检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年

作者： Yang, Ziyuan Huangfu, Huijie Ran, Maosong Wang, Zhiwen Yu, Hui Sun, Mengyu Zhang, Yi Sichuan University College of Computer Science Chengdu610065 China Sichuan University Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Sichuan University School of Cyber Science and Engineering Chengdu610065 China

Deep learning (DL) has made significant advancements in tomographic imaging, particularly in low-dose computed tomography (LDCT) denoising. A recent trend involves servers training powerful models with enormous self-collected data and providing application programming interfaces (APIs) for users, such as Chat-GPT. To avoid model leakage, users are required to upload their data to the server. This approach is particularly advantageous for devices with limited computational capabilities, as it offloads computation to the server, easing the workload on the devices themselves. However, this way raises public concerns about the privacy disclosure risk. Hence, to alleviate related concerns, we propose to directly denoise LDCT in the encrypted domain to achieve privacy-preserving cloud services without exposing private data to the server. Concretely, we employ homomorphic encryption to encrypt private LDCT, which is then transferred to the server model trained with plaintext LDCT for further denoising. Since fundamental DL operations, such as convolution and linear transformation, cannot be directly used in the encrypted domain, we transform the fundamental mathematic operations in the plaintext domain into the operations in the encrypted domain. Moreover, we present two interactive frameworks for linear and nonlinear models, both of which can achieve lossless operating. In this way, the proposed methods can achieve two merits, the data privacy is well protected and the server model is free from the risk of model leakage. Moreover, we provide theoretical proof to validate the lossless property of our framework. Finally, experiments were conducted to demonstrate that the transferred contents are well protected and cannot be reconstructed.1 © 2020 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

TVG: A Training-free Transition Video Generation Method with Diffusion Models

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhang, Rui Chen, Yaosen Liu, Yuegen Wang, Wei Wen, Xuming Wang, Hongxia Sichuan University School of Cyber Science and Engineering Chengdu610065 China Ministry of Education Key Laboratory of Data Protection and Intelligent Management Sichuan University China Sobey Media Intelligence Laboratory Chengdu China University of Electronic Science and Technology of China Sichuan Chengdu611731 China

Transition videos play a crucial role in media production, enhancing the flow and coherence of visual narratives. Traditional methods like morphing often lack artistic appeal and require specialized skills, limiting their effectiveness. Recent advances in diffusion model-based video generation offer new possibilities for creating transitions but face challenges such as poor inter-frame relationship modeling and abrupt content changes. We propose a novel training-free Transition Video Generation (TVG) approach using video-level diffusion models that addresses these limitations without additional training. Our method leverages Gaussian Process Regression (GPR) to model latent representations, ensuring smooth and dynamic transitions between frames. Additionally, we introduce interpolation-based conditional controls and a Frequency-aware Bidirectional Fusion (FBiF) architecture to enhance temporal control and transition reliability. Evaluations of benchmark datasets and custom image pairs demonstrate the effectiveness of our approach in generating high-quality smooth transition videos. The project is provided in https://***/***. © 2025 IEEE. All rights reserved.

关键词： Diffusion models training-free transition video generation

来源：评论

学校读者我要写书评

暂无评论

DMSACNN: Deep Multiscale Attentional Convolutional Neural Network for EEG-Based Motor Decoding

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Liu, Ke Xing, Xin Yang, Tao Yu, Zhuliang Xiao, Bin Wang, Guoyin Wu, Wei Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing China Chongqing University of Posts and Telecommunications Key Laboratory of Cyberspace Big Data Intelligent Security of Ministry of Education China South China University of Technology College of Automation Science and Engineering Guangzhou510641 China Chongqing Normal University National Center for Applied Mathematics in Chongqing Chongqing401331 China Shanghai Jiao Tong University School of Medicine Songjiang Hospital Songjiang Research Institute Shanghai Key Laboratory of Emotions and Affective Disorders Shanghai201600 China

Objective: Accurate decoding of electroencephalogram (EEG) signals has become more significant for the brain-computer interface (BCI). Specifically, motor imagery and motor execution (MI/ME) tasks enable the control of external devices by decoding EEG signals during imagined or real movements. However, accurately decoding MI/ME signals remains a challenge due to the limited utilization of temporal information and ineffective feature selection methods. Methods: This paper introduces DMSACNN, an end-to-end deep multiscale attention convolutional neural network for MI/ME-EEG decoding. DMSACNN incorporates a deep multiscale temporal feature extraction module to capture temporal features at various levels. These features are then processed by a spatial convolutional module to extract spatial features. Finally, a local and global feature fusion attention module is utilized to combine local and global information and extract the most discriminative spatiotemporal features. Main results: DMSACNN achieves impressive accuracies of 78.20%, 96.34% and 70.90% for hold-out analysis on the BCI-IV-2a, High Gamma and OpenBMI datasets, respectively, outperforming most of the state-of-the-art methods. Conclusion and significance: These results highlight the potential of DMSACNN in robust BCI applications. Our proposed method provides a valuable solution to improve the accuracy of the MI/ME-EEG decoding, which can pave the way for more efficient and reliable BCI systems. The source code for DMSACNN is available at https://***/xingxin-99/***. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Proportional-Integral-Derivative(PID)Tuning Based on Back Propagation(BP)Neural Network for Intelligent Vehicle Motion Control

引用

Computers, Materials & Continua 2025年第5期83卷 2375-2401页

作者： Liang Zhou Qiyao Hu Xianlin Peng Qianlong Liu School of Information Science and Technology Northwest UniversityXi’an710127China State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services Northwest UniversityXi’an710127China Generative Artificial Intelligence and Mixed Reality Key Laboratory of Higher Education Institutions in Shaanxi Province Xi’an710127China Shaanxi Silk Road Cultural Heritage Digital Protection and Inheritance Collaborative Innovation Center Xi’an710127China School of Art Northwest UniversityXi’an710127China Network and Data Center Northwest UniversityXi’an710127China

Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control *** modern industrial and technological applications and collaborative edge intelligence,control systems are crucial for ensuring efficiency and ***,deficiencies in these systems can lead to significant operational *** paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control,particularly the limitations of traditional Proportional-Integral-Derivative(PID)controllers inmanaging nonlinear and time-varying dynamics,such as varying road conditions and vehicle behavior,which often result in substantial discrepancies between desired and actual speeds,as well as inefficiencies due to manual parameter *** paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation(BP)neural networks to enhance robustness and *** BP neural network is first trained to capture the nonlinear dynamic characteristics of the *** network is then combined with the PID controller to forma hybrid control *** output layer of the neural network directly adjusts the PIDparameters(k_(p),k_(i),k_(d)),optimizing performance for specific driving scenarios through self-learning and weight *** experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods,with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 ***,real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions,ensuring consistent speed maintenance and enhancing overall system performance.

关键词： PID control backpropagation neural network hybrid control nonlinear dynamic processes edge intelligence

来源：评论

学校读者我要写书评

暂无评论

A Simple Graph Contrastive Learning Framework for Short Text Classification

arXiv

引用

arXiv 2025年

作者： Liu, Yonghao Giunchiglia, Fausto Huang, Lan Li, Ximing Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University China University of Trento Italy

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Mshf-Yolo:Cotton Growth Detection Algorithm Integrated Multi-Semantic and High-Frequency Features

SSRN

引用

SSRN 2025年

作者： Luo, Jiahuan Wu, Qunyong Wang, Yuhang Zhou, Zhan Zhuo, Zhihao Guo, Henyu Fuzhou University Fujian Fuzhou350128 China Key Laboratory of Spatial Data Mining and Information Sharing the Ministry of Education Fuzhou University Fujian Fuzhou350128 China

Cotton growth monitoring is a crucial method for achieving precise management of cotton. Currently, deeplearning-based object detection models have been widely applied in cotton detection. However, existingmodels often struggle to achieve good detection results when facing challenges such as complex environments,occlusion and low contrast. To address these issues, this paper proposes a precise MSHF-YOLO based on theYOLOv8 algorithm. In this network, we introduce Multi-Semantic Spatial and Channel Attention (MSCA)into the backbone, and the upsampling and downsampling modules in the network’s neck are replacedwith the DySample and Adaptive Wavelet Down (AWD) modules to reduce the loss of high-frequencyfeatures. Finally, to further emphasize high-frequency features, we add a high-frequency boost module tothe detection head. The test results show that the algorithm achieves mAP@0.5 and mAP@0.75 of 86.0% and68.2%, respectively, which represents an improvement of 5.5% and 3.5% compared to the original ***, the model size is reduced by 12.5%. Therefore, this algorithm shows great potential for cottongrowth monitoring applications. © 2025, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Intrusion Anomaly Detection with Multi-transformer 6th

Intrusion Anomaly Detection with Multi-transformer

引用

6th International Conference on Blockchain and Trustworthy Systems, BlockSys 2024

作者： Ma, Mengshuai Wen, Bin Liu, Wenlong Du, Wanrong Wei, Xiaoxun Key Laboratory of Data Science and Smart Education Ministry of Education Hainan Normal University Haikou571158 China School of Information Science and Technology Hainan Normal University Haikou571158 China

ISBN: (纸本)9789819614103

With the rapid growth of network scale, more network attacks have emerged, the types of network attacks have become more diverse, and the harm they cause to users has become increasingly serious, which has challenged network intrusion detection and protection methods. In order to further improve the quality of network intrusion detection, the study proposes the Multi-Transformer method, which is based on the switchable attention mechanism. It is a detection model with higher security and greater applicability and is applied to the field of network intrusion detection. The study improves the traditional Transformer model and uses self-attention(single head), multi-head attention, and convolution attention in the attention module. At the same time, in order to improve the interpretability of the model, LIME (Local interpretable Model-Agnostic Explanations) was introduced, using Multiple public datasets for testing. The results show that the detection effect of the Multi-Transformer model is better than other machine learning methods. The proposed method is more secure and applicable, and has better anti-noise ability, which has more practical significance in complex and changeable network environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Shi, Liangtao Zhong, Bineng Liang, Qihua Hu, Xiantao Mo, Zhiyi Song, Shuxiang Ministry of Education Guangxi Normal University Key Laboratory of Education Blockchain and Intelligent Technology Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Wuzhou University School of Data Science and Software Engineering Wuzhou543002 China

Utilizing the high-level semantic information of language to compensate for the limitations of vision information is a highly regarded approach in single-object tracking. However, most existing vision-language (VL) trackers employ full-parameter fine-tuning, which can easily lead to catastrophic forgetting. Therefore, they fail to fully exploit the prior knowledge of pre-trained models from upstream tasks, resulting in unsatisfactory tracking performance. To alleviate the above problem, we propose a simple yet effective Vision-Language Tracking pipeline based on Mamba Adapter, named MAVLT, which adopts the idea of parameter-efficient fine-tuning (PEFT) to realize the interaction between vision-language modalities. This novel approach offers the following advantages: (1)The knowledge of the upstream pre-trained model is efficiently inherited by freezing its parameters. This ensures that the VL tracking framework only learns the modules for vision and language interaction, with a focus on the fusion between modalities. (2)The modal interaction between language and vision encoders is flexibly bridged in each encoder layer via proposed mamba adapter, enabling efficient interaction of visual and language information at multiple levels. Extensive experiments on five popular vision-language tracking benchmarks validate the effectiveness of the proposed MAVLT. Particularly, the MAVLT achieves 73.4% AUC score on the LaSOT benchmarks with only 0.18%(0.32M) of the total parameters updates. Code and models are available at https://***/GXNU-ZhongLab/MAVLT. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fish Counting in Sonar Images With Multi-Task Learning and Local-Global Feature Interaction

引用

IEEE Sensors Journal 2025年

作者： Wang, Yuhang Wu, Qunyong Yang, Shiyu Li, Mengmeng Wang, keyue Chen, Xuanyu Fuzhou350128 China Fuzhou University Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350128 China

Accurate fish counting is crucial for environmental monitoring and management, with sonar imaging providing a non-intrusive way to gather data in previously inaccessible underwater environments. However, the strong visual similarity between fish and noise in sonar images presents significant challenges in achieving high counting accuracy. Existing methods rely on attention maps to emphasize fish regions but do not fully capture the discriminative features between fish and noise, limiting counting accuracy. To address this, we propose the local-global multi-task transformer (LGMFormer) to enhance fish counting in sonar images. The model employs an encoder-decoder architecture, with density map regression as the primary task and multi-class semantic segmentation as an auxiliary task. By predicting multi-class segmentation maps, the shared network layers fully learn discriminative features between fish and noise. We also develop a segmentation-enhanced density head to further strengthen the connection between tasks. Within LGMFormer, the local-global feature interaction module is designed to fuse local spatial detail features with global correlation features for more precise fish counting. Additionally, a high-level feature guidance module is developed to retain more detail during the feature fusion process between the encoder and decoder. We also develop an automatic image segmentation method based on Otsu's thresholding to create multi-class segmentation labels for sonar images. Extensive experiments on a public sonar fish counting dataset demonstrate that LGMFormer outperforms state-of-the-art methods in counting accuracy, reducing the mean absolute error of count prediction by 17.6% and the false recognition rate by 42.9%. The source code will be available at https://***/camerayuhang/LGMFormer. © 2001-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Visual Reinforcement Learning via Spatial-Temporal data Augmentation

Improving Visual Reinforcement Learning via Spatial-Temporal...

引用

Consumer Electronics and Computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Jiabao Li Qingwen Hou Jie Zhang Xianzhong Chen Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

Sample efficiency has been a challenging problem in visual reinforcement learning, where agents not only learn polices but also extract meaningful state representations for decision making from images. Reinforcement Learning methods that adopt data augmentation have significantly improved sample efficiency. However, prior studies have primarily focused on spatial augmentation, which enhances data diversity but insufficiently exploits temporal information, such as historical states which is critical for time-series-dependent reinforcement learning tasks. To address this gap, we introduce a Spatial-Temporal data Augmentation (STDA) framework designed to enhance the agent's ability to learn task-relevant state representations by effectively leveraging historical state information. We evaluate our approach using the DeepMind Control Suite, and empirical results demonstrate that STDA significantly improves performance, surpassing state-of-the-art methods across a range of tasks.

关键词： Visualization Q-learning Law enforcement Decision making Training data Reinforcement learning Benchmark testing data augmentation Consumer electronics

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：