检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Shilv Cai Xiaoguo Liang Shuning Cao Luxin Yan Sheng Zhong Liqun Chen Xu Zou Huazhong University of Science and Technology China National Key Laboratory of Multispectral Information Intelligent Processing Technology China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Image compression and denoising represent fundamental challenges in image processing with many real-world applications. To address practical demands, current solutions can be categorized into two main strategies: 1) sequential method; and 2) joint method. However, sequential methods have the disadvantage of error accumulation as there is information loss between multiple individual models. Recently, the academic community began to make some attempts to tackle this problem through end-to-end joint methods. Most of them ignore that different regions of noisy images have different characteristics. To solve these problems, in this paper, our proposed signal-to-noise ratio (SNR) aware joint solution exploits local and non-local features for image compression and denoising simultaneously. We design an end-to-end trainable network, which includes the main encoder branch, the guidance branch, and the signal-to-noise ratio (SNR) aware branch. We conducted extensive experiments on both synthetic and real-world datasets, demonstrating that our joint solution outperforms existing state-of-the-art methods.

关键词： Image coding Noise reduction Decoding Noise measurement Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Parallel Gaussian Homotopy Approach for Zeroth-Order Optimization

An Adaptive Parallel Gaussian Homotopy Approach for Zeroth-O...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Bingyi Zhou Guoyou Wang National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The Gaussian homotopy method is a classical optimization approach for solving nonconvex problems. It applies Gaussian smoothing to a given problem, using varying smoothing factors to generate a series of proxy problems that are easier to solve, subsequently addressing them gradually from simpler to more complex ones. Traditional Gaussian homotopy methods typically utilize a predefined sequence or parameter to update a single smoothing factor serially. However, this sequential updating process is inefficient and unsuitable for parallel homotopy pipelines. Moreover, the utilization of predefined sequences or parameters leads to a lack of adaptability. To address the abovementioned challenges, we propose an adaptive parallel Gaussian homotopy optimization method. Initially, we introduce an adaptive model called Scaling. This model is formulated as a scaler that concurrently adjusts multiple smoothing factors, with each factor aligning to a homotopy level. It can be integrated easily into serial and parallel homotopy pipelines. Furthermore, we establish a collaborative training regimen to jointly train the Scaling model and a parallel homotopy model, named continuation path learning (CPL) [1] model. Throughout the training process, the Scaling model furnishes CPL with multiple scaled smoothing factors and updates CPL implicitly. Extensive experiments demonstrate that the proposed Gaussian homotopy approach performs competitively.

关键词： Training Adaptation models Smoothing methods Pipelines Optimization methods Collaboration Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Label Semantic Dynamic Guidance Network for Remote Sensing Image Scene Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Chai, Borui Zhao, Tianming Yang, Runou Zhang, Nan Tian, Tian Tian, Jinwen Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Wuhan430074 China

The remote sensing image scene classification continues to face significant challenges due to high intraclass diversity and interclass similarity. Existing methods mainly use semantic associations between images to establish deep semantic associations between classes, ignoring the rich high-level semantic knowledge contained in the label text. This high-level information are especially valuable for distinguishing between confusing categories, as it enables the model to capture both similarity and distinctive features effectively. In this article, we introduce a novel approach that incorporates label semantic information and proposes a plug-and-play framework to guide classification model learning of intraclass and interclass relationships. Specifically, our framework includes a dynamic soft label module (DSLM), which uses textual semantics to facilitate classification model learning of interclass relationships via soft labels at the target level. In addition, we design a coarse-to-fine contrastive module (CFCM) to integrate textual semantics into contrastive learning, guiding the model in capturing intraclass and interclass relationships at the feature level. Our framework is compatible with both convolutional neural network (CNN)-based and vision transformer (ViT)-based classification architectures and is employed solely during training to minimize computational overhead. Experimental results on four datasets validate the effectiveness of our approach. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

POWERFUL LOSSY COMPRESSION FOR NOISY IMAGES

arXiv

引用

arXiv 2024年

作者： Cai, Shilv Liang, Xiaoguo Cao, Shuning Yan, Luxin Zhong, Sheng Chen, Liqun Zou, Xu Huazhong University of Science and Technology China National Key Laboratory of Multispectral Information Intelligent Processing Technology China

Image compression and denoising represent fundamental challenges in image processing with many real-world applications. To address practical demands, current solutions can be categorized into two main strategies: 1) sequential method;and 2) joint method. However, sequential methods have the disadvantage of error accumulation as there is information loss between multiple individual models. Recently, the academic community began to make some attempts to tackle this problem through end-to-end joint methods. Most of them ignore that different regions of noisy images have different characteristics. To solve these problems, in this paper, our proposed signal-to-noise ratio (SNR) aware joint solution exploits local and non-local features for image compression and denoising simultaneously. We design an end-to-end trainable network, which includes the main encoder branch, the guidance branch, and the signal-to-noise ratio (SNR) aware branch. We conducted extensive experiments on both synthetic and real-world datasets, demonstrating that our joint solution outperforms existing state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Federated Stochastic Primal-Dual Learning for Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 17034-17050页

作者： Li, Yiwei Wang, Shuai Chang, Tsung-Hui Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China The Chinese University of Hong Kong Shenzhen School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning (FL) has the potential to empower Internet-of-Vehicles (IoV) networks by enabling smart vehicles (SVs) to participate in the learning process under the orchestration of a vehicular service provider while keeping data locally. In this paper, we propose a novel federated stochastic primal-dual algorithm with differential privacy (FedSPD-DP) to ensure robust privacy protection for FL based IoV (FL-IoV) systems. The FedSPD-DP algorithm leverages multiple steps of local stochastic gradient descent (SGD) and partial client participation (PCP) to improve communication efficiency while incorporating differential privacy (DP) to ensure privacy protection. Our theoretical analysis explores the impact of these strategies on learning performance. Specifically, we demonstrate that the data sampling strategy and PCP enhance data privacy, while a larger number of local SGD steps may increase privacy leakage, revealing a non-trivial tradeoff between communication efficiency and privacy protection. Extensive experiments on real-world data validate the effectiveness of the proposed algorithm, showing superior performance compared to state-of-the-art FL algorithms, and confirming the analytical results and properties. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Efficient dynamic fusion for multispectral pedestrian detection 12

Efficient dynamic fusion for multispectral pedestrian detect...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Cao, Anqi Li, Haipeng Yang, Jian Mi, Xiaofei Chen, Zhong State Key Laboratory for Multispectral Information Processing Technology Huazhong University of Science and Technology Wuhan Hubei China Beijing Aerospace Automatic Control Institute Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

When in an environment with insufficient light, RGB images cannot provide clear pedestrian information, while multispectral thermal imaging can provide accurate positioning information. Therefore, multispectral object detection is more reliable and robust in the open world. Most fusion methods for existing multispectral object detection are static, that is, after the network is trained, all the modalities of each piece of data are input into the network to perform static inference. However, when the light is good enough or the light is very dark, multi-spectral input will bring unnecessary noise interference and computational redundancy. Therefore, a dynamic fusion network (EDFNet) is proposed to selectively fuse RGB and thermal data, so that the network can efficiently perform multispectral fusion and improve the accuracy of object detection. The gating function included in the fusion network is able to perform modality-level decisions based on multimodal features, enabling dynamic inference on data. The Extensive experiments on multiple datasets demonstrate that the proposed fusion method can reduce the computation costs and obtain comparable detection performance. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Operando chemo-mechanical evolution in LiNi0.8Co0.1Mn0.1O2 cathodes

引用

national science Review 2024年第9期11卷 253-263页

作者： Yi Zhang Shuaipeng Hao Fei Pei Xiangpeng Xiao Chang Lu Xing Lin Zhe Li Haijin Ji Yue Shen Lixia Yuan Zhen Li Yunhui Huang State Key Laboratory of Material Processing and Die & Mould Technology School of Materials Science and EngineeringHuazhong University of Science and Technology School of Optical and Electronic Information National Engineering Laboratory for Next Generation Internet Access SystemWuhan National Laboratory for OptoelectronicsHuazhong University of Science and Technology Gatan Inc.& EDAX LLC. AMETEK Commercial Enterprise (Shanghai)Co. Ltd.Pilot Free Trade Zone Department of Physics The Chinese University of Hong Kong

Ni-rich LiNixCoyMnzO2（NCMxyz,x+y+z=1,x≥0.8） layered oxide materials are considered the main cathode materials for high-energy-density Li-ion ***,the endless cracking of polycrystalline NCM materials caused by stress accelerates the loss of active materials and electrolyte decomposition,limiting the cycle ***,understanding the chemo-mechanical evolution during（de）lithiation of NCM materials is crucial to performance *** this work,an optical fiber with με resolution is designed to in operando detect the stress evolution of a polycrystalline LiNi0.8Co0.1Mn0.1O2（P-NCM811） cathode during *** integrating the sensor inside the cathode,the stress variation of P-NCM811 is completely transferred to the optical *** find that the anisotropy of primary particles leads to the appearance of structural stress,inducing the formation of microcracks in polycrystalline particles,which is the main reason for capacity *** isotropy of primary particles reduces the structural stress of polycrystalline particles,eliminating the generation of ***,the P-NCM811 with an ordered arrangement structure delivered high electrochemical performance with capacity retention of 82% over 500 *** work provides a brand-new perspective with regard to understanding the operando chemo-mechanical evolution of NCM materials during battery operation,and guides the design of electrode materials for rechargeable batteries.

关键词： Ni-rich layered oxide cathode in operando stress monitoring polycrystalline chemo-mechanical evolution

来源：评论

学校读者我要写书评

暂无评论

Anti-interference object detection algorithm based on spatio-Temporal behavior perception 12

Anti-interference object detection algorithm based on spatio...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Chen, Guo Han, Peng Mei, Jianwei Zuo, Zhengrong School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan Hubei China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

In a military scenario, targets release decoy projectiles to achieve cover, then escape, evading the attack range of the guidance system. Therefore, recognizing target behaviors such as releasing decoys, escaping, and maneuvering, and locating the spatial position and behavior of the target can provide richer information for the precise targeting of the guidance system. Based on the behaviors of both the target and decoy, a behavioraware anti-interference algorithm is proposed. The core idea of this method is to link event recognition with spatio-Temporal action localization tasks. It extracts spatio-Temporal features of consecutive frames through a 3D backbone network and utilizes a 2D backbone network with a feature pyramid to extract spatial features at different levels of key frames for behavior detection at different scales. Additionally, a context extraction network is introduced in the key frames to achieve global context awareness, improving the accuracy of event recognition. Taking into account the correlation between spatial information, temporal information, and contextual information, this paper introduces channel attention mechanisms to fuse various feature components. Simultaneously, a non-local attention module is incorporated into the 3D backbone network to enhance the understanding of global content and the connection between different frames. Experimental results demonstrate that the proposed algorithm outperforms other algorithms, achieving a frame mean Average Precision (mAP) of 92.69% on our anti-interference dataset,enabling better resistance to interference. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Improving ECAPA-TDNN Performance with Coordinate Attention

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-7页

作者： Liu, Shuanghong Song, Zhida He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The current mainstream networks, such as squeeze and excitation residual neural network (SE-ResNet) and emphasized channel attention, propagation and aggregation based time delay neural network (ECAPA-TDNN), enhance the capability of speaker embedding extractors to extract more discriminative speaker embeddings by incorporating squeeze and excitation (SE) attention within the convolutional blocks. However, the SE attention focuses solely on encoding inter-channel information, overlooking the importance of spatial positional information and time-frequency information, which are crucial for the model’s performance. In this paper, we first experimentally compare the effectiveness of several mainstream attention mechanisms in the computer vision domain for the ECAPA-TDNN model. Next, we focus on the substantial improvements that coordinate attention (CA) brings to the ECAPA-TDNN model. The introduction of CA can help the model embed time-frequency information into the channel representation. Even without using AS-Norm, our proposed model achieves relative reductions of about 5.3% equal error rate (EER) and 5.5% minimum detection cost function (minDCF) on both the Voxceleb-O and Voxceleb-H test sets compared to the ECAPA-TDNN baseline model. In addition, the EER is relatively reduced by 9.46% on the CN-Celeb1 test set. This result strongly demonstrates that the CA module can effectively improve the generalization ability of the ECAPA-TDNN model. © Shanghai Jiao Tong University 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A Valuable and Low-Budget Process Scheme of Equivalized 1 nm technology Node Based on 2D Materials

引用

Nano-Micro Letters 2025年第8期17卷 294-305页

作者： Yang Shen Zhejia Zhang Zhujun Yao Mengge Jin Jintian Gao Yuhan Zhao Wenzhong Bao Yabin Sun He Tian College of Integrated Circuit Science and Engineering Shanghai Key Laboratory of Multidimensional Information ProcessingEast China Normal UniversityShanghai 200241People’s Republic of China Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijing 100084People’s Republic of China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433People’s Republic of China Shaoxin Laboratory Shaoxing 312000People’s Republic of China

Emerging two-dimensional(2D)semiconductors are among the most promising materials for ultra-scaled transistors due to their intrinsic atomic-level *** the stacking process advances,the complexity and cost of nanosheet field-effect transistors(NSFETs)and complementary FET(CFET)continue to *** 1 nm technology node is going to be based on Si-CFET process according to international roadmap for devices and systems(IRDS)(2022,https://***/),but not publicly confirmed,indicating that more possibilities still *** miniaturization advantage of 2D semiconductors motivates us to explore their potential for reducing process costs while matching the performance of next-generation nodes in terms of area,power consumption and *** this study,a comprehensive framework is built.A set of MoS2 NSFETs were designed and fabricated to extract the key parameters and *** then for benchmarking,the sizes of 2D-NSFET are scaled to a extent that both of the Si-CFET and 2D-NSFET have the same average device *** these conditions,the frequency of ultra-scaled 2D-NSFET is found to improve by 36%at a fixed power *** work verifies the feasibility of replacing silicon-based CFETs of 1 nm node with 2D-NSFETs and proposes a 2D technology solution for 1 nm nodes,i.e.,“2D eq 1 nm”*** the same time,thanks to the lower characteristic length of 2D semiconductors,the miniaturized 2D-NSFET achieves a 28%frequency increase at a fixed power ***,developing a standard cell library,these devices obtain a similar trend in 16-bit RISC-V *** work quantifies and highlights the advantages of 2D semiconductors in advanced nodes,offering new possibilities for the application of 2D semiconductors in high-speed and low-power integrated circuits.

关键词： Two-dimensional semiconductors 1 nm technology node Nanosheet field-effect transistors Complementary field-effect transistors Horizontal scaling

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：