检索结果-内蒙古大学图书馆

18th ACM International Conference on Web Search and Data Mining, WSDM 2025

作者： Wang, Zhe Zhou, Sheng Chen, Jiawei Zhang, Zhen Hu, Binbin Feng, Yan Chen, Chun Wang, Can Zhejiang University College of Computer Science Hangzhou China Zhejiang University School of Software Technology Ningbo China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China National University of Singapore Singapore Singapore Ant Group Hangzhou China

ISBN: (纸本)9798400713293

Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial requirement for representation learning in CTDGs is the appropriate estimation and preservation of proximity. However, due to the sparse and evolving characteristics of CTDGs, the spatial-temporal properties inherent in high-order proximity remain largely unexplored. Despite its importance, this property presents significant challenges due to the computationally intensive nature of personalized interaction intensity estimation and the dynamic attributes of CTDGs. To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process. Building on this, we introduce the Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding (CorDGT), which efficiently retains the evolving spatial-temporal high-order proximity for effective node representation learning in CTDGs. Extensive experiments on seven small and two large-scale datasets demonstrate the superior performance and scalability of the proposed CorDGT. The code is available at: https://***/wangz3066/CorDGT. © 2025 Copyright held by the owner/author(s).

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Complementary Learning System Theory-based Active Learning for Audio Classification

Complementary Learning System Theory-based Active Learning f...

引用

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

作者： Hui Geng Zijian Gao Tianjiao Wan Dawei Feng Changjian Wang Kele Xu College of Computer Science and Technology National University of Defense Technology Changsha China State Key Laboratory of Complex & Critical Software Environment Changsha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Deep learning has significantly advanced the audio classification, achieving remarkable results. However, these successes often rely on extensive manual annotation of audio, a labor-intensive and costly process. Active Learning (AL) presents a promising solution by minimizing the required amount of annotation through the iterative selection of the most informative audio samples. Current AL methods for audio classification typically depend solely on the latest model checkpoint, overlooking the dynamics of the entire training process. The Complementary Learning Systems (CLS) theory posits that the interplay between short-term and long-term memory systems can effectively measure sample uncertainty, offering a means to capture training dynamics. In this work, we introduce a novel AL framework for audio classification, termed CLS-AL, which addresses the limitations of existing methods by simultaneously maintaining both short-term and long-term memory models. This dual-memory approach allows for a more comprehensive consideration of training dynamics. The divergence in predictions between these memory models provides a new metric for evaluating the uncertainty of unlabeled samples, enhancing the effectiveness of the AL sample selection process. We demonstrate the effectiveness and generalizability of CLS-AL through extensive experiments on a diverse set of audio datasets, showing that CLS-AL obviously outperforms existing state-of-the-art methods.

关键词： Training Uncertainty Annotations Active learning Measurement uncertainty Manuals Signal processing Predictive models Iterative methods Speech processing

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

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Enhancing Routing Performance Through Trajectory Planning With DRL in UAV-Aided VANETs

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 517-533页

作者： Chen, Jingxuan Huang, Dianrun Wang, Yijie Yu, Ziping Zhao, Zhongliang Cao, Xianbin Liu, Yang Quek, Tony Q. S. Oliver Wu, Dapeng Beihang University School of Electronic and Information Engineering Beijing100191 China State Key Laboratory of CNS/ATM Beijing100191 China Nanyang Technological University School of Computer Science and Engineering Nanyang Avenue 639798 Singapore Singapore University of Technology and Design Information System Technology and Design Pillar Somapah Rd 487372 Singapore Yonsei University Yonsei Frontier Laboratory Seoul03722 Korea Republic of City University of Hong Kong Department of Computer Science Kowloon Hong Kong

Vehicular Ad-hoc Networks (VANETs) have gained significant attention as a key enabler for intelligent transportation systems, facilitating vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Despite their potential, VANETs face critical challenges in maintaining reliable end-to-end connectivity due to their highly dynamic topology and sparse node distribution, particularly in areas with limited infrastructure coverage. Addressing these limitations is crucial for advancing the reliability and scalability of VANETs. To bridge these gaps, this work introduces a heterogeneous UAV-aided VANET framework that leverages uncrewed aerial vehicles (UAVs), also known as autonomous aerial vehicles, to enhance data transmission. The key contributions of this paper include: 1) the design of a novel adaptive dual-model routing (ADMR) protocol that operates in two modes: direct vehicle clustering for intra-cluster communication and UAV/RSU-assisted routing for inter-cluster communication;2) the development of a modified density-based clustering algorithm (MDBSCAN) for dynamic vehicle node clustering;and 3) an improved UAV trajectory planning method based on a multi-agent soft actor-critic (MASAC) deep reinforcement learning algorithm, which optimizes network reachability. Simulation results reveal that the UAV trajectory optimization method achieves higher network reachability ratios compared to existing approaches. Also, the proposed ADMR protocol improves the packet delivery ratio (PDR) while maintaining low end-to-end latency. These findings demonstrate the potential to enhance VANET performance, while also providing valuable insights for the development of intelligent transportation systems and related fields. © 2025 The Authors.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Visual Language Model based Cross-modal Semantic Communication Systems

引用

IEEE Transactions on Wireless Communications 2025年第5期24卷 3937-3948页

作者： Jiang, Feibo Tang, Chuanguo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China Hunan Normal University School of Information Science and Engineering Changsha410081 China Hunan University of Technology and Business School of Computer Science Changsha410205 China Xiangjiang Laboratory Changsha410205 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Nanjing University School of Intelligent Software and Engineering Suzhou215163 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China

Semantic Communication (SC) has emerged as a novel communication paradigm in recent years. Nevertheless, extant Image Semantic Communication (ISC) systems face several challenges in dynamic environments, including low information density, catastrophic forgetting, and uncertain Signal-to-Noise Ratio (SNR). To address these challenges, we propose a novel Vision-Language Model-based Cross-modal Semantic Communication (VLM-CSC) system. The VLM-CSC comprises three novel components: (1) Cross-modal Knowledge Base (CKB) is used to extract high-density textual semantics from the semantically sparse image at the transmitter and reconstruct the original image based on textual semantics at the receiver. The transmission of high-density semantics contributes to alleviating bandwidth pressure. (2) Memory-assisted Encoder and Decoder (MED) employ a hybrid long/short-term memory mechanism, enabling the semantic encoder and decoder to overcome catastrophic forgetting in dynamic environments when there is a drift in the distribution of semantic features. (3) Noise Attention Module (NAM) employs attention mechanisms to adaptively adjust the semantic coding and the channel coding based on SNR, ensuring the robustness of the CSC system. The experimental simulations validate the effectiveness, adaptability, and robustness of the CSC system. © 2002-2012 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Monitoring of Fire-Affected Buildings and Air-Quality Assessment: A Remote-Sensing Study Using Ground-Based interferometric Radar and Google-Earth-Engine

引用

Rangeland Ecology and Management 2025年 101卷 28-42页

作者： Zhang, Hao Zheng, Xiangtian Ghaffar, Bushra Quddoos, Abdul Naz, Iram Aslam, Rana Waqar Fatima, Zoia Abdullah-Al-Wadud, M. Zulqarnain, Rana Muhammad China Academy of Safety Science and Technology Beijing 100012 China Nanjing Institute of Technology School of Computer Engineering Nanjing 211167 China Department of Environmental Science Faculty of Sciences International Islamic University Islamabad 44000 Pakistan State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing (LIESMARS) Wuhan University Wuhan 430079 China Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia Department of Mathematics Saveetha School of Engineering SIMATS Thandalam Tamilnadu Chennai - 602105 India

This study investigates the environmental and structural impacts of crop and rangeland residue burning in Punjab during April and May 2023, utilizing ground-based interferometric radar alongside atmospheric and land use datasets. The radar system was employed to monitor structural deformations in buildings affected by fire, providing critical insights into the broader impacts of the fires on infrastructure. Multiple ground-based interferometric radars for distributed monitoring can effectively obtain the three-dimensional deformation components of structural targets in real fire scenes. The monitoring results conform to the displacement variation law of existing portal steel frame structures during fire deformation, and can provide effective data support for building structure collapse warning under fire. This approach offers a novel method for assessing the structural integrity of buildings during and after fire events, complementing traditional environmental monitoring. Environmental data show a marked increase in atmospheric pollutants such as NO₂, CH₄, and CO in May 2023, directly linked to the residue burning. Active fire data from FIRMS and MODIS revealed a 98% increase in fire events compared to April, while land surface temperature analysis showed a rise of 1.54%, with affected areas reaching up to 45.9°C. LULC analysis indicated a 23.3% decrease in cropland and rangeland areas, reflecting extensive land clearing. These findings highlight the urgent need for sustainable agricultural management and policies to mitigate the environmental and infrastructural damage caused by residue burning in Punjab. © 2025 The Society for Range Management

关键词： Agriculture Fire & Air Quality Distributed monitoring Google Earth Engine Ground-based interferometric radar Sentinel-2

来源：评论

学校读者我要写书评

暂无评论

When Crowdsensing Meets Smart Cities: A Comprehensive Survey and New Perspectives

引用

IEEE Communications Surveys and Tutorials 2025年第2期27卷 1101-1151页

作者： Wang, Zhenning Cao, Yue Jiang, Kai Zhou, Huan Kang, Jiawen Zhuang, Yuan Tian, Daxin Leung, Victor C. M. Wuhan University School of Cyber Science and Engineering Wuhan430072 China Northwestern Polytechnical University College of Computer Xi’an710129 China Guangdong University of Technology School of Automation Guangzhou510006 China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China Beihang University School of Transportation Science and Engineering Beijing100191 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518061 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Crowdsensing has received widespread attention in recent years. It is extensively employed in smart cities and intelligent transportation systems. This paper comprehensively surveys the latest research advancements in crowdsensing for smart cities from a novel perspective. Specifically, this paper is categorized according to sensing entities in smart cities, including human-oriented sensing, vehicle-oriented sensing, and infrastructure-oriented sensing. Meanwhile, the development of Unmanned Aerial Vehicle (UAV)-assisted sensing in recent years is also summarized, accompanied by a timeline of related research. To facilitate easy comprehension, we have positioned the reading flow into the corresponding architectures, resolved problems, existing technical solutions, and specific application scenarios for different sensing entities. In particular, the problems to be solved are further analyzed from four technical perspectives, namely mathematics and operational research, artificial intelligence and machine learning, incentive mechanisms, security and privacy protection. Based on the proposed taxonomy, recent studies are thoroughly investigated to illustrate the current state of research in crowdsensing. Furthermore, this paper highlights the emerging applications of human-oriented and vehicle-oriented sensing in smart cities, as well as the frameworks, platforms, simulators, and datasets involved in crowdsensing. Finally, this paper discusses research directions related to crowdsensing in smart cities, such as digital twins, metaverses, and artificial intelligence-generated content. The primary goal of this survey is to review and synthesize prior research, identify potential avenues for future research, and explore opportunities for collaboration with other relevant research domains. © 1998-2012 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

CESFusion: Cross-Frequency Enhanced Spatial-Spectral Fusion Network for Hyperspectral and Multispectral Image Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Haozheng Yang, Yanhong Li, Chaoyang Lu, Yanjie Zhang, Guodao Chen, Shengyong School of Computer Science and Engineering Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China Engineering Research Center of Learning- Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and Systems School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Institute of Intelligent Media Computing Hangzhou Dianzi University Hangzhou310018 China

The fusion of hyperspectral and multispectral images involves integrating high spectral resolution hyperspectral image (HSI) and high spatial resolution multispectral image (MSI) to generate a HSI with high spatial and spectral resolution (HR-HSI). Existing HSI-MSI fusion methods primarily focus on information fusion within the spatial domain;however, few solutions have explored the employment of frequency analysis to enhance spatial resolution, limiting their capability for global perception. In this paper, we propose an efficient and novel paradigm for HSI-MSI fusion through the cross-frequency enhanced spatial-spectral fusion network, named CESFusion, exploring the complementary fusion of information between the spatial and frequency domains. Specifically, we first present the cross-frequency domain fusion module (CFFM) to perform global analysis through the Fourier transform and effectively integrate and enhance the frequency domain information from both HSI and MSI. Subsequently, we propose the spectral modeling module (SpeMM) based on state space model (SMM) to capture long-range spectral dependencies with linear complexity, and integrate it with the spatial residual block-based module (SRM) for joint spatial-spectral feature extraction. Finally, to enable sufficient interaction between the spatial and frequency domains, we adopt the cross-domain interaction module (CDIM), capturing and integrating complementary information from both domains. Moreover, a frequency-based loss function is purposely designed to further improve the restoration of global information. Extensive experiments conducted on both synthetic and real datasets demonstrate the superiority of our CESFusion, as evidenced by both quantitative and qualitative evaluation results. © 2025 IEEE.

关键词： Image fusion

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：