检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Huayu Wu, Dongyue Shao, Yuanjie Sang, Nong Gao, Changxin National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance. Nevertheless, these methods still suffer from the lack of deterministic foreground-background cues, which impairs their ability to consistently identify and locate foreground targets over time and mine fine-grained details. In this paper, we present a trimap-free Object-Aware Video Matting (OAVM) framework, which can perceive different objects, enabling joint recognition of foreground objects and refinement of edge details. Specifically, we propose an Object-Guided Correction and Refinement (OGCR) module, which employs cross-frame guidance to aggregate object-level instance information into pixel-level detail features, thereby promoting their synergy. Furthermore, we design a Sequential Foreground Merging augmentation strategy to diversify sequential scenarios and enhance capacity of the network for object discrimination. Extensive experiments on recent widely used synthetic and real-world benchmarks demonstrate the state-of-the-art performance of our OAVM with only an initial coarse mask. The code and model will be available. © 2025, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

A Stronger Leakage Model Based on Conditional Generative Adversarial Networks for Correlation Power Analysis

引用

International Journal of Circuit Theory and Applications 2025年第0期

作者： Tang, Cheng Li, Lang Ou, Yu College of Computer Science and Technology Hengyang Normal University Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hengyang China

Deep learning-based side-channel attacks (DL-SCA) have attracted widespread attention in recent years, and most of the researchers are devoted to finding the optimal DL-SCA method. At the same time, traditional SCA methods have lost their luster. However, traditional attacks still have certain advantages. Compared with the DL-SCA method, they do not require cumbersome engineering of tuning DL models and hyperparameters, making them easier to implement. Correlation power analysis (CPA), as a traditional SCA method, is still widely used in various analysis scenarios and plays an important role. In CPA, the leakage model is the key to simulating the power consumption, and it decides the attack efficiency. However, the existing leakage models are designed based on theory but ignore the actual attack scene. We found that conditional generative adversarial networks (CGAN) can ideally learn the target device's leakage characteristics and real power consumption. We let CGAN pre-learn the leakage of the target device, and then make the generator as the leakage model (Formula presented.). The (Formula presented.) leakage model can characterize the leakages of the device and consider the presence of noise in the actual scenario. It can map the power consumption more realistically and accurately, which can lead to a more powerful CPA attack. In this work, three kinds of (Formula presented.) leakage models ((Formula presented.) 1, (Formula presented.) 2, and (Formula presented.) 3 leakage models) corresponding to the labels least significant bit (LSB), hamming weight (HW), and identity (ID) of CGAN are discussed. The experimental results show that the (Formula presented.) 3 leakage model has better attack performance. Compared with the ordinary HW leakage model, the number of traces needed to recover the key on the ASCAD and SAKURA-AES datasets reduced by about 38.9% and 85.9%, respectively. © 2025 John Wiley & Sons Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Underwater Image Restoration Based on Improved SwinIR Model

Underwater Image Restoration Based on Improved SwinIR Model

引用

International Conference on intelligent Control and information processing (ICICIP)

作者： Yanke Lu Fang Li Xiaonan Luo Guangxi Key Laboratory of Image and and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Center for Applied Mathematics of Guangxi (GUET) Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

Image restoration is a classic foundational visual task, aimed at recovering damaged images, such as those affected by compression, blurring, or noise, to high-definition clarity. Although current image enhancement techniques largely rely on convolutional neural networks, the efficient capabilities of Transformers demonstrated in complex visual tasks have not yet been extensively applied in the field of image restoration. This paper presents an optimized image restoration strategy based on the SwinlR model, which is applied to the task of underwater image restoration. In the shallow feature extraction phase, deep separable convolution technology is employed; while in the deep feature extraction phase, a Spatial Gated Feedforward Network (SGFN) is utilized. The experimental data suggests that the novel approach surpasses conventional techniques in effectiveness and has effectively minimized both the model's parameter quantity and computational demands.

关键词： Visualization Convolution Computational modeling Noise information processing Logic gates Feature extraction Transformers Image restoration intelligent control

来源：评论

学校读者我要写书评

暂无评论

Comments and extensions on "State-equivalent form and minimum-order compensator design for rectangular descriptor systems"

arXiv

引用

arXiv 2025年

作者： Shi, Shuo Zhang, Juan Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Mathematics and Computational Science Xiangtan University Xiangtan411105 China

This technical note presents a counterexample showing that the equivalence conditions proposed by Geng et al. (IEEE Trans. Automat. Control, 2024), which use a minimum-order compensator (MOC) to achieve desired designs, including generalized regularity or both generalized regularity and free of impulse, are sufficient but not necessary. Furthermore, revised equivalence conditions are introduced, along with an equivalence condition ensuring the closed-loop system remains generalized regular, impulse-free, and stable using MOC. Additionally, it is shown that output feedback can replace the MOC, achieving the same design without increasing dimensionality. These findings are validated through a circuit *** Codes 93B05, 93B52, 15A03 Copyright © 2025, The Authors. All rights reserved.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Deep Supervised Cone-Based Nonnegative Matrix Factorization in Image pattern Space 2nd

Deep Supervised Cone-Based Nonnegative Matrix Factorization ...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： He, Jinghui Chen, Wen-Sheng Pan, Binbin Chen, Bo School of Mathematical Sciences Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9789819619030

Deep nonnegative matrix factorization (DNMF) is a promising approach for analyzing image data at hierarchical levels, as it can reveal hierarchical nonnegative features of the data in the image pattern space. Nevertheless, most existing DNMF models are unsupervised learning methods, making the image data fall in the same cone spanned by the basis images. This limitation potentially degrades the performance of the DNMF algorithms. To overcome the same cone problem, this paper proposes a novel deep-supervised cone-based NMF (DSCNMF) method. The DSCNMF model is established according to the fact that samples from the same class are confined within the same cone, whereas data from distinct classes occupy separate cones. The optimization objective of DSCNMF seeks to minimize the volume of each cone while maximizing the distance between different cones. Furthermore, graph regularization is integrated into the proposed model to preserve the local data structure. The multiplicative update formulas are acquired using the gradient descent method, and the DSCNMF algorithm is theoretically proven to be convergent. The experimental results conducted on two publicly available facial image datasets demonstrate the effectiveness and superiority of the proposed DSCNMF method compared with several state-of-the-art DNMF algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Textured Surface Defect Detection with Image-Level Accuracy Optimization via Patch-Level Features and Simulation-Based Samples

Textured Surface Defect Detection with Image-Level Accuracy ...

引用

Algorithms, Computing and Machine Learning (CACML), Asia Conference on

作者： Fen Li Dongxiao Li Le Huang Hangrui Chen Ming Zhang Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

ISBN: (数字)9798331543143

ISBN: (纸本)9798331543150

Textured surface defect detection plays a critical role in industrial product quality monitoring. However, excessive reliance on pixel-level precision, especially when defect boundaries are unclear, can lead to more complex models, lower efficiency, and increased risk of false positives or missed detections, ultimately compromising system reliability. Additionally, challenges such as the difficulty of collecting defect samples, severe class imbalances, and high pixel-level labeling costs hinder the effectiveness of convolutional neural networks in terms of both inference speed and computational efficiency. To overcome these challenges, we propose SiamSimNet, a dual-channel Siamese network that relies on high-quality training data generated through simulation algorithms, minimizing the need for real defect samples. By incorporating locally aware patch features, the proposed method significantly improves detection accuracy and robustness, while maintaining high inference efficiency. This approach shows strong potential for real-world industrial applications.

关键词： Accuracy Costs Computational modeling Feature extraction Robustness Surface texture Computational efficiency Labeling Monitoring Defect detection

来源：评论

学校读者我要写书评

暂无评论

An enhanced sparse subset selection model based on adaptive projection distance

引用

Evolutionary Intelligence 2025年第3期18卷 1-15页

作者： Feng, Feng Gao, Erwei Zhi, Xiaobin Zhao, Yichuan School of Science and Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an710121 China School of Communication and Information Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China School of Science and Research Center for Intelligent Systems and Data Science Xi’an University of Posts and Telecommunications Xi’an710121 China Department of Mathematics and Statistics Georgia State University AtlantaGA30303 United States

Subset selection focuses on identifying representative samples from a large dataset to produce a data subset that can represent the main features of the original data and also reduce the data size in an effective way. Sparse representation theory puts emphasis on enhancing the data sparsity, while subset selection aims to reduce the data size. Sparse subset selection is an important branch of subset selection that incorporates sparse representation theory into the exploration of subset selection. Sparse modeling representative selection model has demonstrated outstanding performance in data classification and video summarization. Nonetheless, it suffers from the issue of poor typicality of the selected representatives. Although some recent works have addressed this problem to some extent by introducing the concept of clustering coding terms, most of the clustering coding terms constructed by these existing methods are implicit, and the model structure is complicated, inefficient, and difficult to be understood. To overcome these difficulties, we propose an adaptive projection distance-based sparse subset selection model. This model constructs a clustering coding item by adaptively calculating the projection distance between data. It can not only eliminate redundant and noisy features in the original data but also ensure that the selected representatives are more typical. To solve the proposed model, an efficient algorithm is developed by virtue of the alternating direction method of multipliers. Extensive experiments with comparative analysis demonstrate that the proposed model outperforms several state-of-the-art models in various tasks including subset selection, cluster analysis, classification, and face image representative selection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Haptic Compression Inspired by Embodied AI for Haptic Communications

引用

IEEE Transactions on Multimedia 2025年

作者： Lu, Hang Tan, Xinmeng Chen, Mingkai Zhang, Zhe Zhang, Xuguang Chen, Jianxin Wei, Xin Zhao, Tiesong Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Science & Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China

Haptic data compression has gradually become a key issue for emerging real-time haptic communications in Tactile Internet (TI). However, it is challenging to achieve a tradeoff between high perceptual quality and compression ratio in haptic data compression scheme. Inspired by the perspective of embodied AI, we propose a cross-modal haptic compression scheme for haptic communications to improve the perception quality on TI devices in this paper. Since multimodal fusion is routinely employed to improve the ability of system in cognition, we assume that haptic codec is guided by visual semantics to optimize parameter settings in the coding process. We first design a multi-dimensional tactile feature fusion network (MTFFN) relying on multi-head attention mechanism. The MTFFN extracts the multi-dimensional features from the material surface and maps them to infer the coding parameters. Secondly, we provide second-order difference and linear interpolation to establish an criterion for the determination of optimal codec parameters, which are customized by the material categories so as to give high robustness. Finally, the simulation results reveal that our compression scheme can efficiently make a personalized codec procedure for different materials, obtaining more than 17% improvement in terms of compression ratio with high perceptual quality at the same time. © 2025 IEEE.

关键词： Data compression ratio

来源：评论

学校读者我要写书评

暂无评论

Kernel-learning parameter prediction and evaluation in algebraic multigrid method for several PDEs

arXiv

引用

arXiv 2025年

作者： Zhang, Juan Luo, Junyue Zhang, Fangfang Yue, Xiaoqiang Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

This paper explores the application of kernel learning methods for parameter prediction and evaluation in the Algebraic Multigrid Method (AMG), focusing on several Partial Differential Equation (PDE) problems. AMG is an efficient iterative solver for large-scale sparse linear systems, particularly those derived from elliptic and parabolic PDE discretizations. However, its performance heavily relies on numerous parameters, which are often set empirically and are highly sensitive to AMG’s effectiveness. Traditional parameter optimization methods are either computationally expensive or lack theoretical support. To address this, we propose a Gaussian Process Regression (GPR)-based strategy to optimize AMG parameters and introduce evaluation metrics to assess their effectiveness. Trained on small-scale datasets, GPR predicts nearly optimal parameters, bypassing the time-consuming parameter sweeping process. We also use kernel learning techniques to build a kernel function library and determine the optimal kernel function through linear combination, enhancing prediction accuracy. In numerical experiments, we tested typical PDEs such as the constant-coefficient Poisson equation, variable-coefficient Poisson equation, diffusion equation, and Helmholtz equation. Results show that GPR-predicted parameters match grid search results in iteration counts while significantly reducing computational time. A comprehensive analysis using metrics like mean squared error, prediction interval coverage, and Bayesian information criterion confirms GPR’s efficiency and reliability. These findings validate GPR’s effectiveness in AMG parameter optimization and provide theoretical support for AMG’s practical application. © 2025, CC BY.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

Relaxing Distillation Constraints for Improved New Class Learning in Continual Semantic Segmentation

Relaxing Distillation Constraints for Improved New Class Lea...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zheng Ti Xuze Hao Renhai Chen College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Continual Semantic Segmentation (CSS) aims to continuously learn new classes while mitigating catastrophic forgetting. Existing CSS methods primarily address this challenge through knowledge distillation. While they focus on maintaining stability for old classes, this emphasis often restricts plasticity in learning new ones. In this work, we propose two plug-and-play methods to better balance stability and plasticity. First, for feature map distillation, we replace pixel-level constraints with statistical information extraction within a window, improving the learning of new classes while preserving structural integrity to overcome forgetting. Second, we use relative ranks of predictions to replace exact probabilistic values to loosen the constraints in the logit distribution of old classes. Extensive experiments demonstrate that our methods outperform state-of-the-art methods when integrating into several baselines across various CSS scenarios.

关键词： Semantic segmentation Semantics Signal processing Feature extraction Probabilistic logic information retrieval Acoustics Data mining Speech processing

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：