检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ma, Yifeng Wang, Suzhen Ding, Yu Ma, Bowen Lv, Tangjie Fan, Changjie Hu, Zhipeng Deng, Zhidong Yu, Xin Li, Lincheng Department of Computer Science and Technology BNRist THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University China Fuxi AI Lab Netease Zhejiang Hangzhou China The School of Computer Science The University of Queensland Brisbane Australia

Audio-driven talking head generation has drawn growing attention. To produce talking head videos with desired facial expressions, previous methods rely on extra reference videos to provide expression information, which may be difficult to find and hence limits their usage. In this work, we propose TalkCLIP, a framework that can generate talking heads where the expressions are specified by natural language, hence allowing for specifying expressions more conveniently. To model the mapping from text to expressions, we first construct a text-video paired talking head dataset where each video has diverse text descriptions that depict both coarse-grained emotions and fine-grained facial movements. Leveraging the proposed dataset, we introduce a CLIP-based style encoder that projects natural language-based descriptions to the representations of expressions. TalkCLIP can even infer expressions for descriptions unseen during training. TalkCLIP can also use text to modulate expression intensity and edit expressions. Extensive experiments demonstrate that TalkCLIP achieves the advanced capability of generating photo-realistic talking heads with vivid facial expressions guided by text descriptions. Copyright © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

EPM: Evolutionary Perception Method for Anomaly Detection in Noisy Dynamic Graphs

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第7期37卷 4035-4048页

作者： Wang, Huan Chen, Junyang Wu, Yirui Leung, Victor C. M. Wang, Di Huazhong Agricultural University Key Laboratory of Smart Farming for Agricultural Animals Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education College of Informatics Wuhan430072 China King Abdullah University of Science and Technology Division of Computer Electrical and Mathematical Sciences and Engineering Thuwal23955 Saudi Arabia Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Hohai University College of Computer and Information Nanjing210098 China Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518115 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

With the rapid expansion of interactions across various domains such as social networks, transaction networks, and IP-IP networks, anomaly detection in dynamic graphs has become increasingly critical for mitigating potential risks. However, existing anomaly detection methods often assume noise-free dynamic graphs, overlooking the prevalence of noisy dynamic graphs in real-world applications. Specifically, noisy dynamic graphs affected by structural noises—such as spurious and missing nodes and edges—struggle to consistently provide reliable structural evidence for anomaly detection. To tackle this challenge, we propose an Evolutionary Perception Method (EPM) for identifying anomalous nodes in noisy dynamic graphs by resisting the interference of structural noises. EPM primarily consists of two components: a dynamic fitter and a filtering reviser. The dynamic fitter characterizes the interaction dynamics of nodes that removes and generates links at each period as a multiple superposition state, utilizing various link prediction algorithms to fit evolutionary mechanisms. Additionally, the filtering reviser designs evolutional entropies to quantify the evolutional uncertainty in multiple superposition states, further reconstructing the Kalman filter to optimize these entropies. Extensive experiments have proved that our proposed EPM outperforms state-of-the-art methods in discovering anomalous nodes in noisy dynamic graphs. © 1989-2012 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Another Lattice Attack Against ECDSA with the wNAF to Recover More Bits per Signature 1

引用

18th EAI International Conference on Security and Privacy in Communication Networks, SecureComm 2022

作者： Ma, Ziqiang Li, Shuaigang Lin, Jingqiang Cai, Quanwei Fan, Shuqin Zhang, Fan Luo, Bo School of Information Engineering Ningxia University Yinchuan China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Science and Technology of China Hefei China State Key Laboratory of Cryptology Beijing China School of Cyber Science and Technology College of Computer Science and Technology Zhejiang University Hangzhou310027 China Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province Hangzhou310027 China Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States

ISBN: (数字)9783031255380

ISBN: (纸本)9783031255373

In the resource-constrained environment such as the Internet of Things, the windowed Non-Adjacent-Form (wNAF) representation is usually used to improve the calculation speed of the scalar multiplication of ECDSA. This paper presents a practical cache side channel attack on ECDSA implementations which use wNAF representation. Compared with existing works, our method exploits more information from the cache side channels, which is then efficiently used to construct lattice attacks in the ECDSA private key recovery. First, we additionally monitor the invert function which is related to the sign of the wNAF digits, and obtain a Double-Add-Invert chain through the Flush+Flush cache side channel. Then, we develop effective methods extracting 154.2 bits information of the ephemeral key per signature for 256-bit ECDSA from this chain, much more than the best known result which extracts 105.8 bits per signature. Finally, to efficiently use the extracted information, we convert the problem of recovering the private key to the Hidden Number Problem (HNP) and the Extended Hidden Number Problem (EHNP) respectively, which are solved by lattice reduction algorithms. We applied the attack on ECDSA with the secp256k1 curve in OpenSSL 1.1.0h. The experimental results show that only 3 signatures are enough to recover the private key. To the best of our knowledge, this work exploits the signs of the wNAF representation, along with the Double-Add chain against ECDSA, to recover the private key with the least number of signatures. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Device-to-Device Communications aided Integrated Sensing and Communication Networks: A Joint Design of Bandwidth and Power Allocations

Device-to-Device Communications aided Integrated Sensing and...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Dou, Chenglong Huang, Ning Wu, Yuan Qian, Liping Quek, Tony Q.S. University of Macau State Key Laboratory of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519301 China Zhejiang University of Technology College of Information Engineering Hangzhou310023 China Singapore University of Technology and Design 487372 Singapore

ISBN: (纸本)9798350351255

Integrated sensing and communication (ISAC) networks constitute a crucial paradigm for facilitating numerous advanced services in future wireless networks. This paper investigates the joint bandwidth and power allocations for device-to-device (D2D) communications aided ISAC in which D2D pairs complete their data transmissions by using the bandwidth allocated by the base station (BS) while providing sensing services for the BS. To this end, we formulate a joint optimization of bandwidth allocation and power allocations for both the target sensing and data transmission of each D2D pair, with the objective of maximizing a system-wise gain that accounts for both performances of target sensing and D2D data transmission. Despite the formulated optimization problem is strictly non-convex, we develop an efficient algorithm based on Lagrangian duality and sequential convex programming for solving it. Simulation results demonstrate that our proposed D2D communications aided ISAC is both accurate and efficient over several benchmark schemes. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

HRSE: Heterogeneous Reliable-Aware SFC Embedding by DRL with Greedy Rules in SAGIN

HRSE: Heterogeneous Reliable-Aware SFC Embedding by DRL with...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Kaixin Qin Songtao Guo Guiyan Liu Yue Zeng College of Computer Science Chongqing University Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education Shanghai Department of Computer Science and Technology The State Key Laboratory for Novel Software Technology Nanjing University

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Ensuring the quality of service (QoS) in the Space-Air-Ground Integrated Network (SAGIN) requires implementing appropriate service function chain (SFC) embedding strategies to provide reliable general services and AI services. However, the complicated topology, limited infrastructure resources, and the heterogeneity in hardware and software in SAGIN hinder existing reliable embedding solutions from delivering high QoS. To address the challenges, this paper takes into account the heterogeneous reliable-aware SFC embedding (HRSE) problem in SAGIN. Specifically, we formulate the HRSE problem as a nonlinear integer programming problem that is NP-hard. Subsequently, an algorithm called HRSFCEA, which consists of deep reinforcement learning (DRL) and greedy rules, is proposed to tackle the challenges. Initially, leveraging the autonomous decision-making capability of DRL, SFC embedding is executed to select backups efficiently. The proposed algorithm reduces frequent trial and error by modifying its actions. Next, the paper gives the algorithm analysis including the complexity and unreliable environment. Finally, simulation results based on real-world datasets demonstrate that the DRL scheme converges to high rewards with minimal differences across varying numbers of hidden layer neurons. The proposed algorithm can improve the acceptance rate by up to 82% while incurring no more than 5% additional cost compared to the state-of-art algorithms.

关键词： Service function chaining computer network reliability Software algorithms Quality of service Space-air-ground integrated networks Reliability engineering Deep reinforcement learning Software Software reliability Topology

来源：评论

学校读者我要写书评

暂无评论

Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction 39

Details Enhancement in Unsigned Distance Field Learning for ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Cheng Hou, Fei Wang, Wencheng Qin, Hong Zhang, Zhebin He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Advanced Interdisciplinary Sciences University of Chinese Academy of Sciences China Department of Computer Science Stony Brook University United States InnoPeak Technology United States College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and DCUDF for extracting the local minimal average distance surface. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Action recognition through fusion of sEMG and skeletal data in feature level

引用

Journal of Ambient Intelligence and Humanized Computing 2022年第9期13卷 4125-4134页

作者： Wang, Xinming Ding, Weili Bian, Shuangshuang Liu, Honghai Department of Automation Institute of Electrical Engineering Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Yanshan University 438 West of Hebei Avenue Haigang District Qinhuangdao066004 China School of Mechanical Engineering and Automation State Key Laboratory of Robotics and Systems Harbin Institute of Technology Shenzhen Nanshan District Shenzhen518055 China

Human action can be recognized through a unimodal way. However, the information obtained from a single mode is limited due to the fact that a single mode contains only one type of physical attribute. Therefore, it is motivational to improve the accuracy of actions through fusion of two different complementary modality, which are the surface electromyography (sEMG) and the skeletal data. In this paper, we propose a general framework of fusion of sEMG signals and skeletal data. Firstly, vector of locally aggregated descriptor (VLAD) was extracted from sEMG sequences and skeletal sequences, respectively. Secondly, features obtained from sEMG and skeletal data are mapped through different weighted kernels using multiple kernel learning. Finally, the classification results are obtained through the model of multiple kernel learning. A dataset of 18 types of human actions is collected via KinectV2 and Thalmic Myo armband to verify our ideas. The experimental results show that the accuracy of human action recognition are improved by combining skeletal data with sEMG signals. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

What limits limits?

引用

National science Review 2021年第1期8卷 11-14页

作者： Yong-Chun Liu Kun Huang Yun-Feng Xiao Lan Yang Cheng-Wei Qiu State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Frontier Science Center for Quantum Information Tsinghua University Department of Optics and Optical Engineering University of Science and Technology of China State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics School of Physics Peking University Department of Electrical and Systems Engineering Washington University Department of Electrical and Computer Engineering National University of Singapore

There are fundamental rules and principles setting the limits of physical systems. It triggers an interesting thought—can we break the limits under specific circumstances? A realistic system can only provide limited functionalities because its performance is physically constrained by some fundamental principles.‘Breaking the limit’, which usually implies that the capability of a system could be enhanced significantly,

关键词：

来源：评论

学校读者我要写书评

暂无评论

DHAKR: Learning Deep Hierarchical Attention-Based Kernelized Representations for Graph Classification 39

DHAKR: Learning Deep Hierarchical Attention-Based Kernelized...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Qian, Feifei Bai, Lu Cui, Lixin Li, Ming Lyu, Ziyu Du, Hangyuan Hancock, Edwin School of Artificial Intelligence Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing Normal University Beijing China School of Information Central University of Finance and Economics Beijing China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China Zhejiang Institute of Optoelectronics Jinhua China School of Cyber Science and Technology Sun Yat-Sen University Shenzhen China School of Computer and Information Technology Shanxi University Taiyuan China Department of Computer Science University of York York United Kingdom

ISBN: (纸本)157735897X

Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-Based Kernelized Representations (DHAKR) for graph classification. To this end, we commence by learning an assignment matrix to hierarchically map the substructure invariants into a set of composite invariants, resulting in hierarchical kernelized representations for graphs. Moreover, we introduce the feature-channel attention mechanism to capture the interdependencies between different substructure invariants that will be converged into the composite invariants, addressing the shortcoming of discarding the importance of different substructures arising in most existing R-convolution graph kernels. We show that the proposed DHAKR model can adaptively compute the kernel-based similarity between graphs, identifying the common structural patterns over all graphs. Experiments demonstrate the effectiveness of the proposed DHAKR model. Copyright © 2025, Association for the Advancement of Artificia Intelligence (***). All rights reserved.

关键词： Deep 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：