检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Feng, Wei Wang, Feifan Han, Ruize Qian, Zekun Wang, Song College of Intelligence and Computing Tianjin University Tianjin300350 China Key Research Center for Surface Inspection and Analysis of Cultural Relics SACH China the Department of Computer Science and Engineering University of South Carolina ColumbiaSC29208 United States

Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking. This way, the videos for MvMHAT require more complex annotations while containing more information for self learning. In this work, we tackle this problem with a self-supervised learning aware end-to-end network. Specifically, we propose to take advantage of the spatial-temporal self-consistency rationale by considering three properties of reflexivity, symmetry and transitivity. Besides the reflexivity property that naturally holds, we design the self-supervised learning losses based on the properties of symmetry and transitivity, for both appearance feature learning and assignment matrix optimization, to associate the multiple humans over time and across views. Furthermore, to promote the research on MvMHAT, we build two new large-scale benchmarks for the network training and testing of different algorithms. Extensive experiments on the proposed benchmarks verify the effectiveness of our method. We have released the benchmark and code to the public. Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Distributed Pairwise Protection for Security-Aware Mission Chains in UAV Networks

Distributed Pairwise Protection for Security-Aware Mission C...

引用

World Congress on computing and Communication Technologies (WCCCT)

作者： Yuhang Zhao Guangming Duan Danyang Zheng Xiaojun Cao Chengzong Peng School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology China SUGON Industrial Control and Security Center China School of Computing and Artificial Intelligence Southwest Jiaotong University China Department of Computer Science Georgia State University USA

ISBN: (数字)9798331512620

ISBN: (纸本)9798331512637

The unmanned aerial vehicles (UAVs) communication network exhibits significant potential in natural disaster management, with applications in flood relief and wildfire control. In these scenarios, UAVs can dynamically form mission chains (MCs) to collaboratively execute tasks such as real-time monitoring and post-disaster search and rescue. To address security challenges in these dynamic environments, we implement MCs as security-aware service function chains (SFCs). However, traditional SFC techniques are often inefficient and resource-intensive when applied to MCs in UAV networks, due to the networks’ dynamic nature and resource constraints. In this paper, we introduce and mathematically formulate a novel problem, termed the security-aware SFC distributed pairwise protection (SSFC-DPP) problem in UAV networks, which optimizes SFC protection against failures while balancing security and resource demands, and prove its NP-hardness. To tackle SSFC-DPP, we propose an efficient heuristic approach, the distributed pairwise node protection (DPNP) algorithm, integrating a security-resource ratio (SRR) factor and pairwise backup selection (PBS) technique. Extensive simulations show that DPNP reduces overall backup costs by 8.05% and 51.39% compared to two benchmark algorithms, respectively.

关键词： Wildfires Service function chaining Heuristic algorithms Benchmark testing Autonomous aerial vehicles Real-time systems Security Reliability Protection Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Cross-View Fuzziness and Intra-view Uncertainty-Based Weight Reconstruction for Multi-view Feature Selection 11th

Cross-View Fuzziness and Intra-view Uncertainty-Based Weigh...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Xiang, Biao Chen, Hongmei Mi, Yong Sang, Binbin Horng, Shi-Jinn Li, Tianrui Institute of Artificial Intelligence School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China College of Computer and Information Science Chongqing Normal University Chongqing401331 China Department of Computer Science and Information Engineering Asia University Taichung41354 Taiwan

ISBN: (纸本)9783031927430

Weight assignment is a universal and indispensable process in multi-view feature selection. However, most existing methods overlook the fuzziness and uncertainty implied in multi-view data. This may result in improper weight assignment, degrading the quality of selected features. A cross-view fuzziness and intra-view uncertainty-based weight reconstruction method (CFIUWR) is proposed for multi-view feature selection. With the fuzzy rough set theory, fuzzy approximation operators recognize cross-view fuzziness and intra-view uncertainty, which are evaluated by classification-related measurement. Cross-view fuzziness and intra-view uncertainty are incorporated to develop a reconstruction mechanism for view and feature weights. An optimization algorithm is derived, guaranteeing rapid convergence. Comparisons with state-of-the-art methods on several real-world datasets demonstrate the superiority of the CFIUWR. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

arXiv

引用

arXiv 2023年

作者： Yuan, Haonan Sun, Qingyun Fu, Xingcheng Zhang, Ziwei Ji, Cheng Peng, Hao Li, Jianxin Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China School of Computer Science and Engineering Beihang University China Key Lab of Education Blockchain and Intelligent Technology Guangxi Normal University China Department of Computer Science and Technology Tsinghua University China

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatiotemporal invariant patterns. Specifically, we first design the environment-aware EA-DGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions

arXiv

引用

arXiv 2023年

作者： Qin, Libo Pan, Wenbo Chen, Qiguang Liao, Lizi Yu, Zhou Zhang, Yue Che, Wanxiang Li, Min School of Computer Science and Engineering Central South University China Harbin Institute of Technology China Research Center for Social Computing and Information Retrieval Cyprus Singapore Management University Singapore Department of Computer Science Columbia University United States School of Engineering Westlake University China

End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of large pre-trained models, has further led to significant progress in EToD research in recent years. In this paper, we present a thorough review and provide a unified perspective to summarize existing approaches as well as recent trends to advance the development of EToD research. The contributions of this paper can be summarized: (1) First survey: to our knowledge, we take the first step to present a thorough survey of this research field;(2) New taxonomy: we first introduce a unified perspective for EToD, including (i) Modularly EToD and (ii) Fully EToD;(3) New Frontiers: we discuss some potential frontier areas as well as the corresponding challenges, hoping to spur breakthrough research in EToD field;(4) Abundant resources: we build a public website1, where EToD researchers could directly access the recent progress. We hope this work can serve as a thorough reference for the EToD research community. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Provably Efficient Simulation of 1D Long-Range Interacting Systems at Any Temperature

引用

Physical Review Letters 2025年第19期134卷 190404-190404页

作者： Rakesh Achutha Donghoon Kim Yusuke Kimura Tomotaka Kuwahara Analytical quantum complexity RIKEN Hakubi Research Team RIKEN Center for Quantum Computing (RQC) Wako Saitama 351-0198 Japan Department of Computer Science and Engineering Indian Institute of Technology (Banaras Hindu University) Varanasi 221005 India PRESTO Japan Science and Technology (JST) Kawaguchi Saitama 332-0012 Japan RIKEN Cluster for Pioneering Research (CPR) Wako Saitama 351-0198 Japan

We introduce a method that ensures efficient computation of one-dimensional quantum systems with long-range interactions across all temperatures. Our algorithm operates within a quasipolynomial run-time for inverse temperatures up to β=poly(ln(n)). At the core of our approach is the density matrix renormalization group algorithm, which typically does not guarantee efficiency. We have created a new truncation scheme for the matrix product operator of the quantum Gibbs states, which allows us to control the error analytically. Additionally, our method can be applied to simulate the time evolution of systems with long-range interactions, achieving significantly better precision than that offered by the Lieb-Robinson bound.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational Limits of Low-Rank Adaptation (LoRA) for Transformer-Based Models

arXiv

引用

arXiv 2024年

作者： Hu, Jerry Yao-Chieh Su, Maojiang Kuo, En-Jui Song, Zhao Liu, Han Department of Computer Science Northwestern University EvanstonIL60208 United States Department of Information and Computing Science USTC Anhui Hefei230026 China Physics Division National Center for Theoretical Sciences Taipei106319 Taiwan Adobe Research SeattleWA98103 United States Department of Statistics and Data Science Northwestern University EvanstonIL60208 United States

We study the computational limits of Low-Rank Adaptation (LoRA) update for finetuning transformer-based models using fine-grained complexity theory. Our key observation is that the existence of low-rank decompositions within the gradient computation of LoRA adaptation leads to possible algorithmic speedup. This allows us to (i) identify a phase transition behavior and (ii) prove the existence of nearly linear algorithms by controlling the LoRA update computation term by term, assuming the Strong Exponential Time Hypothesis (SETH). For the former, we identify a sharp transition in the efficiency of all possible rank-r LoRA update algorithms for transformers, based on specific norms resulting from the multiplications of the input sequence X, pretrained weights W*, and adapter matrices αBA/r. Specifically, we derive a shared upper bound threshold for such norms, and show that efficient (sub-quadratic) approximation algorithms of LoRA exist only below this threshold. For the latter, we prove the existence of nearly linear approximation algorithms for LoRA adaptation by utilizing the hierarchical low-rank structures of LoRA gradients and approximating the gradients with a series of chained low-rank approximations. To showcase our theory, we consider two practical scenarios: partial (e.g., only WV and WQ) and full adaptations (e.g., WQ, WV, and WK) of weights in attention heads. © 2024, CC BY-NC-SA.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient Batch Verification and Privacy-Preserving Data Aggregation Scheme in V2G Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Congcong Wang, Chen Shen, Jian Vasilakos, Athanasios V. Wang, Bin Wang, Weizheng Department of Software Engineering Nanjing University of Information Science and Technology Nanjing210044 China the Zhejiang Key Laboratory of Digital Fashion and Data Governance the Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation Zhejiang Sci-Tech University Hangzhou310018 China Zhejiang Provincial Innovation Center of Advanced Textile Technology Shaoxing312000 China College of Computer Science and Information Technology IAU Saudi Arabia Grimstad4879 Norway Network and Data Security Hangzhou310053 China Computer Science Department City University of Hong Kong Hong Kong the Division of Computer Science University of Aizu Fukushima965–8580 Japan

In recent years, against the backdrop of smart grids, vehicle-to-grid (V2G) interaction has become a hot topic. With the increasing number of new energy vehicles, handling massive amounts of electricity transaction data has become an urgent problem in need of resolution. Ensuring the security of the vast quantities of electricity transaction data has emerged as a significant challenge. Therefore, two data aggregation schemes are proposed in this paper, both supporting batch verification and privacy protection in centralized and distributed scenarios, respectively. Firstly, an improved Paillier cryptosystem is utilized to achieve lightweight encryption in the proposed schemes. In addition, a novel distributed data aggregation structure that combines a large number of geographically distributed fog nodes with centralized cloud servers is introduced. This structure not only meets the requirements of lightweight encryption and resistance against single point failures but also reduces the communication complexity of distributed data aggregation to O(n). According to the security proofs and experimental analysis, it can be demonstrated that both proposed schemes are effective and secure, meeting the lightweight requirements of modern smart grid systems. © 2025 IEEE. All rights reserved,

关键词： Data aggregation

来源：评论

学校读者我要写书评

暂无评论

Construction and Application of Protein-Protein Interaction Knowledge Graph 9th

Construction and Application of Protein-Protein Interaction ...

引用

9th International Symposium on Artificial Intelligence and Robotics, ISAIR 2024

作者： Xiong, Jing Wang, Xiaohong Dou, Fangkun Cao, Haowei Hong, Tenglong Li, Zhiwei Jing, Xiaoli School of Computer Science Qufu Normal University Rizhao276827 China Shandong Foreign Trade Vocational College Qingdao266100 China Rizhao-Qufu Normal University Joint Technology Transfer Center Rizhao276827 China Institute of Oceanology Chinese Academy of Sciences Qingdao266071 China Jinan250101 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250101 China China Everbright Bank Qingdao R&D Center Qingdao266071 China Rizhao Medical Insurance Service Center Rizhao276826 China Department of Information Research Qingdao Marine Science and Technology Center Qingdao266237 China

ISBN: (纸本)9789819629107

With the rapid advancement of emerging technologies such as high-throughput sequencing, cryo-electron microscopy, mass spectrometry, and artificial intelligence, our understanding of protein interactions has deepened significantly, leading to an increasing demand for effective data integration. This study tackles the complexity of protein interaction networks and the challenges associated with data integration by employing a top-down approach. It utilizes a protein ontology as the semantic framework, integrates resources from the BioGRID and UniProt databases, and constructs a comprehensive protein-protein interaction knowledge graph (PPIKG). This knowledge graph not only provides an intuitive, graphical interface for visualizing intricate protein interactions but also serves as a centralized platform for downloading protein interaction data. It acts as a one-stop solution for scientists aiming to explore and comprehend the complex landscape of protein interactions. With its user-friendly visualization and efficient download tools, the knowledge graph simplifies the data acquisition process, thereby fostering a deeper, holistic understanding of protein interaction networks among researchers. This innovative approach to data integration is set to accelerate scientific discovery and enhance our comprehension of biological systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Eltrack: Correlating Events and Language for visual Tracking

SSRN

引用

SSRN 2024年

作者： Alansari, Mohamad Alnuaimi, Khaled Alansari, Sara Werghi, Naoufel Javed, Sajid Department of Electrical Engineering College Of Computing And Mathematical Sciences Department of Computer Science Khalifa University Abu Dhabi United Arab Emirates Center for Autonomous Robotic Systems Khalifa University Abu Dhabi United Arab Emirates Center for Cyber-Physical Systems Khalifa University Abu Dhabi United Arab Emirates

The reliance on visible cameras in visual Object Tracking (VOT) presents challenges in handling rapid object movements and illumination variations. In contrast, event cameras, inspired by biological vision systems, capture asynchronous and sparse events with significantly lower latency. While visible cameras excel in perceiving texture details and slow motion, event cameras offer advantages such as freedom from motion blur and a larger dynamic range, making them suitable for fast motion and low illumination scenarios. Integrating these two sensor modalities can enhance the reliability of object *** paper addresses key challenges in event-based tracking and tracking by language descriptions. First, we tackle the scarcity of large-scale event-based benchmarks by leveraging the \textit{v2e} toolbox to synthesize event data from eight conventional frame-based benchmarks. This synthesized event data is then processed into a novel event image representation called Pseudo-Frames. Second, we mitigate the shortage of Natural Language (NL)-described datasets by employing the visual-Language (VL) image-captioning module, comprising BLIP-2 and GPT-4, to generate captions for eight VOT benchmarks *** propose a multi-modal visual-Language Object Tracking (VLOT) framework named ELTrack, which integrates RGB, event, and Natural Language Processing (NLP) modalities to enhance tracking performance. Our framework includes a simple superimpose fusion module that combines RGB frames with the proposed Pseudo-Frames, along with our VL image-captioning module to provide NL descriptions for the given sequences. Extensive experiments on our proposed framework demonstrate its effectiveness in addressing VOT challenges and achieving state-of-the-art (SOTA) performance across eight tracking *** datasets, NL descriptions, and source code associated with this work will be made available at: \url{https://***/HamadYA/ELTrack-Correlating-Events-and-Language-for

关键词： Cameras

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：