检索结果-内蒙古大学图书馆

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

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Safe and Reliable Diffusion Models via Subspace Projection

arXiv

引用

arXiv 2025年

作者： Chen, Huiqiang Zhu, Tianqing Wang, Linlin Yu, Xin Gao, Longxiang Zhou, Wanlei Faculty of Data Science City University of Macau China School of Computer Science University of Queensland QLD Australia Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such as copyrighted works or offensive images. While existing methods attempt to eliminate specific unwanted concepts, they often fail to ensure complete removal—allowing the concept to reappear in subtle forms. For instance, a model may successfully avoid generating images in Van Gogh’s style when explicitly prompted with "Van Gogh", yet still reproduce his signature artwork when given the prompt "Starry Night". In this paper, we propose SAFER, a novel and efficient approach for thoroughly removing target concepts from diffusion models. At a high level, SAFER is inspired by the observed low-dimensional structure of the text embedding space. The method first identifies a concept-specific subspace Sc associated with the target concept c. It then projects the prompt embeddings onto the complementary subspace of Sc, effectively erasing the concept from the generated images. Since concepts can be abstract and difficult to fully capture using natural language alone, we employ textual inversion to learn an optimized embedding of the target concept from a reference image. This enables more precise subspace estimation and enhances removal performance. Furthermore, we introduce a subspace expansion strategy to ensure comprehensive and robust concept erasure. Extensive experiments demonstrate that SAFER consistently and effectively erases unwanted concepts from diffusion models while preserving generation quality. © 2025, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

E2DAS: An Efficient Equivariant Dynamic Aggregation Saliency Model for Omnidirectional Images 27th

E2DAS: An Efficient Equivariant Dynamic Aggregation Saliency...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhang, Nana Liu, Qian Zhu, Dandan Zhu, Kun Zhai, Guangtao Yang, Xiaokang School of Computer Science and Technology Donghua University No.2999 Renmin North Road Songjiang District Shanghai201620 China Institute of AI Education Shanghai East China Normal University No.3663 Zhongshan North Road Putuo District Shanghai200333 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University No.4800 Cao’an Highway Jiading District Shanghai201804 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University No. 800 Dongchuan Road Minhang District Shanghai200240 China

ISBN: (纸本)9783031781216

Recent years have witnessed rapid progress of convolutional neural networks (CNNs) and their successful application in the task of saliency prediction for omnidirectional images (ODIs). Albeit achieving tremendous performance improvements, these CNNs-based saliency models are plagued by two major shortcomings: spatial content-agnostic and computationally intensive. Inspired by the effectiveness of equivariant network in the majority of computer vision tasks, we propose a novel efficient equivariant dynamic aggregation saliency (E2DAS) model to efficiently tackle the issue of human fixation prediction in ODIs. To be specific, our proposed model consists of an efficient equivariant module, a dynamic convolutional aggregation module, and an optimization computation module. Different from existing saliency models for ODIs, we are the first attempt to introduce an efficient equivariant dynamic convolutional aggregation operation into the saliency prediction task, which can fundamentally alleviate the projection distortion problem and can effectively learn spatial content-adaptive features. Moreover, we clearly observe a considerable decrease in the number of parameters resulting from the replacement of standard convolution with dynamic convolution aggregation. Extensive experiments on several benchmark datasets show the proposed model’s superiority over other state-of-the-art methods in terms of performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Equivariant dynamic aggregation light-weight model omnidirectional images saliency prediction spatial content-adaptive

来源：评论

学校读者我要写书评

暂无评论

Online Queue-Aware service Migration and Resource Allocation in Mobile Edge computing

引用

IEEE Transactions on Vehicular technology 2025年

作者： Du, An Jia, Jie Chen, Jian Wang, Xingwei Huang, Ming Northeastern University School of Computer Science and Engineering Engineering Research Center of Security Technology of Complex Network System Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Northeastern University School of Computer Science and Engineering Shenyang110819 China

Mobile edge computing (MEC) integrated with Network Functions Virtualization (NFV) helps run a wide range of services implemented by Virtual Network Functions (VNFs) deployed at MEC networks. This emerging paradigm offers flexible edge resource management for Internet service Providers (ISPs) and improves service satisfaction of diverse applications. However, a critical challenge lies in processing extremely unpredictable and bursty traffic flow, especially in event-trigger sensing tasks. In this paper, we study queue-aware service migration and resource allocation in an MEC network, where different devices with different arrival patterns request different network services. To this end, we first formulate a novel long-term operation cost minimization problem subject to the stability of multiple queues by adopting a simultaneous migration scheme and determining resource allocation dynamically. To address the problem efficiently, we propose an online control framework to make decisions without any prior system information. We first adopt the Lyapunov optimization technique to decompose the long-term optimization problem into multi-per-slot subproblems. Then, we adopt a decoupled optimization algorithm based on the coordinate descent method and augmented Lagrangian method to solve the offline mixed integer non-linear programming (MINLP) subproblems. Extensive results reveal that the proposed online optimization framework can efficiently balance queue stability and cost consumption. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Joint UAV Deployment and Edge Association for Energy-Efficient Federated Learning

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Wu, Tao Li, Maomao Qu, Yuben Wang, Hongjun Wei, Zhenhua Cao, Jiannong National University of Defense Technology Hefei230009 China Nanjing University of Aeronautics and Astronautics Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing211106 China Xi'an Research Institute of High Technology Xi'an710025 China The HongKong Polytechnic University Department of Computing Hong Kong Hong Kong

Recently, federated learning (FL) has become a promising distributed learning paradigm that caters to the recent trend of pushing intelligence from the cloud to the edge. Nevertheless, communication bottlenecks and device dropout can lead to inefficient FL in the large network scale, where massive devices cannot be accessed with severely limited network resources. Inspired by the Unmanned Aerial Vehicle (UAV)-assisted mobile edge computing (MEC), we propose the multi-UAV assisted FL design to provide the intermediate model aggregation in the sky. Specifically, we study the problem of joint UAV dePloyment and edge aSsociation (UPS) to minimize the overall energy consumption, which concerns UAV deployment, edge association, and resource allocation. Unfortunately, solving this problem is non-trivial, due to its infinite search space and the complex coupling among mixed optimization variables. To tackle this difficulty, we exploit the FL bundle generation method to reduce candidate locations of UAVs from infinite to finite. Then, we decompose the initial problem and devise an alternating optimization-based algorithm to achieve the optimal resource allocation in the closed form. On this basis, we design a greedy-based approximation algorithm with logN performance guarantee for UAV deployment and edge association. Extensive simulations are conducted to validate the effectiveness of our proposed solution. Compared with five benchmarks, our proposed algorithm can significantly reduce the overall training energy consumption under the training time constraint, while always maintaining better training performance under different parameter settings. © 2015 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Hybrid FFT: A Novel Pipeline and Memory-Based Architecture for Radix-2k FFT in Large Size Processing

arXiv

引用

arXiv 2025年

作者： Zhao, Fangyu Xiao, Chunhua Wang, Zhiguo Du, Xiaohua Dong, Bo College of Computer Science Chongqing University Chongqing China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education China Sichuan Huacun Zhigu Technology Co. Ltd. Chengdu China

In the field of digital signal processing, the fast Fourier transform (FFT) is a fundamental algorithm, with its processors being implemented using either the pipelined architecture, well-known for high-throughput applications but weak in hardware utilization, or the memory-based architecture, designed for area-constrained scenarios but failing to meet stringent throughput requirements. Therefore, we propose an adaptive hybrid FFT, which leverages the strengths of both pipelined and memory-based architectures. In this paper, we propose an adaptive hybrid FFT processor that combines the advantages of both architectures, and it has the following features. First, a set of radix-2kmulti-path delay commutators (MDC) units are developed to support high-performance large-size processing. Second, a conflict-free memory access scheme is formulated to ensure a continuous data flow without data contention. Third, We demonstrate the existence of a series of bit-dimension permutations for reordering input data, satisfying the generalized constraints of variable-length, high-radix, and any level of parallelism for wide adaptivity. Furthermore, the proposed FFT processor has been implemented on a field-programmable gate array (FPGA). As a result, the proposed work outperforms conventional memory-based FFT processors by requiring fewer computation cycles. It achieves higher hardware utilization than pipelined FFT architectures, making it suitable for highly demanding applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Pipeline processing systems

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Time-Varying Workload Scheduling With Priority and Resource Awareness

引用

IEEE Transactions on Network and service Management 2025年

作者： Liu, Qifeng Fan, Qilin Zhang, Xu Li, Xiuhua Wang, Kai Xiong, Qingyu Chongqing University School of Big Data and Software Engineering Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing400044 China Nanjing University School of Electronic Science and Engineering Nanjing210023 China Haihe Laboratory of Information Technology Application Innovation Tianjin300072 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China Shandong Key Laboratory of Industrial Network Security Weihai264209 China

With the proliferation of cloud services and the continuous growth in enterprises' demand for dynamic multi-dimensional resources, the implementation of effective strategy for time-varying workload scheduling has become increasingly significant. In this paper, we propose a deep reinforcement learning (DRL)-based method for time-varying workload scheduling, aiming to allocate resources efficiently across servers in the cluster. Specifically, we integrate a classifier and queue scorer to construct a priority queue that exploits temporal resource utilization patterns across different workload classes. Then, we design parallel graph attention layers to capture the dimensional features and temporal dynamics of cloud server cluster. Moreover, we propose a DRL algorithm to generate scheduling strategies that can adapt to dynamic environments. Validation on real-world traces from Google cluster demonstrates that our method outperforms existing approaches in key metrics of cloud server cluster management. © 2004-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Time-aware Medication Recommendation via Intervention of Dynamic Treatment Regimes 25

Time-aware Medication Recommendation via Intervention of Dyn...

引用

Proceedings of the ACM on Web Conference 2025

作者： Yishuo Li Qi Zhang Wenpeng Lu Xueping Peng Weiyu Zhang Jiasheng Si Yongshun Gong Liang Hu 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) Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Department of Computer Science and Technology Tongji University Shanghai China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia 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) Jinan China School of Software Shandong University Jinan China

ISBN: (纸本)9798400712746

Medication recommendation aims to suggest personalized drug combinations to patients based on their longitudinal medical histories stored in electronic health record (EHR) datasets. Patients' Dynamic Treatment Regimes (DTRs) determine how patients' drug combinations change along with the evolution of disease treatment. DTRs are effective for comprehending disease-treatment dynamics and for recommending a timely and personalized combination of medications for patients. However, existing medication recommender systems (MRSs) overlook the multiple treatment pathways generated by the intervention of DTRs and can only recommend a single treatment paradigm, ignoring the fact that patients may be at different treatment stages and thus require different treatment regime. Such disregard leads to a significant limitation in recommending personalized medication combinations tailored to different treatment stages, yielding greatly compromised accuracy and applicability of MRSs. Moreover, existing methods often overlook the time interval information over patients' successive visits, which is critical to indicate patients' treatment evolution. To address these significant gaps, we propose a Time-aware Medication Recommendation Framework via Intervention of Dynamic Treatment Regimes, called MR-DTR. To explicitly illustrate the intervention processes of DTRs on similar patients, we employ a co-guided graph to connect various patient sequences. In addition, to fully utilize the time interval information, we design a time-aware guidance mechanism dedicated to the co-guided graph to efficiently learn medication representation using the patient's guidance information. We also introduce relative time intervals in the encoder to act as positional information. Extensive experiments on two real-world datasets demonstrate that MR-DTR surpasses state-of-the-art models in terms of recommendation performance. Our code is available at: https://***/liyifo/MR-DTR.

关键词： dynamic treatment regimes

来源：评论

学校读者我要写书评

暂无评论

MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention

arXiv

引用

arXiv 2025年

作者： Yang, Rui Wu, Xiaojun He, Shengfeng The School of Computer Sciences Shaanxi Normal University Xi'An China The School of Computer Science The Key Laboratory of Intelligent Computing and Service Technology for Folk Song of the Ministry of Culture and Tourism Shaanxi Normal University Xi'An710119 China The School of Computing and Information Systems Singapore Management University Singapore

Current sketch extraction methods either require extensive training or fail to capture a wide range of artistic styles, limiting their practical applicability and versatility. We introduce Mixture-of-Self-Attention (MixSA), a training-free sketch extraction method that leverages strong diffusion priors for enhanced sketch perception. At its core, MixSA employs a mixture-of-self-attention technique, which manipulates self-attention layers by substituting the keys and values with those from reference sketches. This allows for the seamless integration of brushstroke elements into initial outline images, offering precise control over texture density and enabling interpolation between styles to create novel, unseen styles. By aligning brushstroke styles with the texture and contours of colored images, particularly in late decoder layers handling local textures, MixSA addresses the common issue of color averaging by adjusting initial outlines. Evaluated with various perceptual metrics, MixSA demonstrates superior performance in sketch quality, flexibility, and applicability. This approach not only overcomes the limitations of existing methods but also empowers users to generate diverse, high-fidelity sketches that more accurately reflect a wide range of artistic expressions. Copyright © 2025, The Authors. All rights reserved.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Assisted Privacy-Preserving and Synchronized key Agreement for VDTNs

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Wang, Chenhao Ming, Yang Liu, Hang Feng, Jie Yang, Mengmeng Xiang, Yang Chang'an University School of Information Engineering Xi'an710064 China Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China Commonwealth Scientific and Industrial Research Organization Australia Swinburne University of Technology Department of Computing Technologies VIC3122 Australia

With the continuous development of digitization evolutions, vehicular digital twin networks (VDTNs) facilitate traffic data and optimization results to be exchanged between the vehicle and digital twin as well as shared among a group of digital twins. However, the data exchange and group sharing processes take place in real-time over public communication channels, which suffer from various security and privacy threats. key agreement technologies are promising to enable secure data communications for entities, but the existing key agreement schemes generally fail to fulfill the requirements of synchronization, privacy, and entity management for VDTNs. Therefore, we propose a blockchain-assisted privacy-preserving and synchronized key agreement scheme for VDTNs. In the proposed scheme, the anonymous vehicle and digital twin can negotiate a secret session key in the case of synchronization to achieve secure data exchange. Meanwhile, digital twins are capable of utilizing synchronized state information to dynamically establish a common group encryption key but hold individual decryption keys, which guarantee the security of group sharing. Additionally, the proposed scheme is able to protect identity privacy and manage vehicles and digital twins with the assistance of blockchain and smart contract. The security analysis demonstrates that the proposed scheme provides security and privacy assurances for VDTNs. The performance evaluation indicates that it has excellent expressions in terms of efficiency, practicality, and smart contract consumption. © 2004-2012 IEEE.

关键词： Differential privacy

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：