检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Chen, Yinan Zhang, Jiangning Bi, Yali Hu, Xiaobin Hu, Teng Xue, Zhucun Yi, Ran Liu, Yong Tai, Ying College of Control Science and Engineering Zhejiang University China YouTu Lab Tencent China College of Computer and Information Science Southwest University China Department of Computer Science & Engineering Shanghai Jiao Tong University China School of Intelligence Science and Technology Nanjing University China

Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provides a comprehensive review of the latest advancements in image inversion techniques, focusing on two main paradigms: Generative Adversarial Network (GAN) inversion and diffusion model inversion. We categorize these techniques based on their optimization methods. For GAN inversion, we systematically classify existing methods into encoder-based approaches, latent optimization approaches, and hybrid approaches, analyzing their theoretical foundations, technical innovations, and practical trade-offs. For diffusion model inversion, we explore training-free strategies, fine-tuning methods, and the design of additional trainable modules, highlighting their unique advantages and limitations. Additionally, we discuss several popular downstream applications and emerging applications beyond image tasks, identifying current challenges and future research directions. By synthesizing the latest developments, this paper aims to provide researchers and practitioners with a valuable reference resource, promoting further advancements in the field of image inversion. We keep track of the latest works at https://***/RyanChenYN/ImageInversion. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Eddy Current Induced in a Finite-Length Tube by a C-Core Sensor in Arbitrary Axial Position

引用

IEEE Transactions on Magnetics 2025年第5期61卷

作者： Xiang, Yike Luo, Yao Du, Zhiye Tytko, Grzegorz Wang, Yuneng Chen, Zhichao Wuhan University State Key Laboratory of Power Grid Environmental Protection School of Electrical Engineering and Automation Wuhan430072 China Wuhan University School of Electrical Engineering and Automation Wuhan430072 China Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Gliwice44-100 Poland

The enhanced truncated region eigenfunction expansion (enhanced TREE) method is employed to derive an analytical model of a finite-length metal tube tested by a C-core coil in an arbitrary axial position. The vector potential and the coil impedance variation are calculated. To develop an efficient algorithm, the 1-D finite element method (1-D FEM), vector normalization, and Clenshaw-Curtis quadrature are integrated. To improve the computation performance of the complex eigenvalues with large imaginary parts, a coordinate transformation technique is implemented within the Arnoldi iteration. The efficacy of the proposed approach is validated by comparing the theoretical predictions with experimental results. © 1965-2012 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

A Cross-Task Transfer SAR Target Recognition Method Based on AMFFNet and IACGAN

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wan, Xunyang Du, Xiaolin Cui, Guolong Chen, Xiaolong Zheng, Jibin Yantai University School of Computer and Control Engineering Yantai264005 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Naval Aviation University Yantai264001 China Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China

Convolutional neural networks (CNN) have shown excellent capability in synthetic aperture radar (SAR) target recognition. However, obtaining sufficient training samples for improving network recognition is difficult due to the deficiency of labeled SAR image data. To tackle the problem, a cross-task transfer method for SAR target recognition is proposed in this paper, which is based on a designed attention multi-scale feature fusion network (AMFFNet) and an improved auxiliary classifier generative adversarial network (IACGAN). In this method, firstly, a data augmentation method based on you only cut twice (YOCT) is devised for expanding the training samples. Secondly, the partial weight parameters of AMFFNet are initialized by the pre-trained IACGAN discriminator. Finally, AMFFNet is fine-tuned using the training samples. Additionally, on the network structure of AMFFNet, multi-scale features are extracted by adopting a multi-scale depth separable convolution module, which allows the model to acquire more informative features. Attention mechanisms are employed in this network to enhance its ability to capture important features while reducing the effects of noise. A multi-level feature fusion structure is used to further raise the representational capability of the model. Experimental results on multiple open-source real SAR datasets show that the proposed method can achieve better recognition performance under different percentages of training data, and the effectiveness and superiority of the method are confirmed by its robustness to noise. © 1965-2011 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Accelerating Stable Matching between Workers and Spatial-Temporal Tasks for Dynamic MCS: A Stagewise Service Trading Approach

arXiv

引用

arXiv 2025年

作者： Qi, Houyi Liwang, Minghui Wang, Xianbin Fu, Liqun Hong, Yiguang Li, Li Cheng, Zhipeng School of Informatics Xiamen University Fujian China Department of Control Science and Engineering Canada Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China Department of Electrical and Computer Engineering Western University ON Canada School of Future Science and Engineering Soochow University Jiangsu China

Designing proper incentives in mobile crowdsensing (MCS) networks represents a critical mechanism in engaging distributed mobile users (workers) to contribute heterogeneous data for diverse applications (tasks). We develop a novel stagewise trading framework to reach efficient and stable matching between tasks and workers, upon considering the diversity of tasks and the dynamism of MCS networks. This framework integrates futures and spot trading stages, where in the former, we propose futures trading-driven stable matching and pre-path-planning (FT-SMP3) for long-term task-worker assignment and pre-planning of workers’ paths based on historical statistics and risk analysis. While in the latter, we investigate spot trading-driven DQN path planning and onsite worker recruitment (ST-DP2WR) mechanism to enhance workers’ and tasks’ practical utilities by facilitating temporary worker recruitment. We prove that our proposed mechanisms support crucial properties such as stability, individual rationality, competitive equilibrium, and weak Pareto optimality theoretically. Also, comprehensive evaluations confirm the satisfaction of these properties in practical network settings, demonstrating our commendable performance in terms of service quality, running time, and decision-making overheads. Copyright © 2025, The Authors. All rights reserved.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

Stroke-p2pHD: Cross-modality generation model of cerebral infarction from CT to DWI images

引用

Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical engineering 2025年第2期42卷 255-262页

作者： Wang, Qing Zhao, Xinyao Liu, Xinyue Zou, Zhimeng Nan, Haiwang Zheng, Qiang School of Computer and Control Engineering Yantai University Shandong Yantai264005 China Department of Radiology Yantaishan Hospital Shandong Yantai264001 China Department of Radiology Muping District Hospital of Traditional Chinese Medicine Shandong Yantai264100 China

Among numerous medical imaging modalities, diffusion weighted imaging (DWI) is extremely sensitive to acute ischemic stroke lesions, especially small infarcts. However, magnetic resonance imaging is time-consuming and expensive, and it is also prone to interference from metal implants. Therefore, the aim of this study is to design a medical image synthesis method based on generative adversarial network, Stroke-p2pHD, for synthesizing DWI images from computed tomography (CT). Stroke-p2pHD consisted of a generator that effectively fused local image features and global context information (Global_to_Local) and a multi-scale discriminator (M2Dis). Specifically, in the Global_to_Local generator, a fully convolutional Transformer (FCT) and a local attention module (LAM) were integrated to achieve the synthesis of detailed information such as textures and lesions in DWI images. In the M2Dis discriminator, a multi-scale convolutional network was adopted to perform the discrimination function of the input images. Meanwhile, an optimization balance with the Global_to_Local generator was ensured and the consistency of features in each layer of the M2Dis discriminator was constrained. In this study, the public Acute Ischemic Stroke Dataset (AISD) and the acute cerebral infarction dataset from Yantaishan Hospital were used to verify the performance of the Stroke-p2pHD model in synthesizing DWI based on CT. Compared with other methods, the Stroke-p2pHD model showed excellent quantitative results (mean-square error = 0.008, peak signal-to-noise ratio = 23.766, structural similarity = 0.743). At the same time, relevant experimental analyses such as computational efficiency verify that the Stroke-p2pHD model has great potential for clinical applications. © 2025 West China Hospital, Sichuan Institute of Biomedical engineering. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

On Word-of-Mouth and Private-Prior Sequential Social Learning

arXiv

引用

arXiv 2025年

作者： Da Col, Andrea Rojas, Cristian R. Krishnamurthy, Vikram The Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm100 44 Sweden The School of Electrical and Computer Engineering Cornell University IthacaNY14853 United States

— Social learning provides a fundamental framework in economics and social sciences for studying interactions among rational agents who observe each other’s actions but lack direct access to individual beliefs. This paper investigates a specific social learning paradigm known as Word-of-Mouth (WoM), where a series of agents seeks to estimate the state of a dynamical system. The first agent receives noisy measurements of the state, while each subsequent agent relies solely on a degraded version of her predecessor’s estimate. A defining feature of WoM is that the final agent’s belief is publicly broadcast and adopted by all agents, in place of their own. We analyze this setting both theoretically and through numerical simulations, showing that some agents benefit from using the public belief broadcast by the last agent, while others suffer from performance deterioration. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

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

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

Periodic-Enhanced Informer Model for Short-Term Wind Power Forecasting Using SCADA Data

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Liu, Zhao-Hua Li, Long-Wei Wei, Hua-Liang Li, Ming Lv, Ming-Yang Zhang, Ying-Jie Hunan University of Science and Technology School of Information and Electrical Engineering Xiangtan411201 China University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

Supervisory control and Data Acquisition (SCADA) systems can collect abundant information about wind farm operation and environment. To better make use of SCADA data, a periodic-enhanced informer model for short-term wind power forecasting using scada data is proposed. Firstly, to effectively filter out noise in SCADA data, a v-p curve-based method is adopted by incorporating a quartile approach to remove sparse outliers;a density-based spatial clustering of applications with noise (DBSCAN) algorithm is then employed to eliminate stacked outliers from the power curve. Secondly, a multi-feature input set selection method based on Maximization Information Coefficient is introduced to make better use of the SCADA system data by reducing the number of features. Thirdly, a Temporal Convolutional Network (TCN) is designed to extract the scalar projection of the input set, followed by fusing the local time stamp and global time stamp to build the periodic information enhanced prediction model embedding layer. Subsequently, the enhanced input set is fed into an informer model to predict future wind power. Finally, considering the multiple temporal scales structure characteristics present in the dataset, a multi-scale deep fusion module is established in the informer model to deeply integrate the features of different scales. It can simultaneously avoid the resource waste and overfitting problems caused by increasing the network depth. The experimental results, which are obtained from several deep learning methods on real SCADA data, demonstrate that the suggested approach has good predictive capability. © 2010-2012 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation

arXiv

引用

arXiv 2025年

作者： Jiang, Shiqi Yuan, Hui Li, Shuai Hamzaoui, Raouf Wang, Xu Huo, Junyan School of software Shandong University Shandong Jinan China School of Control Science and Engineering Shandong University Shandong Jinan China School of Engineering and Sustainable Development De Montfort University LeicesterLE1 9BH United Kingdom College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Telecommunications Engineering Xidian University Xi’an China

In recent years, learned image compression (LIC) methods have achieved significant performance improvements. However, obtaining a more compact latent representation and reducing the impact of quantization errors remain key challenges in the field of LIC. To address these challenges, we propose a feature extraction module, a feature refinement module, and a feature enhancement module. Our feature extraction module shuffles the pixels in the image, splits the resulting image into sub-images, and extracts coarse features from the sub-images. Our feature refinement module stacks the coarse features and uses an attention refinement block composed of concatenated three-dimensional convolution residual blocks to learn more compact latent features by exploiting correlations across channels, within sub-images (intra-sub-image correlations), and across sub-images (inter-sub-image correlations). Our feature enhancement module reduces information loss in the decoded features following quantization. We also propose a quantization error compensation module that mitigates the quantization mismatch between training and testing. Our four modules can be readily integrated into state-of-the-art LIC methods. Experiments show that combining our modules with Tiny-LIC outperforms existing LIC methods and image compression standards in terms of peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) on the Kodak dataset and the CLIC dataset. Copyright © 2025, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

CorPN: Corner Prediction Network for Visual Tracking

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Qun Zhang, Haijun Yang, Kai Dai, Wei Ma, Jianghong Liu, Yuping the Department of Computer Science Harbin Institute of Technology Shenzhen Xili University Town Shenzhen518055 China the School of Computer Science and Artificial Intelligence WuHan Textile University Wuhan430200 China the School of Information and Control Engineering Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou221116 China the School of Microelectronics Fudan University Shanghai200433 China

Object tracking is a well-established task in the field of computer vision. Despite numerous efforts over the last few decades, object tracking remains a formidable challenge, largely due to the complexity of the scenes encountered in video sequences. In line with the powerful capabilities of Transformers for object feature extraction and fusion, as well as drawing inspiration from CornerNet, this paper introduces a new Transformer-based anchor-free method designed for object tracking called CorPN (i.e., Corner Prediction Network). Specifically, a Transformer-based backbone is proposed to extract and fuse deep features in a Siamese network architecture. Furthermore, our methodology aims to emulate the intuitive cognitive process by which humans identify the bounding-box corners of objects. CorPN turns out to be a more effective and robust tracking method because it jointly leverages multi-level feature aggregation, corner prediction, and probabilistic prediction incorporated in the tracking head. In extensive evaluations on public datasets, our method achieves a state-of-the-art performance. In particular, our approach achieves an area-under-the-curve (AUC) of 85.2%, a precision score (P) of 84.5%, and a normalized precision score (Pnorm) of 89.6%, outperforming extant state-of-the-art trackers on these metrics. © 2025 IEEE. All rights reserved,

关键词： Object detection

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：