检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Xiaoliang Shen, Fu-Rao Han, Feng Zhao, Jian Nie, Changhai State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns. Existing research primarily focuses on transferability to different FR models, overlooking the direct transferability to victim's face images, which is a practical threat in real-world scenarios. In this study, we propose a novel adversarial attack method that considers both the transferability to the FR model and the victim's face image, called NerfTAP. Leveraging Neural Radiance Fields (NeRF)-based 3D Generative Adversarial Network (GAN), we generate new view face images for the source and target subjects to enhance transferability of adversarial patches. We introduce a style consistency loss to ensure the visual similarity between the adversarial UV map and the target UV map under a 0-1 mask, enhancing the effectiveness and naturalness of the generated adversarial face images. Extensive experiments and evaluations on various FR models demonstrate the superiority of our approach over existing attack techniques. Our work provides valuable insights for enhancing the robustness of FR systems in practical adversarial settings. © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Decentralized Counterfactual Value with Threat Detection in Multi-Agent Mixed Cooperative and Competitive Environment

SSRN

引用

SSRN 2023年

作者： Dong, Shaokang Li, Chao Yang, Shangdong Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science Nanjing University of Posts and Telecommunications China

This paper introduces a fully decentralized method to address the problem of general mixed cooperation and competition in multi-agent setting. There are two main types of traditional Multi-Agent Reinforcement Learning (MARL) methods. The first kind is communication-based method which is designed to achieve coordination to deal with the non-stationary problem. However, it causes great communication overhead and can only be applied in fully cooperative environment. Another kind of methods follows Centralized Training and Decentralized Execution (CTDE) framework, which needs a centralized critic in the training process resulting in the huge computational complexity as the number of agents grows. In addition, neither approach is fully decentralized, because they either need to communicate the implicit information, or need to know the rewards of other agents. Different to the above methods, this paper introduces a Decentralized Counterfactual Value (DCV) to model other agents' behaviors, combined with the Threat Detection mechanism to learn the latent competitive or cooperative relationship with others. Finally, we prove that our method DCVTD does not affect the convergence of the basic algorithm and validate that DCVTD outperforms other fully decentralized methods, CTDE methods and other agent modeling or social influence methods in the experiments. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Momentum Posterior Regularization for Multi-hop Dense Retrieval

arXiv

引用

arXiv 2024年

作者： Xia, Zehua Wu, Yuyang Xia, Yiyun Nguyen, Cam-Tu State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science Nanjing University China School of Artificial Intelligence Nanjing University China

Multi-hop question answering (QA) often requires sequential retrieval (multi-hop retrieval), where each hop retrieves missing knowledge based on information from previous hops. To facilitate more effective retrieval, we aim to distill knowledge from a posterior retrieval, which has access to posterior information like an answer, into a prior retrieval used during inference when such information is unavailable. Unfortunately, current methods for knowledge distillation in one-time retrieval are ineffective for multi-hop QA due to two issues: 1) Posterior information is often defined as the response (i.e. the answer), which may not clearly connect to the query without intermediate retrieval;and 2) The large knowledge gap between prior and posterior retrievals makes existing distillation methods unstable, even resulting in performance loss. As such, we propose MoPo (Momentum Posterior Regularization) with two key innovations: 1) Posterior information of one hop is defined as a query-focus summary from the golden knowledge of the previous and current hops;2) We develop an effective training strategy where the posterior retrieval is updated along with the prior retrieval via momentum moving average method, allowing smoother and effective distillation. Experiments on HotpotQA and StrategyQA demonstrate that MoPo outperforms existing baselines in both retrieval and downstream QA tasks‡ © 2024, CC BY-NC-SA.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Neural Super-Resolution for Real-Time Rendering with Radiance Demodulation

Neural Super-Resolution for Real-Time Rendering with Radianc...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jia Li Ziling Chen Xiaolong Wu Lu Wang Beibei Wang Lei Zhang Shandong University State Key Laboratory for Novel Software Technology Nanjing University School of Intelligence Science and Technology Nanjing University The Hong Kong Polytechnic University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

It is time-consuming to render high-resolution images in applications such as video games and virtual reality, and thus super-resolution technologies become increasingly popular for real-time rendering. However, it is challenging to preserve sharp texture details, keep the temporal stability and avoid the ghosting artifacts in real-time super-resolution rendering. To address this issue, we introduce radiance demodulation to separate the rendered image or radiance into a lighting component and a material component, considering the fact that the light component is smoother than the rendered image so that the high-resolution material component with detailed textures can be easily obtained. We perform the super-resolution on the lighting component only and re-modulate it with the high-resolution material component to obtain the final super-resolution image with more texture details. A reliable warping module is proposed by explicitly marking the occluded regions to avoid the ghosting artifacts. To further enhance the temporal stability, we design a frame-recurrent neural network and a temporal loss to aggregate the previous and current frames, which can better capture the spatial-temporal consistency among reconstructed frames. As a result, our method is able to produce temporally stable results in real-time rendering with high-quality details, even in the challenging 4 × 4 super-resolution scenarios. Code is available at: https://***/Riga2/NSRD.

关键词： Video games Superresolution Neural networks Lighting Virtual reality Rendering (computer graphics) Real-time 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

ATOM: Automated Black-Box Testing of Multi-Label Image Classification Systems

ATOM: Automated Black-Box Testing of Multi-Label Image Class...

引用

IEEE International Conference on Automated software Engineering (ASE)

作者： Shengyou Hu Huayao Wu Peng Wang Jing Chang Yongjun Tu Xiu Jiang Xintao Niu Changhai Nie Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University China Guangdong OPPO Mobile Telecommunications Corp. Ltd. China

Multi-label Image Classification Systems (MICSs) developed based on Deep Neural Networks (DNNs) are extensively used in people's daily life. Currently, although there are a variety of approaches to test DNN-based systems, they typically rely on the internals of DNNs to design test cases, and do not take the core specification of MICS (i.e., correctly recognizing multiple objects in a given image) into account. In this paper, we propose ATOM, an automated and systematic black-box testing framework for testing MICS. Specifically, ATOM exploits the label combination as the testing adequacy criteria, hoping to systematically examine the impact of correlations between a fixed number of labels on the classification ability of MICS. Then, ATOM leverages image search engine and natural language processing to find test images that are not only common to the real-world, but also relevant to target label combinations. Finally, ATOM combines metamorphic testing and label information to realize test oracle identification, based on which the ability of MICS in classifying different label combinations is evaluated. To evaluate the effectiveness of ATOM, we have performed experiments on two popular datasets of MICS, VOC and COCO (each with five state-of-the-art DNN models), and one real-world photo tagging application from our industrial partner. The experimental results reveal that the performance of current DNN-based MICSs remains less satisfactory even in recognizing correlations between only two labels, as ATOM triggers a total number of 6,049 such label combination related errors for all MICSs studied. In particular, ATOM reports 587 error-revealing images for the industrial MICS, in which 92% of them are confirmed by the developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficiency-First Fault-Tolerant Replica Scheduling Strategy for Reliability Constrained Cloud Application 18th

Efficiency-First Fault-Tolerant Replica Scheduling Strategy ...

引用

18th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2021

作者： Zhang, Yingxue Fan, Guisheng Yu, Huiqun Chen, Xingpeng Department of Computer Science and Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

ISBN: (纸本)9783030935702

Reliability requirement assurance is an important prerequisite for application execution in the cloud. Although copy management can improve the reliability of applications, it also brings a series of resource waste and overhead issues. Therefore, the efficiency-first fault-tolerant algorithm (EFFT) with minimum execution cost in the cloud application is proposed. This algorithm minimizes the execution cost of the application under the constraints of reliability, and solves the problem of excessive overhead caused by too many copies. The EFFT algorithm is divided into two stages: initial allocation and dynamic adjustment. On the initial allocation of EFFT algorithm, a sorting rule is defined to determine the priority of tasks and instances. During the adjustment phase, by defining an actual efficiency ratio indicator to measure the cost-effectiveness of an instance, the EFFT algorithm makes a good trade-off between cost and reliability in order to minimize execution costs. Run our algorithm on randomly generated parallel applications of different scales and compare the experimental results with four advanced algorithms. The experiments show that the performance of the algorithm we proposed is better than the other algorithms in terms of execution cost and fault tolerance. © 2022, IFIP International Federation for Information Processing.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Learners' states Monitoring Method Based on Face Recognition technology 12

Learners' States Monitoring Method Based on Face Recognition...

引用

12th International Conference on Identification, Information and Knowledge in the internet of Things, IIKI 2021

作者： Qiao, Xiaoyi Zheng, Xiangwei Sun, Xiaofang Li, Shuqin Zhang, Yuang School of Information Science and Engineering Shandong Normal University Jinan250014 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250014 China

At present, many scholars focus on the learners' states in online learning, however, a complete real-time monitoring system of learners' states has not been proposed. In order to better detect the learning process and provide learners with a basis for self-reflection, this paper describes a learners' states monitoring method based on face recognition technology (LSMFR). A learner monitoring system is developed to collect the learners' states in real-time through external cameras and record the tired blinking, yawning, head posture, and emotional expression of learners respectively. After a comprehensive analysis, the evaluation score of learners' states is obtained. In the running process of the system, information feedback is completed by recording the detection content in real-time and then states of learning effectiveness are generated. After learning for a short time, learners check the data record for self-reflection. The simulation test is carried out on the system and the analysis shows that the system achieves the correct analysis of the learners' states, and generates accurate evaluation scores. © 2022 The Authors. Published by Elsevier B.V.

关键词： face recognition learners' states procedure analysis real-time monitoring

来源：评论

学校读者我要写书评

暂无评论

Energy-saving Processors Two-phases Frequency Reduction Algorithm on Heterogeneous Embedded Systems

Energy-saving Processors Two-phases Frequency Reduction Algo...

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Weihong Huang Kuan Jiang Jing Huang Li Lisi Yufeng Xiao Zihao Deng School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China

Energy saving has become a key issue for heterogeneous embedded systems. Previous energy-saving methods attempt to minimize the energy consumption of applications in heterogeneous embedded systems subject to deadline constraints by reducing the processor frequency. However, good scheduling strategy can also minimize energy consumption to some extent. This paper proposes a novel energy-saving scheduling algorithm, called the Energy-saving Processors Two-phases Frequency Reduction (EPTFR) Algorithm. In the first stage, within the deadline constraints, the maximum working frequency of each processor is reasonably and synchronously reduced; in the second phase, when running sub-applications on the processor, under the constraints of the earliest start time and latest end time of sub-applications, the actual operating frequency of the processor is reasonably reduced. Finally, the effectiveness of the EPTFR algorithm is verified through numerical experiments, and the results show that the proposed EPTFR algorithm can achieve a significant energy-saving effect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Value of Information Optimization for Object Detection-Driven Joint Video Transmission and Processing in UAV-Enabled Wireless Networks

IEEE Journal on Miniaturization for Air and Space Systems

引用

IEEE Journal on Miniaturization for Air and Space Systems 2025年第2期6卷 59-69页

作者： Cheng, Nan Chen, Haoran Sun, Ruijin Ma, Longfei Zhou, Conghao Zhang, Yuan Hui, Yilong Xidian University State Key Laboratory of ISN School of Telecommunications Engineering Xi’an710071 China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Huzhou313001 China

In the wake of disasters, rapid and efficient search and rescue operations are essential. Unmanned aerial vehicles (UAVs) have become instrumental in such scenarios, providing real-time video streaming that can be used for object detection to locate survivors. This technology, however, faces significant challenges due to the limited communication and onboard computational resources, which are critical for processing and transmitting high-quality video data. To address these issues, this paper proposes a novel approach that leverages the concept of the value of information (VoI) to optimize the trade-off between the accuracy of object detection and the associated communication costs. By dynamically adjusting the video stream’s quality, the proposed system aims to ensure that the most valuable information is transmitted within the constraints of bandwidth and computational power. To operationalize this concept, we introduce a Deep reinforcement learning (DRL) algorithm that employs the soft actor-critic (SAC) method. The algorithm benefits from the integration of object features and contextual information extracted by ResNet50, which is then processed through a cross-attention structure within the critic network. Our simulation results indicate that our approach significantly enhances the VoI, achieving higher accuracy in object detection with better resource management compared to traditional strategies. © 2019 IEEE.

关键词： Drones

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：