检索结果-内蒙古大学图书馆

HRAM-VITON: High-Resolution Virtual Try-On with Attention Mechanism

Computers, Materials & Continua 2025年第2期82卷 2753-2768页

作者： Yue Chen Xiaoman Liang Mugang Lin Fachao Zhang Huihuang Zhao College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002China

The objective of image-based virtual try-on is to seamlessly integrate clothing onto a target image, generating a realistic representation of the character in the specified attire. However, existing virtual try-on methods frequently encounter challenges, including misalignment between the body and clothing, noticeable artifacts, and the loss of intricate garment details. To overcome these challenges, we introduce a two-stage high-resolution virtual try-on framework that integrates an attention mechanism, comprising a garment warping stage and an image generation stage. During the garment warping stage, we incorporate a channel attention mechanism to effectively retain the critical features of the garment, addressing challenges such as the loss of patterns, colors, and other essential details commonly observed in virtual try-on images produced by existing methods. During the image generation stage, with the aim of maximizing the utilization of the information proffered by the input image, the input features undergo double sampling within the normalization procedure, thereby enhancing the detail fidelity and clothing alignment efficacy of the output image. Experimental evaluations conducted on high-resolution datasets validate the effectiveness of the proposed method. Results demonstrate significant improvements in preserving garment details, reducing artifacts, and achieving superior alignment between the clothing and body compared to baseline methods, establishing its advantage in generating realistic and high-quality virtual try-on images.

关键词： Virtual try-on attention mechanism high-resolution image generation

来源：评论

学校读者我要写书评

暂无评论

Deep semantic network for hyperspectral image classification using enhanced bifurcation and light self-Gaussian attention mechanism

引用

Journal of Applied Remote Sensing 2025年第1期19卷

作者： Wan, Xiaoqing Chen, Feng He, Yupeng Hengyang Normal University College of Computer Science and Technology Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

Convolutional neural networks (CNNs) are widely used in hyperspectral image (HSI) classification due to their strong feature extraction capabilities. Nevertheless, CNN-based classification methods face challenges in capturing deep semantic features effectively, and as the number of layers increases, computational expenses escalate significantly. In addition, spatial locations and spectral bands in HSI data have varying discriminative power. To address these challenges, we propose a novel approach, DSNet, which integrates a multiway attention mechanism with a CNN-based deep semantic network to improve HSI classification. First, we extract shallow abstract features using a module that combines 3D and 2D convolution layers, followed by transformation through a Gaussian-weighted feature tokenizer. Second, we introduce an enhanced bifurcation attention mechanism with dynamically adjustable perceptual ranges to capture spatial semantic information from both horizontal and vertical perspectives. Third, a convolutional multilayer perceptron module is employed to extract high-level feature representations in both spatial and spectral dimensions, which are then refined by a light self-Gaussian attention module. Finally, a linear layer is used to determine the sample labels. Experiments conducted on three publicly available hyperspectral datasets illustrate that the proposed DSNet achieves superior performance compared with several contemporary state-of-the-art methods, even when trained with limited samples. © 2025 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Stacked Network Method for Enhancing the Performance of Side-Channel Attacks

引用

Computers, Materials & Continua 2025年第4期83卷 1001-1022页

作者： Zhicheng Yin Lang Li Yu Ou College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application HengyangNormal UniversityHengyang421002China

The adoption of deep learning-based side-channel analysis(DL-SCA)is crucial for leak detection in secure *** previous studies have applied this method to break targets protected with *** the increasing number of studies,the problem of model *** research mainly focuses on exploring hyperparameters and network architectures,while offering limited insights into the effects of external factors on side-channel attacks,such as the number and type of *** paper proposes a Side-channel Analysis method based on a Stacking ensemble,called *** our method,multiple models are deeply *** the extended application of base models and the meta-model,Stacking-SCA effectively improves the output class probabilities of the model,leading to better ***,this method shows that the attack performance is sensitive to changes in the number of ***,five independent subsets are extracted from the original ASCAD database as multi-segment datasets,which are mutually *** method shows how these subsets are used as inputs for Stacking-SCA to enhance its attack *** experimental results show that Stacking-SCA outperforms the current state-of-the-art results on several considered datasets,significantly reducing the number of attack traces required to achieve a guessing entropy of ***,different hyperparameter sizes are adjusted to further validate the robustness of the method.

关键词： Side-channel analysis deep learning stacking ensemble learning model generalization

来源：评论

学校读者我要写书评

暂无评论

TSGFormer: temporal-aware network and spatial encoding GCN for three-dimensional human pose estimation

引用

Multimedia Systems 2025年第3期31卷 1-19页

作者： Xiao, Xinwang Zhao, Huihuang Li, Yuhang Tang, Peng Deng, Yue College of Computer Science and Technology Hengyang Normal University Hengyang421008 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hengyang421008 China

Transformer-based approaches have significantly driven recent progress in three-dimensional human pose estimation. However, existing transformer-based approaches are still deficient in capturing localized features, and they lack task-specific a priori information by obtaining queries, keys, and values through simple linear mappings. Existing methods lack effective human constraints for model training. We introduce the Spatial Encoding Graph Convolutional Network Transformer (SEGCNFormer), designed to enhance model capacity in capturing local features. In addition, we propose a Temporal-Aware Network, which generates queries, keys, and values possessing a priori knowledge of human motion, enabling the model to better understand the structural information of human poses. Finally, we leverage the knowledge of human anatomy and motion to design the Human Structural Science Loss, which performs a rationality assessment of human actions and imposes physical constraints on the generated poses. Our method outperforms existing methods on the Human3.6M dataset in both 27 and 81 sampling frames, and our predicted poses are closer to the actual poses with less error. For the existing three issues, we proposed effective methods and conducted targeted experiments, which confirmed the effectiveness of our strategies. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian boundary value methods applied to KdV-KdV systems

引用

Applied Numerical Mathematics 2025年 214卷 1-27页

作者： Luo, Qian Xiao, Aiguo Luo, Xuqiong Yan, Xiaoqiang School of Mathematics and Computational Science Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan 411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan 411105 China School of Mathematics and Statistics Changsha University of Science and Technology Changsha410114 China National Center for Applied Mathematics in Hunan Xiangtan University Hunan 411105 China

In this paper, we propose a highly accurate scheme for two KdV systems of the Boussinesq type under periodic boundary conditions. The proposed scheme combines the Fourier-Galerkin method for spatial discretization with Hamiltonian boundary value methods for time integration, ensuring the conservation of discrete mass and energy. By expanding the system in Fourier series, the equations are firstly transformed into Hamiltonian form, preserving the original Hamiltonian structure. Applying the Fourier-Galerkin method for semi-discretization in space, we obtain a large-scale system of Hamiltonian ordinary differential equations, which is then solved using a class of energy-conserving Runge-Kutta methods, known as Hamiltonian boundary value methods. The efficiency of this approach is assessed, and several numerical examples are provided to demonstrate the effectiveness of the method. © 2025 IMACS

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

引用

IEEE Transactions on Image processing 2025年 PP卷 PP页

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based crossmodel&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. © 1992-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

MCFNet: Multiscale Cross-domain Fusion Network for HSI and LiDAR Data Joint Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Song, Qiya Mo, Feng Ding, Kexin Xiao, Lin Dian, Renwei Kang, Xudong Li, Shutao Hunan Normal University School of Information Science and Engineering Hunan Changsha410081 China School of Robotics Hunan University Hunan Changsha410082 China Fujian Key Laboratory of Spatial Information Perception and Intelligent Processing Yango University China

Hyperspectral image (HSI) encompasses abundant spatial and spectral details, while Light Detection and Ranging (LiDAR) delivers precise elevation data. The amalgamation of HSI and LiDAR data significantly improves the precision of image classification. However, most methods focus solely on spatial features while neglecting frequency domain information, limiting the ability of deep models to characterize land cover. Furthermore, how to establish a sufficient interaction between different modalities is also an important issue. In this paper, we propose a novel multiscale cross-domain fusion network (MCFNet) for joint classification of HSI and LiDAR data. The main idea is that the wavelet transform can provide details at different resolutions simultaneously, supplementing spatial domain information and enriching feature representation. In addition, the multimodal fusion module (MFM) guided by HSI and the cross-domain fusion module (CDFM) strategy are developed to integrate features from diverse modalities and domains, respectively. Specifically, frequency domain features are extracted by discrete wavelet transform, and spatial domain features of the image are captured through a set of convolution operations. Then interactive fusion is performed by MFM and CDFM, and finally the integrated features are categorized using a classification module. Extensive experiments on three widely-used HSI and LiDAR datasets indicate that MCFNet outperforms the SOTA methods. © 1980-2012 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech Synthesis

Anchored Monotonic Alignment and Representation Substitution...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Wu, Ning-Qian Hu, Ya-Jun Chen, Liping Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China iFLYTEK Research iFLYTEK Co. Ltd. China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China

ISBN: (纸本)9798350368741

Spontaneous behaviors in speech pose significant challenges for speech synthesis. Existing research has not adequately addressed these behaviors, with most studies relying on specially recorded datasets. In contrast, real-world data more accurately reflects the natural, spontaneous speaking styles in everyday life and encompasses a wider range of spontaneous behaviors. However, such data is often of lower quality, and the distribution of spontaneous behaviors is highly imbalanced. In this study, we explore spontaneous speech synthesis using real-world data within the VITS2 framework. To overcome these challenges, we introduce two techniques: anchored monotonic alignment and spontaneous hidden representation substitution. Experimental results demonstrate that these methods enhance model alignment and improve the naturalness of the generated speech. Our proposed approach successfully addresses the challenge of synthesizing rare spontaneous behaviors and offers users flexible control over the synthesized speech. © 2025 IEEE.

关键词： real-world data speech synthesis spontaneous behaviors spontaneous speech synthesis VITS

来源：评论

学校读者我要写书评

暂无评论

Colocalized Raman and IR Spectroscopies via Vibrational-Encoded Fluorescence for Comprehensive Vibrational Analysis

引用

Journal of the American Chemical Society 2025年第19期147卷 16309-16318页

作者： Meng, Zhao-Dong Wu, Tai-Rui Zhou, Li-Ling You, En-Ming Dong, Zhi-Peng Zhang, Xia-Guang Chen, Gan-Yu Wu, De-Yin Yi, Jun Tian, Zhong-Qun School of Electronic Science and Engineering State Key Laboratory of Physical Chemistry of Solid Surfaces College of Chemistry and Chemical Engineering Fujian Key Laboratory of Ultrafast Laser Technology and Applications IKKEM Xiamen University Xiamen361005 China School of Ocean Information Engineering Fujian Provincial Key Laboratory of Oceanic Information Perception and Intelligent Processing Jimei University Xiamen361021 China Key Laboratory of Green Chemical Media and Reactions Ministry of Education School of Chemistry and Chemical Engineering Henan Normal University Xinxiang453007 China

Vibrational spectroscopy, including Raman scattering and infrared (IR) absorption, provides essential molecular fingerprint information, facilitating diverse applications, such as interfacial sensing, chemical analysis, and biomedical diagnostics. The complementary selection rules of Raman and IR spectroscopies offer distinct, yet mutually reinforcing, insights into molecular structure and dynamics. However, in dynamic or complex chemical environments, either technique alone is not capable of providing a complete and nuanced picture of molecular vibrations. Simultaneous detection of complementary vibrational modes within the same molecular group remains challenging due to wavelength discrepancies and sensitivity mismatches between Raman and IR spectroscopies. In this work, to address the gap between these spectroscopies, we developed an integrated approach based on vibrational-encoded fluorescence (VEF), in which the complementary vibrational information is respectively encoded into the different parts of fluorescence radiation: Stokes fluorescence carrying Raman information and anti-Stokes fluorescence reflecting IR information. This method employs a dual-resonant microsphere-on-mirror plasmonic structure to bridge the waveband gap, enabling the simultaneous detection of complete vibrational modes in the visible spectrum with ultrahigh sensitivity down to ∼100 molecules. Hyperspectral colocalization imaging demonstrates spatial correlations between the complementary vibrations. By careful calibration, the detection efficiency is improved by 8 orders of magnitude compared to unenhanced IR spectroscopy. This approach creates new opportunities for the precise identification of molecular vibrational information in complex chemical environments. © 2025 American Chemical Society.

关键词： Vibrational spectroscopy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：