检索结果-内蒙古大学图书馆

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Zihan Deng Zhisheng Wang Shanyuan Lin Guohang He Demin Jiang Shunli Wang Ultra Precision Optoelectronic Instrument Engineering Research Institute Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Engineering University Harbin China Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China

ISBN: (数字)9798331519315

ISBN: (纸本)9798331519322

To reduce the harmful effects of radiation dose on the human body, the sparse scanning method is widely used. Recently, deep learning methods have been widely used in rather challenging reconstruction tasks such as sparse angles, and the dual domain method has a natural advantage because it can process the information in both the sine domain and the image domain. However, the existing two-domain methods do not pay enough attention to the allocation of training costs and strategies for the two domains. To solve this problem, in this paper, we design a Computation Overhead Optimization Dual-Domain network with Multi-Level Cross-Domain Connections for Sparse View CT Reconstruction. We carries out feature extraction and image recovery for projection and image respectively through two Transformer-based subnets of coding-decoding type. In particular, in the two domains, we use the multilevel cross-domain connection method to connect the coding layers of the same scale in the two subnetworks, and adopt the two-channel method for up-sampling .The experimental results on clinical data validate the effectiveness of our method and training strategy. From the subjective and objective evaluation indexes of reconstruction results, our method can outperform some of the most advanced methods in the past.

关键词： Training Deep learning Computed tomography Signal processing Transformers Resource management Speech processing Positron emission tomography Image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Self-perception Enhanced Large Language Model for 3D Region-of-Interest Captioning with Limited Data

引用

IEEE Transactions on Multimedia 2025年 27卷 2935-2948页

作者： Shi, Lu Kan, Shichao Jin, Yi Zhang, Linna Cen, Yigang Bejing Jiaotong University and the Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing100044 China Central South University School of Computer Science and Engineering Hunan Changsha0410083 China Beijing Jiaotong University Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education and the School of Computer and lnformation Technology Beijing100044 China Guizhou University School of Mechanical Engineering Guiyang550025 China

3D Region-of-Interest (RoI) Captioning involves translating a model's understanding of specific objects within a complex 3D scene into descriptive captions. Recent advancements in Large Language Models (LLMs) have shown great potential in this area. Existing methods capture the visual information from RoIs as input tokens for LLMs. However, this approach may not provide enough detailed information for LLMs to generate accurate region-specific captions. In this paper, we introduce Self-RoI, a Large Language Model with multi-modal self-perception capabilities for 3D RoI captioning. To ensure LLMs receive more precise and sufficient information, Self-RoI incorporates Implicit Textual Info. Perception to construct a multi-modal vision-language information. This module utilizes a simple mapping network to generate textual information about basic properties of RoI from vision-following response of LLMs. This textual information is then integrated with the RoI's visual representation to form a comprehensive multi-modal instruction for LLMs. Given the limited availability of 3D RoI-captioning data, we propose a two-stage training strategy to optimize Self-RoI efficiently. In the first stage, we align 3D RoI vision and caption representations. In the second stage, we focus on 3D RoI vision-caption interaction, using a disparate contrastive embedding module to improve the reliability of the implicit textual information and employing language modeling loss to ensure accurate caption generation. Our experiments demonstrate that Self-RoI significantly outperforms previous 3D RoI captioning models. Moreover, the Implicit Textual Info. Perception can be integrated into other multi-modal LLMs for performance enhancement. We will make our code available for further research. © 1999-2012 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Fed RDP: A Robust Federated Learning Framework for Multi Party Decision-Making

引用

IEEE Transactions on network and Service Management 2025年

作者： An, Jian Tang, Siyu Ping, Ruyuan Li, Ran He, Xin Jin, Xiaolong Xi’an Jiaotong University School of Computer Science and Technology China Shaanxi Province Key Laboratory of Computer Network Xi’an Jiaotong University Xi’an710049 China Xi’an Jiaotong University School of Computer Science and Technology Xi’an710049 China Henan University School of Software Kaifeng475001 China Rocket Force University of Engineering School of Combat Supporting Xi’an710000 China

In the field of intelligent manufacturing, the vast and heterogeneous nature of data across different departments poses significant challenges for collaborative decision-making. Direct data sharing often leads to severe privacy and security concerns. Although federated learning offers a promising solution, issues such as participant selection and privacy protection remain inadequately addressed. During model training, it is crucial to minimize the influence of low-quality participants and prevent the inference of sensitive information through gradient analysis, which could threaten model performance or data privacy. To address these challenges, this paper proposes a robust federated learning model, Fed-RDP, based on participant contribution evaluation and personalized differential privacy. The model leverages blockchain technology for secure data flow and storage, implemented through smart contracts. Historical parameters are submitted to evaluate contributions based on the concept of the least core, with real-time updates to reputation scores. When participants upload their local models, the scores are used as weights to aggregate and update the global model. Additionally, personalized differential noise is added to the uploaded gradients based on participant scores, preserving privacy while maximizing the utility of the data. Experimental results demonstrate that this approach effectively identifies low-quality participants, optimizes evaluation time, and protects privacy through personalized differential noise. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CGNet: Classification-Guided Multi-Task Interactive network for Hyperspectral and Multispectral Image Fusion

CGNet: Classification-Guided Multi-Task Interactive Network ...

引用

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

作者： Guohua Lv Yanlong Xu Yongbiao Gao Guixin Zhao Guotao Wang Xiangcheng Sun Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science China Shandong Key Laboratory of Ubiquitous Intelligent Computing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application (Southeast University) Ministry of Education China Beihang University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The goal of fusing hyperspectral images (HSI) and multispectral images (MSI) is to generate high-resolution hyperspectral images for downstream tasks. However, most existing methods overlook the specific requirements of these tasks, leading to a gap between the fusion process and its subsequent applications due to insufficient guidance from downstream tasks. To address this issue, we propose a classification-guided multitask interactive network (CGNet) that integrates both fusion and classification tasks into a unified framework, with two branches producing the fused image and classification results, respectively. In the fusion branch, we design a multi-level residual refinement module to efficiently integrate spatial and spectral information. Additionally, an attention-based multi-scale fusion module, incorporating both spatial and channel attention, is carefully crafted to enhance representation learning. In the classification branch, both 2-D and 3-D convolutions are employed to improve classification performance. Moreover, an information interaction module is proposed to guide the fusion task based on classification outcomes. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches on the Pavia Centre and Pavia University datasets.

关键词： Representation learning Three-dimensional displays Attention mechanisms Convolution Streaming media Multitasking Speech processing Image fusion Information exchange Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Graph Representation Learning for Microarchitecture Design Space Exploration 23

Graph Representation Learning for Microarchitecture Design S...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Xiaoling Yi Jialin Lu Xiankui Xiong Dong Xu Li Shang Fan Yang State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China and School of Microelectronics Fudan University Shanghai China ZTE Corporation China and State Key Laboratory of Mobile Network and Mobile Multimedia Technology China State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China and China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798350323481

Design optimization of modern microprocessors is a complex task due to the exponential growth of the design space. This work presents GRL-DSE, an automatic microarchitecture search framework based on graph embeddings. GRL-DSE uses graph representation learning to build a compact and continuous embedding space. Multi-objective Bayesian optimization using an ensemble surrogate model conducts microarchitecture design space exploration in the graph embedding space to efficiently and holistically optimize performance-power-area (PPA) objectives. Experimental studies on RISC-V BOOM show that GRL-DSE outperforms previous techniques by 74.59% on Pareto front quality and outperforms manual designs in terms of PPA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zram Instance Pool Framework for Adaptive Memory Compression in Resource-Sensitive Embedded Operating Systems

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Deng, Yin Xie, Guoqi Xiong, Chenglai Zhao, Sirong Ren, Wei Li, Kenli Hunan University Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan Changsha410082 China Huawei Technology Co. Ltd. Central Software Institute Guangdong Shenzhen518129 China

Memory compression can reduce the size of the inactive data in the random access memory (RAM), thereby freeing up unused space and allowing more programs to run;however, current mainstream memory compression frameworks (e.g., Zram and Zswap) and algorithms (e.g., Zstd and Lz4) do not effectively solve the problem of increased CPU utilization, causing they cannot be directly applied to the resource-sensitive embedded operating system that is sensitive to both CPU utilization and memory usage. In this study, we develop a Zram instance pool framework called ZramPool for adaptive memory compression. The framework consists of the swap space with multiple Zram instances and the adaptive Zram compression module. Through introducing linear regression analysis, the number of Zram instances can be adaptively adjusted based on the size of the compressed data, allowing Zram instances to work in parallel to match the workload. In ZramPool, we achieve two different requirements of reducing CPU utilization while keeping compression speed and increasing compression speed while keeping CPU utilization. ZramPool is deployed in the embedded Linux OS with a 8GB memory size running on the ARMv8 architecture. For the first requirement, ZramPool can reduce CPU utilization by an average of 11.42% while the compression speed only decreases by an average of 2.4%. For the second requirement, ZramPool can increase compression speed by an average of 11.71% while the CPU utilization only increases by an average of 1.9%. © 1982-2012 IEEE.

关键词： Random access storage

来源：评论

学校读者我要写书评

暂无评论

COO-DuDo: computation overhead optimization methods for dual-domain sparse-view CT reconstruction

引用

Expert Systems with Applications 2025年 286卷

作者： Deng, Zihan Wang, Zhisheng Shan, Yuanlin He, Guohang Du, Tiantian Wang, Shunli Center of Ultra-Precision Optoelectronic Instrument Engineering Harbin Institute of Technology Harbin150080 China Ministry of Industry and Information Technology Harbin150080 China Artificial Intelligence Media Computing Laboratory School of Computer Science and Technology Harbin Engineering University Harbin150080 China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronic and Information Guangxi University Nanning530000 China Faculty of Education University of Hong Kong Hong Kong

Recently, deep learning methods have shown exciting effects in Sparse-view CT reconstruction. The Dual-Domain (DuDo) deep learning method is one of the representative methods, and it can process the information in both the sinogram and image domains. However, the existing DuDo methods do not pay enough attention to the allocation of training costs and strategies for the two domains, which will result in wasted computing overhead or insufficient training in one of the two domains. In this paper, we propose a Computation-Overhead Optimization (COO) DuDo training strategy for sparse-view CT reconstruction, i.e., COO-DuDo. The training ratio of different domains is controlled by calculating their computation overhead, loss, and gradient variation of the loss. To make our COO-DuDo strategy enable sparse-view CT reconstruction better, we adopt a DuDo-network (COO-DDNet) structure based on two coding-decoding-type subnetworks. The evaluation, animal and clinical experiments have verified the effectiveness of our training strategies and methods. Our research provides a broader perspective for dual-domain image restoration tasks from the perspective of computational overhead. © 2025 Elsevier Ltd

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

E-MAEL: Efficient Multi-Cloud Data Auditing With Error Localization for IoT Consumer Devices in Metaverse

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Liu, Mingxi Fan, Kuan Lu, Ning Shi, Wenbo Alenazi, Mohammed J.F Chen, Chien-Ming Kumari, Saru Northeastern University at Qinhuangdao College of Computer Science and Engineering Northeastern University Hebei Key Laboratory of Marine Perception Network and Data Processing Shenyang China Hebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao China Northeastern University College of Computer Science and Engineering Shenyang China Northeastern University at Qinhuangdao sHebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao China Department of Computer Engineering Riyadh11451 Saudi Arabia Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing China Chaudhary Charan Singh University Department of Mathematics Uttar Pradesh Meerut India

By integrating multi-cloud (MC) storage with the "edge-to-cloud" architecture of consumer IoT, the metaverse paradigm achieves enhanced efficiency in real-time data collection and interactive virtual feedback. However, data stored across multiple clouds is vulnerable to tampering and theft due to the inherent insecurity of cloud computing, and cloud service providers, driven by economic interests, may conceal data losses. Existing data integrity auditing techniques fail to ensure prompt and reliable verification for distributed data in the MC-enabled metaverse paradigm, limiting their effectiveness in eliminating erroneous data swiftly. To address these challenges, we propose E-MAEL (Efficient Multi-cloud Data Auditing with Error Localization) for IoT devices in the metaverse. We design an MC self-auditing framework based on blockchain to eliminate audit delays caused by third-party auditors. A variable-length auditing protocol based on Schnorr is introduced, reducing computation overhead by up to 21% compared to schemes relying on bilinear pairing and RSA assumptions. We develop a single-round error localization strategy based on symmetric unbalanced block design, enabling efficient identification and removal of erroneous data while resisting collusion attacks. A dynamic reputation update strategy using convex functions is proposed, providing robust reputation management for MCs and effectively penalizing audit errors. Theoretical security analyses and experimental results demonstrate the effectiveness of EMAEL in improving computational efficiency and enhancing reliability in MC auditing systems. © 1975-2011 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Multimodal depression recognition and analysis: Facial expression and body posture changes via emotional stimuli

引用

Journal of Affective Disorders 2025年 381卷 44-54页

作者： Liu, Yang Li, Xingyun Wang, Mengqi Bi, Jianlu Lin, Shaoqin Wang, Qingxiang Yu, Yanhong Ye, Jiayu Zheng, Yunshao Endocrinology The Fifth Clinical College of Guangzhou University of Chinese Medicine Guangzhou 510095 China Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University Lanzhou 730000 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Science) Jinan 250353 China Shandong Mental Health Center Shandong University Jinan 250014 China College of Traditional Chinese Medicine Shandong University of Traditional Chinese Medicine Jinan 250355 China School of Computer Science Guangdong University of Technology Guangzhou 510006 China Endocrinology Guangdong Provincial Second Hospital of Traditional Chinese Medicine Guangzhou 510095 China

Background: Clinical studies have shown that facial expressions and body posture in depressed patients differ significantly from those of healthy individuals. Combining relevant behavioral features with artificial intelligence technology can effectively improve the efficiency of depression detection, thereby assisting doctors in early identification of patients. This study aims to develop an end-to-end multimodal recognition model combining facial expressions and body posture via deep learning techniques, enabling rapid preliminary screening of depression. Methods: We invited 146 subjects (73 in the patient group and 73 in the control group) to participate in an emotion-stimulus experiment for depression recognition. We focused on differentiating depression patients from the control group by analyzing changes in body posture and facial expressions under emotional stimuli. We first extracted images of body position and facial emotions from the video, then used a pre-trained ResNet-50 network to extract features. Additionally, we analyzed facial expression features using OpenFace for sequence analysis. Subsequently, various deep learning frameworks were combined to assess the severity of depression. Results: We found that under different stimuli, facial expression units AU04, AU07, AU10, AU12, AU17, and AU26 had significant effects in the emotion-stimulus experiment, with these features generally being negative. The decision-level fusion model based on facial expressions and body posture achieved excellent results, with the highest accuracy of 0.904 and an F1 score of 0.901. Conclusions: The experimental results suggest that depression patients exhibit predominantly negative facial expressions. This study validates the emotion-stimulus experiment, demonstrating that combining facial expressions and body posture enables accurate preliminary depression screening. © 2025 Elsevier B.V.

关键词： Body posture Depression recognition Emotional stimuli Facial expressions

来源：评论

学校读者我要写书评

暂无评论

GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge network

arXiv

引用

arXiv 2025年

作者： Xiao, Wenjing Shi, Chenglong Chen, Miaojiang Liu, Zhiquan Chen, Min Song, H. Herbert Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China School of Computer Electronics and Information Guangxi University Nanning530004 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Pazhou Laboratory Guangzhou510330 China College of Cyber Security Jinan University Guangzhou510632 China

With the exponential growth of Internet of Things (IoT) devices, edge computing (EC) is gradually playing an important role in providing cost-effective services. However, existing approaches struggle to perform well in graph-structured scenarios where user data is correlated, such as traffic flow prediction and social relationship recommender systems. In particular, graph neural network (GNN)based approaches lead to expensive server communication cost. To address this problem, we propose GraphEdge, an efficient GNN-based EC architecture. It considers the EC system of GNN tasks, where there are associations between users and it needs to take into account the task data of its neighbors when processing the tasks of a user. Specifically, the architecture first perceives the user topology and represents their data associations as a graph layout at each time step. Then the graph layout is optimized by calling our proposed hierarchical traversal graph cut algorithm (HiCut), which cuts the graph layout into multiple weakly associated subgraphs based on the aggregation characteristics of GNN, and the communication cost between different subgraphs during GNN inference is minimized. Finally, based on the optimized graph layout, our proposed deep reinforcement learning (DRL) based graph offloading algorithm (DRLGO) is executed to obtain the optimal offloading strategy for the tasks of users, the offloading strategy is subgraph-based, it tries to offload user tasks in a subgraph to the same edge server as possible while minimizing the task processing time and energy consumption of the EC system. Experimental results show the good effectiveness and dynamic adaptation of our proposed architecture and it also performs well even in dynamic scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

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：