检索结果-内蒙古大学图书馆

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Li, Changlong Zhu, Zongwei Wang, Chao Liu, Fangming Xu, Fei Sha, Edwin H.-M. Zhou, Xuehai School of Computer Science and Technology East China Normal University China Jianghuai Advance Technology Center Hefei230026 China MoE Engineering Research Center of Hardware/Software Co-Design Technology and Application China School of Software Engineering University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China Huazhong University of Science and Technology China Peng Cheng Laboratory China

ISBN: (纸本)9781939133458

In mobile systems, memory can be compressed page-by-page to save space. This approach is widely adopted because memory data is accessed by page. However, this paper shows that the system response speed is significantly limited by page-grained compression. In this paper, we observe that approximately a quarter of anonymous memory pages are highly correlated, even though the association is implicit. Inspired by this, we propose Archer, an association-rule-aware memory compression framework in mobile systems. Archer demonstrates that memory in mobile devices should be compressed using flexible granularity, rather than relying solely on traditional page compression. To further integrate association-rule mining techniques into system design, we redesign the LRU mechanism and propose an adaptive memory compression region. Experimental results show that the average app launching speed is 1.55x faster when enabling Archer, and the average photographic speed and frame rate increase by 1.42x and 1.31x, respectively, compared to the state-of-the-art. © 2025 FAST. All Rights Reserved.

关键词： Portable equipment

来源：评论

学校读者我要写书评

暂无评论

Enhancing Weakly Supervised Medical Segmentation via Heterogeneous Co-training with Box-Wise Augmentation and Pseudo-Label Filtering 6th

Enhancing Weakly Supervised Medical Segmentation via Hetero...

引用

6th IFIP TC 12 International Conference on Intelligence Science, ICIS 2024

作者： Wang, You Qi, Lei Yu, Qian Shi, Yinghuan Gao, Yang State Key Laboratory of Novel Software Technology National Insititute of Health-care Data Science Nanjing University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China School of Data and Computer Science Shandong Woman’s University Jinan China

ISBN: (纸本)9783031712524

In this paper, we introduce an innovative approach to weakly supervised medical image segmentation with box annotations. Different from the previous methods which simply utilize a single conventional network with the same augmentation techniques widely used in supervised segmentation, we aim to introduce diverse augmentations and heterogenous networks to leverage the box annotations for promising generalization ability. Specifically, to amplify the diversity between the contents within the box and its surroundings, we propose the interior and exterior box augmentation (IEBA) technique, in which distinct augmentation techniques are employed for regions inside and outside the bounding boxes. Also, for the purpose of selecting pseudo-labels of superior quality, we propose the pseudo-label filter module (PLFM) to eliminate unreliable pseudo-labels. Besides, as CNN demonstrates superior capabilities in acquiring local information, and ViT specializes in capturing global context, we facilitate a bidirectional learning process between CNN and ViT through quadruple cross consistency losses (QCCL). In inference, we only employ the superior model from the validation set to obtain parameter efficiency. Our approach is evaluated across four tasks on two public datasets, utilizing the 3D dice similarity coefficient as the evaluation metric. The experimental results show that the proposed method outperforms the state-of-the-art comparison methods. © IFIP International Federation for Information Processing 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-View Incongruity Learning for Multimodal Sarcasm Detection 31

Multi-View Incongruity Learning for Multimodal Sarcasm Detec...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Guo, Diandian Cao, Cong Yuan, Fangfang Liu, Yanbing Zeng, Guangjie Yu, Xiaoyan Peng, Hao Yu, Philip S. Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Technology Beijing Institute of Technology China Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9798891761964

Multimodal sarcasm detection (MSD) is essential for various downstream tasks. Existing MSD methods tend to rely on spurious correlations. These methods often mistakenly prioritize non-essential features yet still make correct predictions, demonstrating poor generalizability beyond training environments. Regarding this phenomenon, this paper undertakes several initiatives. Firstly, we identify two primary causes that lead to the reliance of spurious correlations. Secondly, we address these challenges by proposing a novel method that integrate Multimodal Incongruities via Contrastive Learning (MICL) for multimodal sarcasm detection. Specifically, we first leverage incongruity to drive multi-view learning from three views: token-patch, entity-object, and sentiment. Then, we introduce extensive data augmentation to mitigate the biased learning of the textual modality. Additionally, we construct a test set, SPMSD, which consists potential spurious correlations to evaluate the the model's generalizability. Experimental results demonstrate the superiority of MICL on benchmark datasets, along with the analyses showcasing MICL's advancement in mitigating the effect of spurious correlation. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge Environments

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Jia, Ninghui Qu, Zhihao Ye, Baoliu Wang, Yanyan Hu, Shihong Guo, Song Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Nanjing211100 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Kowloon Hong Kong

In traditional centralized machine learning, transmitting raw data to a cloud center incurs high communication costs and raises privacy concerns. This is particularly challenging in mobile edge environments, where devices are dynamic and resource-constrained. Federated Learning (FL) addresses these issues by allowing devices to train models locally and upload parameters to a central server without sharing local data. However, limited wireless channel resources and dynamic transmission performance make communication overhead a major bottleneck of FL in mobile edge environments. Concerning this challenge, this survey provides a comprehensive summary of methods to improve communication efficiency in FL, focusing on: 1) minimizing communication complexity to reduce total transmission volume, 2) scheduling resources appropriately to improve training efficiency, 3) utilizing over-the-air computation (OTA) to integrate computation into communication for accommodating the computation/communication characteristics of FL in mobile edge environments. Thus, this work analyzes research from the perspective of convergence and data heterogeneity to reduce communication rounds by optimizing algorithm performance. We hope that this survey could offer insights into communication-efficient FL for future research. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Universal Construction for Linearizable but Not Strongly Linearizable Concurrent Objects 10th

Universal Construction for Linearizable but Not Strongly L...

引用

10th International Symposium on Dependable software Engineering: Theories, Tools and Applications, SETTA 2024

作者： Wang, Chao Wu, Peng Petri, Gustavo Jia, Qiaowen He, Youlin Lv, Yi Liu, Zhiming Centre for Research and Innovation in Software Engineering College of Computer and Information Science Southwest University Chongqing China and State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Arm Research Cambridge United Kingdom China Great Wall Technology Group Co. Ltd. Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819606016

Strong linearizability is a variant of linearizability and is more suitable for verification. In this paper we investigate the following two problems: (1) for which deterministic sequential specifications there exist linearizable but not strongly linearizable objects;(2) can we capture any violation scheme of strong linearizability for practical objects that are linearizable but not strongly linearizable. To deal with the first problem, we propose two classes of deterministic sequential specifications called inclusively-permutative sequential specifications and exclusively-permutative sequential specifications. The first class of sequential specifications contains sequential specifications of counter, register, max-register, snapshot, set, queue, stack and priority queue. The second class of sequential specifications contains sequential specifications of blocking queue, blocking stack and blocking priority queue. To establish these results, we propose a uniform methodology to construct a wait-free, linearizable but not strongly linearizable object for these two classes of sequential specifications. Our universal construction is based on the classical universal construction, and it additionally permits each operation to change the "take-effect-order" of previous operations. To deal with the second problem, we use bi-branch distinguishable executions to represent violations of strong linearizability. We investigate eight objects that are linearizable but not strongly linearizable, and we show that for each object, it has a pair of bi-branch distinguishable executions such that our universal construction can generate another pair of bi-branch distinguishable executions with the same set of histories. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overview of Security Threats, Attack Detection and Defense for Large-Scale Multi-Agent Systems (LSMAS) in Internet of Things (IoT)

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 70-81页

作者： Cai, Jijing Wen, Long Feng, Hailin Fang, Kai Chen, Junxin Wei, Wei Wang, Wei Zhejiang A and F University College of Mathematics and Computer Science Hangzhou311300 China Macau University of Science and Technology School of Innovation Engineering Macau999078 China Dalian University of Technology School of Software Dalian116621 China Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Beijing Institute of Technology School of Medical Technology Beijing100081 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Shenzhen518172 China

With the global advancement of the Internet of Things (IoT), large-scale multi-agent systems (LSMAS) technology has been increasingly adopted across various industries. Despite the widespread use of IoT, vulnerabilities in its software and hardware components pose significant challenges to ensuring security. To address the security concerns faced by LSMAS, this article explores its application in IoT domains such as smart grids, smart manufacturing, and smart healthcare. By examining the structural layers of IoT-the perception layer, network layer, and application layer-this paper analyzes the specific security threats encountered by each layer, along with the defense strategies designed to counter these attacks. Furthermore, we categorize and compare both traditional and AI-based attack detection methods, dividing the latter into machine learning-based, deep learning-based, and transfer learning-based approaches. This analysis highlights the strengths and weaknesses of the various attack detection methods currently deployed in LSMAS, identifying the existing challenges they face. Finally, we outline potential trends for the future development of LSMAS in IoT, offering research directions for experts in related fields. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

引用

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

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology SydneyNSW2007 Australia Institute of Software Chinese Academy of Sciences Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 1982-2012 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Toward Long Video Understanding via Fine-Detailed Video Story Generation

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第5期35卷 4592-4607页

作者： You, Zeng Wen, Zhiquan Chen, Yaofo Li, Xin Zeng, Runhao Wang, Yaowei Tan, Mingkui South China University of Technology School of Future Technology Guangzhou510006 China Peng Cheng Laboratory Shenzhen518066 China South China University of Technology School of Software Engineering Guangzhou510006 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518115 China Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China

Long video understanding has become a critical task in computer vision, driving advancements across numerous applications from surveillance to content retrieval. Existing video understanding methods suffer from two challenges when dealing with long video understanding: intricate long-context relationship modeling and interference from redundancy. To tackle these challenges, we introduce Fine-Detailed Video Story generation (FDVS), which interprets long videos into detailed textual representations. Specifically, to achieve fine-grained modeling of long-temporal content, we propose a Bottom-up Video Interpretation Mechanism that progressively interprets video content from clips to video. To avoid interference from redundant information in videos, we introduce a Semantic Redundancy Reduction mechanism that removes redundancy at both the visual and textual levels. Our method transforms long videos into hierarchical textual representations that contain multi-granularity information of the video. With these representations, FDVS is applicable to various tasks without any fine-tuning. We evaluate the proposed method across eight datasets spanning three tasks. The performance demonstrates the effectiveness and versatility of our method. © 1991-2012 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Evaluating Logical Expressions by Membrane Systems

引用

Chinese Journal of Electronics 2025年第2期23卷 278-283页

作者： Ping Guo Jinfang Ji Haizhu Chen Ran Liu College of Computer Science Chongqing University Chongqing China Chongging Key Laboratory of Software Theory and Technology Chongqing China Department of Software Engineering Chongqing College of Electronic Engineering Chongqing China

Boolean and relational operations, which are defined for solving mathematically logical problems, are always required in computing models. Membrane computing is a kind of distributed parallel computing model. In this paper, we design different membranes for implementing primary Boolean and relational operations respectively. And based on these membranes, a membrane system can be constructed by a present algorithm for evaluating a logical expression. Some examples are given to illustrate how to perform the Boolean, relational operations and evaluate the logical expression correctly in these membrane systems.

关键词： Computational modeling Parallel processing Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Arithmetic Expression Evaluations with Membranes

引用

Chinese Journal of Electronics 2025年第1期23卷 55-60页

作者： Ping Guo Haizhu Chen Hui Zheng College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Software Theory and Technology Chongqing China Department of Software Engineering Chongqing College of Electronic Engineering Chongqing China

Arithmetic operations and expression evaluations are fundamental in computing models. This paper firstly designs arithmetic membranes without priority rules for basic arithmetic operations, and then proposes an algorithm to construct expression P systems based on several of such membranes after designing synchronous and asynchronous transmission strategies among the membranes. For any arithmetic expression, an expression P system can be built to evaluate it effectively. Finally, we discuss different parallelism strategies through which different expression P systems can be built for an arithmetic expression.

关键词： Computational modeling Biological system modeling Parallel processing Biomembranes Compounds Arithmetic

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：