Displays最新文献_第4页

Spatial derivative-guided SNR regional differentiation enhancement fusion strategy for low-light image enhancement 空间导数制导的低光图像信噪比区域分异增强融合策略

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-15 DOI: 10.1016/j.displa.2025.103219

Jiahui Zhu , Aoqun Jian , Le Yang , RunFang Hao , Luxiao Sang , Yang Ge , Rihui Kang , Shengbo Sang

{"title":"Spatial derivative-guided SNR regional differentiation enhancement fusion strategy for low-light image enhancement","authors":"Jiahui Zhu , Aoqun Jian , Le Yang , RunFang Hao , Luxiao Sang , Yang Ge , Rihui Kang , Shengbo Sang","doi":"10.1016/j.displa.2025.103219","DOIUrl":"10.1016/j.displa.2025.103219","url":null,"abstract":"<div><div>Low-light image enhancement aims to improve brightness and contrast while preserving image content. Research into this problem has made significant progress with the development of deep learning technology. However, the Signal-to-Noise Ratio(SNR) of different regions varies greatly when processing images with drastic changes in brightness. Existing methods often produce artifacts and noise that degrade image quality. To address these problems,the proposed method incorporates local and global prior knowledge into the image, employing an efficient local-to-local and local-to-global feature fusion mechanism. This facilitates the generation of enhanced images that exhibit enhanced naturalness and a broader color dynamic range. In this approach, a spatial derivative-guided SNR regional differentiation enhancement fusion strategy is introduced. The enhancement of low SNR regions is processed in the frequency domain using the Fast Fourier Transform (FFT) while the enhancement of high/normal SNR regions is handled by a convolutional encoder. The convolution residual block structure, which captures local information, generates short-range branches. The FFT module in the frequency domain generates long-range branches. The fusion of the two is guided by the SNR information of the original image. This approach also incorporates spatial derivatives as local priors in a low-light image enhancement network with an encoder–decoder structure. The encoder employs the symmetrical properties of the image’s spatial derivatives and incorporates correlating modules for the suppression of noise. Experiments conducted on disparate datasets illustrate that our approach outperforms existing state-of-the-art(SOTA) methods in terms of visual quality. Furthermore, the single-frame inference time can be reduced to 0.079 s.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103219"},"PeriodicalIF":3.4,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145095568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AsPrompt: Attribute-structured knowledge-guided dual-modal coupling prompt learning for few-shot image classification AsPrompt：基于属性结构化知识引导的双模态耦合提示学习，用于少拍图像分类

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-13 DOI: 10.1016/j.displa.2025.103217

Zhiyong Deng, Ronggui Wang, Lixia Xue, Juan Yang

{"title":"AsPrompt: Attribute-structured knowledge-guided dual-modal coupling prompt learning for few-shot image classification","authors":"Zhiyong Deng, Ronggui Wang, Lixia Xue, Juan Yang","doi":"10.1016/j.displa.2025.103217","DOIUrl":"10.1016/j.displa.2025.103217","url":null,"abstract":"<div><div>The few-shot image classification task involves classifying images when only a limited number of training images are available. This field has seen significant advancements in recent years due to the development of pre-trained vision-language models (e.g., CLIP), which exhibit strong generalization capabilities. Recent studies have further leveraged classes-related descriptions as part of prompt learning to better adapt these foundational vision-language models for downstream tasks. However, the textual descriptions used in traditional methods often lack sufficient class-discriminative information, limiting the model’s expressiveness on unseen data domains. Given that large language models possess rich structured knowledge bases, they offer new avenues for enhancing textual information. Against this backdrop, we propose a novel method called AsPrompt, which integrates attribute-structured knowledge guidance with a dual-modal coupling prompt learning mechanism. This approach not only enriches class-discriminative textual information but also effectively integrates structured knowledge with traditional textual information by capturing the structured relationships between entity sets and attribute sets. Experimental results demonstrate that AsPrompt surpasses other state-of-the-art prompt learning methods on 11 different few-shot image classification datasets, showcasing its superior performance. The code can be found at <span><span>https://github.com/SandyPrompt/AsPrompt</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103217"},"PeriodicalIF":3.4,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145095573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PDCR-SR: Enhancing facial super-resolution with multi-scale prior dictionary and region-specific contrastive regularization PDCR-SR：利用多尺度先验字典和区域特异性对比正则化增强面部超分辨率

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-13 DOI: 10.1016/j.displa.2025.103218

Zefeng Ying , Shuqi wang , Ping Shi , Xiumei Jia

引用次数: 0

Can different contexts shape the perception of a product? A study using eye-tracking in virtual environments 不同的环境能塑造产品的感知吗？一项在虚拟环境中使用眼球追踪的研究

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-13 DOI: 10.1016/j.displa.2025.103222

Francisco Felip-Miralles, Julia Galán Serrano, Almudena Palacios-Ibáñez

{"title":"Can different contexts shape the perception of a product? A study using eye-tracking in virtual environments","authors":"Francisco Felip-Miralles, Julia Galán Serrano, Almudena Palacios-Ibáñez","doi":"10.1016/j.displa.2025.103222","DOIUrl":"10.1016/j.displa.2025.103222","url":null,"abstract":"<div><div>Virtual reality (VR) environments offer immersive experiences that improve products presentation and evaluation by allowing realistic representations and a more accurate interaction. Advances in both hardware and software have made this tool popular. It also improves visual quality for incorporating functions like eye tracking and enables user behaviour to be analysed in more depth. Despite all this favouring its application while evaluating products, it is still necessary to investigate how different factors influence perceptions of virtual prototypes (VP) to make the most of the advantages of VR. The present research uses three case studies to explore how a context (neutral, natural, urban) impacts evaluations of product characteristics, emotional response, trust in response, observation patterns, behaviour in virtual environments, cybersickness levels and feeling of presence. The results reveal that the context does not significantly influence product evaluation, but impacts emotional response (more positive on the natural vs. urban background) and form of observation (VP is observed longer when presented on a neutral background). These findings open up new opportunities to optimise products design and evaluation. However, future research should consider other variables like users’ age and other product categories.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103222"},"PeriodicalIF":3.4,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Uncertainty-aware weakly supervised temporal action localization with knowledge selection 基于知识选择的不确定性感知弱监督时间动作定位

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-12 DOI: 10.1016/j.displa.2025.103215

Huanqing Yan , Bo Sun , Jun He

{"title":"Uncertainty-aware weakly supervised temporal action localization with knowledge selection","authors":"Huanqing Yan , Bo Sun , Jun He","doi":"10.1016/j.displa.2025.103215","DOIUrl":"10.1016/j.displa.2025.103215","url":null,"abstract":"<div><div>Weakly-Supervised Temporal Action Localization (WS-TAL) aims to localize actions in untrimmed videos using only video-level labels. The core challenge is the lack of fine-grained annotations, which leads to high prediction uncertainty and confusion between actions and background. To address this, we propose an <em>Uncertainty-Aware and Knowledge-Selection</em> (UAKS) approach. Specifically, we integrate two uncertainty estimation strategies to cooperatively optimize the model and leverage uncertainty to guide external knowledge selection. First, evidential learning estimates model uncertainty, generating more confident predictions via regularization. Second, probabilistic distribution learning captures data uncertainty. Both uncertainties jointly guide model optimization. Additionally, uncertainty-driven knowledge selection enables the efficient utilization of external knowledge under weak supervision. Experiments show that our method improves accuracy and robustness, with 12.9% and 2% accuracy improvements on THUMOS and ActivityNet v1.3 datasets respectively, demonstrating the potential of uncertainty modeling in WS-TAL.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103215"},"PeriodicalIF":3.4,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145095569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lightweight context-awareness hybrid-attention network for waste segmentation in cluttered scenes 用于杂乱场景中垃圾分割的轻量级上下文感知混合关注网络

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-12 DOI: 10.1016/j.displa.2025.103213

Yangke Li, Xinman Zhang

{"title":"Lightweight context-awareness hybrid-attention network for waste segmentation in cluttered scenes","authors":"Yangke Li, Xinman Zhang","doi":"10.1016/j.displa.2025.103213","DOIUrl":"10.1016/j.displa.2025.103213","url":null,"abstract":"<div><div>With the acceleration of urbanization, municipal solid waste is increasing at an alarming rate, posing a significant obstacle to achieving sustainable development. On the one hand, improper disposal of hazardous waste causes environmental pollution. On the other hand, inefficient sorting of recyclable waste results in resource waste. Therefore, automatic waste sorting systems based on computer vision have received more attention. To achieve waste segmentation in a cluttered industrial environment, this paper proposes a lightweight context-awareness hybrid-attention network, which is suitable for industrial terminal devices with limited resources. Specifically, we introduce an efficient spatial cascade module based on the multi-branch architecture, which can extract richer spatial features under different receptive fields. In addition, we use a plug-and-play feature enhancement module based on the Transformer architecture, which can effectively model long-range dependencies and enhance important information. At the same time, we use the channel shuffle operation to achieve information exchange between different groups. To fuse detailed information and semantic features, we design a novel semantic fusion module. It not only uses a spatial awareness module to extract multi-scale features, but also uses a channel awareness module to enhance critical features. Experimental results show that our model outperforms other methods. It not only achieves satisfactory segmentation results, but also has fewer model parameters.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103213"},"PeriodicalIF":3.4,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thermal turbulence mitigation in underwater images of nuclear fuel assemblies 核燃料组件水下图像中的热湍流缓解

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-11 DOI: 10.1016/j.displa.2025.103186

Lei Li , Mohan He , Wenjun Ren , Hengjian Gao , Shangqing Huang , Shukun Wu , Lei Fan , Hao Chen , Kaiwei Zhang

{"title":"Thermal turbulence mitigation in underwater images of nuclear fuel assemblies","authors":"Lei Li , Mohan He , Wenjun Ren , Hengjian Gao , Shangqing Huang , Shukun Wu , Lei Fan , Hao Chen , Kaiwei Zhang","doi":"10.1016/j.displa.2025.103186","DOIUrl":"10.1016/j.displa.2025.103186","url":null,"abstract":"<div><div>Underwater imaging of nuclear fuel assemblies is crucial for inspection, monitoring, and safety evaluation in nuclear facilities. However, thermal turbulence caused by temperature gradients and convective flows in the cooling water can lead to severe visual degradation, including geometric distortions and blurring. To facilitate research in this underexplored area, we construct a dedicated dataset that captures thermal turbulence in underwater nuclear fuel assembly imaging. The dataset contains multi-frame sequences of turbulence-degraded images, along with corresponding ground truth images captured under still-water conditions. Building upon this dataset, we propose a novel multi-frame turbulence removal network that exploits temporal redundancy and motion cues for effective restoration. The proposed architecture integrates five key components: a feature extraction backbone for spatial encoding, a temporal self-attention block to capture long-range inter-frame dependencies, a bidirectional flow-guided propagation module, an optical flow-based warping mechanism for spatial alignment, and a fusion-reconstruction head for generating high-quality reference frames. Extensive experiments on the proposed dataset demonstrate that our method achieves superior performance over existing baselines, particularly in scenarios involving complex turbulence dynamics and non-rigid motion. The proposed framework provides a robust solution for visual enhancement in thermally dynamic underwater environments encountered in nuclear engineering applications.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103186"},"PeriodicalIF":3.4,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From simulation to reality: robust image quality assessment and calibration error compensation in 3D display systems 从仿真到现实：三维显示系统的鲁棒图像质量评估和校准误差补偿

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-09 DOI: 10.1016/j.displa.2025.103216

Jun Xu , Sihong Zhai , Lei Zhao

{"title":"From simulation to reality: robust image quality assessment and calibration error compensation in 3D display systems","authors":"Jun Xu , Sihong Zhai , Lei Zhao","doi":"10.1016/j.displa.2025.103216","DOIUrl":"10.1016/j.displa.2025.103216","url":null,"abstract":"<div><div>Objective image quality assessment metrics (IQAs) play a critical role in both 2D and 3D display technologies. However, existing studies largely rely on open-source databases or simulated images, with limited empirical evaluations involving actual 3D image comparisons. Moreover, little research has explored the potential of IQAs to assist in correcting calibration errors in 3D display systems. In this study, we apply a range of widely used 2D IQAs to both simulated and real-world 3D image quality evaluations. Six representative metrics—selected based on their performance, computational efficiency, and industry relevance over the past two decades—are employed to assess image quality in 3D displays. By deliberately introducing deviations into the calibration parameters, we analyze the impact on perceived image quality and demonstrate that IQAs can effectively detect and compensate for minor calibration errors in 3D systems. Simulation and experimental results show that traditional metrics such as PSNR and SSIM underperform, while CW-SSIM and GMSD provide moderate results. In contrast, FISM and MDSI exhibit superior performance and robustness. These findings support the use of objective IQAs as a practical tool for assisting in the calibration and performance optimization of glasses-free 3D display devices.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103216"},"PeriodicalIF":3.4,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145095571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BFL-SE: Blockchain federated learning with secure and effective weight-assignment model aggregation BFL-SE：安全有效的权重分配模型聚合的区块链联邦学习

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-08 DOI: 10.1016/j.displa.2025.103210

Yingli Peng , Gang Yao , Zijie Zhao , Chenpei Wang , Xinyu Ruan , Hongjian Shi , Ruhui Ma

{"title":"BFL-SE: Blockchain federated learning with secure and effective weight-assignment model aggregation","authors":"Yingli Peng , Gang Yao , Zijie Zhao , Chenpei Wang , Xinyu Ruan , Hongjian Shi , Ruhui Ma","doi":"10.1016/j.displa.2025.103210","DOIUrl":"10.1016/j.displa.2025.103210","url":null,"abstract":"<div><div>With the proliferation of interactive displays in edge–cloud environments, including emerging AR/VR visualization platforms, ensuring secure visual data processing while maintaining real-time responsiveness has become a critical requirement. Federated learning emerges as a new way of edge–cloud computing framework to handle privacy and security issues in display-centric edge computing. However, federated learning still suffers from problems such as over-reliance on central servers and the tampering of models. Blockchain technology provides decentralized and tamper-proof ability in the field of finance and has its potential in edge–cloud computing. In this paper, we propose a framework BFL-SE that combines blockchain and federated learning. We design several modules to further improve the framework’s security and efficiency. For security, we integrate FLTrust into our proposed framework and compute the trust scores of the clients to filter out malicious clients. For efficiency, we predict the client’s future model loss reductions using the client’s historical loss values to identify clients with better performance. The trust scores and the loss predictions constitute the aggregation weights. The final obtained global model is uploaded to the blockchain. The experiment results show that our framework balances the security and efficiency of the FL process. The model accuracies under label parameter attacks are all greater than 85%, and the convergence is faster than the baselines.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103210"},"PeriodicalIF":3.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145046153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Beyond siloed aggregation: An adaptive federated reinforcement learning model with multi-level knowledge distillation against evolving financial fraud 超越孤立聚合：针对不断演变的财务欺诈的多层次知识蒸馏的自适应联邦强化学习模型

IF 3.4 2区工程技术

Displays Pub Date : 2025-09-08 DOI: 10.1016/j.displa.2025.103205

Nana Zhang , Qin Li , Kun Zhu , Dandan Zhu

{"title":"Beyond siloed aggregation: An adaptive federated reinforcement learning model with multi-level knowledge distillation against evolving financial fraud","authors":"Nana Zhang , Qin Li , Kun Zhu , Dandan Zhu","doi":"10.1016/j.displa.2025.103205","DOIUrl":"10.1016/j.displa.2025.103205","url":null,"abstract":"<div><div>Credit card fraud detection (CCFD) is increasingly challenged by extreme class imbalance, non-IID data distributions across institutions, and rapidly evolving attack patterns. To address these issues, we present BSAFD, an adaptive federated reinforcement learning model with multi-level knowledge distillation in financial fraud detection, combining four synergistic components: a kernel-guided adversarial representation learning module that uses a compact encoder–decoder backbone with adaptive kernel sampling and adversarial augmentation to synthesize high-quality minority-class transactions and produce robust embeddings; hierarchical multi-level knowledge distillation that aligns each client’s local classifier with the global model via logit-level soft labels and feature-relation alignment to transfer output confidence and preserve inter-sample geometry; PPO-based federated reinforcement learning that constrains local updates through clipped likelihood ratios to stabilize asynchronous gradient aggregation across heterogeneous participants; and label-driven federated fusion that groups clients by fraud-rate profiles and fuses their distilled feature representations into a unified classifier. Extensive experiments on six real-world fraud datasets demonstrate that BSAFD consistently outperforms ten state-of-the-art baselines in AUC, F1 score, and average precision.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"91 ","pages":"Article 103205"},"PeriodicalIF":3.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0