer encoder to capture the global context and (iii) an attention‐based fusion block to dynamically combine the two ...
Mandeep Singh Devgan   +5 more
wiley   +1 more source

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

open access: yes, 2020
Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analysis (SA) aims to leverage useful information in multiple source domains to help do SA in an unlabeled target domain that has no supervised information.
Xu, Zenglin   +7 more
core   +1 more source

Dual Frequency Side Scan Sonar Image Fusion for Deep‐Learning Based Underwater Target Detection

open access: yesIET Radar, Sonar &Navigation, Volume 20, Issue 1, January/December 2026.
Traditional single‐frequency side‐scan sonar faces trade‐offs between imaging resolution and detection range, along with issues such as speckle noise and target–shadow coupling. To address these, this study proposes D2FNet, a dual‐domain fusion model integrating three key modules, which—tested on a new dataset of over 9000 paired sea‐trial images ...
Jiajun Xian   +9 more
wiley   +1 more source

An Empirical Analysis of MIL Pooling Under UCF‐Crime‐to‐ShanghaiTech Transfer in Weakly Supervised Video Anomaly Detection

open access: yesApplied Computational Intelligence and Soft Computing, Volume 2026, Issue 1, 2026.
Weakly supervised video anomaly detection (WSVAD) reduces the need for dense temporal annotations, but the behavior of Multiple Instance Learning (MIL) aggregation mechanisms under dataset shift remains insufficiently characterized. This study presents a controlled empirical analysis, rather than a new detection architecture, of Mean, Top‐k, and ...
Marwan Tayseer Al Zawahra   +3 more
wiley   +1 more source

TF‐MEET: A Transferable Fusion Multi‐Band Transformer for Cross‐Session EEG Decoding

open access: yesCAAI Transactions on Intelligence Technology, Volume 10, Issue 6, Page 1799-1812, December 2025.
ABSTRACT Electroencephalography (EEG) is a widely used neuroimaging technique for decoding brain states. Transformer is gaining attention in EEG signal decoding due to its powerful ability to capture global features. However, relying solely on a single feature extracted by the traditional transformer model to address the domain shift problem caused by ...
Qilong Yuan   +7 more
wiley   +1 more source

MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks

open access: yesMathematics
This paper introduces a novel unsupervised domain adaptation (UDA) method, MeTa Discriminative Class-Wise MMD (MCWMMD), which combines meta-learning with a Class-Wise Maximum Mean Discrepancy (MMD) approach to enhance domain adaptation.
Hsiau-Wen Lin   +4 more
doaj   +1 more source

The SYNTHIDIA Dataset: Synthetic Insulator Defect Imaging and Annotation

open access: yesHigh Voltage, Volume 10, Issue 6, Page 1496-1508, December 2025.
ABSTRACT Accurate and timely insulator defect detection is crucial for maintaining the reliability and safety of the power supply. However, the development of deep‐learning‐based insulator defect detection is hindered by the scarcity of comprehensive, high‐quality datasets for insulator defects.
Qingzhen Liu   +4 more
wiley   +1 more source

Efficient unsupervised domain adaptation for crack segmentation with interpretable Fourier– Morphology blending and Uncertainty‐guided self‐training

open access: yesComputer-Aided Civil and Infrastructure Engineering, Volume 40, Issue 29, Page 5790-5807, 9 December 2025.
Abstract Automated crack segmentation models are vital for infrastructure monitoring but fail when deployed in new domains. Overcoming this domain shift without costly re‐annotation is vital. This paper presents a novel unsupervised domain adaptation framework that uniquely integrates Fourier‐based style transfer with targeted morphological operators ...
Saheli Bhattacharya   +4 more
wiley   +1 more source

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds [PDF]

open access: yes, 2023
Deep perception models have to reliably cope with an open-world setting of domain shifts induced by different geographic regions, sensor properties, mounting positions, and several other reasons.
Zimmermann, Karel   +4 more
core  

Multiscale Change Detection Domain Adaptation Model Based on Illumination–Reflection Decoupling

open access: yesRemote Sensing
In the change detection (CD) task, the substantial variation in feature distributions across different CD datasets significantly limits the reusability of supervised CD models.
Rongbo Fan   +5 more
doaj   +1 more source

Home - About - Disclaimer - Privacy