检索结果-内蒙古大学图书馆

A key frame extraction algorithm oriented for video copy detection based on PCC and the histogram of video frames

Journal of Computational Information Systems 2014年第16期10卷 6999-7006页

作者： Peng, Fei Qian, Qin Long, Min College of Computer Science and Electronics Engineering Hunan University Changsha China Key Laboratory for Embedded and Network Computing of Hunan Province Changsha China College of Computer and Communication Engineering Changsha University of Science and Technology Changsha China

Aim to improve the accuracy and the robustness of the video copy detection, a novel key frame extraction algorithm is proposed. The shot segmentation is accomplished by evaluating the Pearsons correlation coefficients (PCC) between adjacent frames, while the key frames are extracted by combining the boundary-based and visual content-based methods. Experimental results show that the proposed key frame extraction algorithm is effective, and it is robust against some content preserving video processing attacks for some existed video hash methods. It provides a novel effective method for key-frames extraction in the video copy detection. 1553-9105/Copyright © 2014 Binary Information Press

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Deep generative network for image inpainting with gradient semantics and spatial-smooth attention

引用

Journal of Visual communication and Image Representation 2024年 98卷

作者： Sheng, Ziqi Xu, Wenbo Lin, Cong Lu, Wei Ye, Long School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China Applied Laboratory of Dig Data and Education Statistics School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510320 China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China

As a powerful forgery operation in the image content security area, image inpainting based on deep generative networks can yield visually appealing outputs but often produces ambiguous artifacts, especially in boundary and high semantic areas. To address this issue, a novel end-to-end network with gradient semantics and spatial-smooth attention (GS-SSA) is proposed, which combines a gradient learning network and an image inpainting network. The gradient learning network is meant to properly anticipate the gradient semantics in the hole region and get a complete gradient semantic map. The image inpainting network utilizes the complete gradient semantic map to better repair the missing pixels and obtain the final inpainting results. Moreover, spatial-smooth attention is introduced into the image inpainting network, considering both the spatial structural relations and the surrounding information in the hole region. Experimental results on public datasets show the superiority of the proposed method, especially in large-hole region tasks. © 2023 Elsevier Inc.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Deployable Architecture Against Application-level DDoS Attacks

A Deployable Architecture Against Application-level DDoS Att...

引用

The 9th International Conference for Young Computer Scientists(第九届国际青年计算机大会)

作者： Xiaolin Chen Feng Wang Hui Deng Mu Mu Sanglu Lu Computer Science Department Chuxiong Normal University China State Key Laboratory of Novel Softwar Computer Appliance Key Lab of Yunnan Province China Computing Department Lancaster University United Kingdom State Key Laboratory of Novel Software Technology Nanjing University China

In application-level DDoS attacks, attackers mimic legitimate client behavior by sending proper-looking requests via bots. The previous DDoS solutions focus on bandwidth flooding attacks, and have encountered significant difficulty in deployment. This paper presents a deployable architecture that counts the application-level DDoS attacks against web servers by combining overlay and IP anycast. In this architecture, when a protected web server is under attacks, the traffic to the server will be redirected to an overlay via IP anycast. The overlay nodes provide effective protection to the server by the distributed filter, the distributed traffic control, and also by building a temporary collaborative edge web cache. We demonstrate that this novel architecture has strong incentives to deploy and is able to be deployed by a single ISP without any modifications to implementation of routers and end host. We then discuss its properties and design challenges.

关键词： Computer crime Service oriented architecture Web server Protection Bandwidth Floods Information filtering Information filters Traffic control Buildings

来源：评论

学校读者我要写书评

暂无评论

An Identification Method of Image-based for Output Pattern of Metamorphic Relation in Burnup Calculation Program 3

An Identification Method of Image-based for Output Pattern o...

引用

3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021

作者： Fu, Shengfu Yang, Xiaohua Li, Meng Wang, Fan Eng. and Technol. Res. Ctr. of Software Eval. and Test. for Intellectual Equipment of Hunan Province Hunan Prov. Hengyang421001 China CNNC Key Laboratory on High Trusted Computing Hunan Prov. Hengyang421001 China School of Computer Science and Technology University of South China Hunan Hengyang421001 China

ISBN: (纸本)9781665402675

It is challenging to verify the design and analysis software adequately for nuclear power areas because of the inflated cost, time-consuming benchmark problems development, and few verification examples. This situation is called the test oracle problem. Metamorphic testing cleverly combines the specific properties of physical equations and numerical algorithms with software verification. Without constructing numerical solutions or verification examples, it verifies the software by checking whether the input and output of multiple executions meet the metamorphic relations. Since metamorphic relation is the nature rules of physical models and numerical algorithms, it is not restricted to specific code implementation technology. Therefore, it is no doubt that metamorphic testing is a promising technique to alleviate the test oracle *** relation is the key to metamorphic testing, which consists of input pattern and output pattern. The former can be obtained through manual analysis by industry experts, while the latter does not have a system identification method. An output pattern identification method based on the solution figure has been introduced here. Specifically, the input pattern is received by artificially analyzing the physical property of the program under test. Next, a group of test inputs has been generated according to such patterns. The calculation results are received after those inputs drive the program. Moreover, the function form of the output pattern is guided by the image of the results. Finally, metamorphic relation is constructed by input pattern and output pattern. For a demonstration of this method's details, a nuclide burnup calculation code is employed here, namely NUIT. By investigating the resulting image of 3820 isotopes, their output pattern classification models have been established according to the burnup depth and nuclide density. It includes four categories and seventeen sub-categories. The verification of other burnup

关键词： Verification

来源：评论

学校读者我要写书评

暂无评论

Isolating Compiler Bugs by Generating Effective Witness Programs with Large Language Models

arXiv

引用

arXiv 2023年

作者： Tu, Haoxin Zhou, Zhide Jiang, He Yusuf, Imam Nur Bani Li, Yuxian Jiang, Lingxiao School of Software Dalian University of Technology Dalian China School of Computing and Information Systems Singapore Management University Singapore Singapore Key Laboratory for Ubiquitous Network Service Software of Liaoning Province China DUT Artificial Intelligence Dalian China

Compiler bugs pose a significant threat to safety-critical applications, and promptly as well as effectively isolating these bugs is crucial for assuring the quality of compilers. However, the limited availability of debugging information on reported bugs complicates the compiler bug isolation task. Existing compiler bug isolation approaches convert the problem into a test program mutation problem, but they are still limited by ineffective mutation strategies or high human effort requirements. Drawing inspiration from the recent progress of pre-trained Large Language Models (LLMs), such as ChatGPT, in code generation, we propose a new approach named LLM4CBI to utilize LLMs to generate effective test programs for compiler bug isolation. However, using LLMs directly for test program mutation may not yield the desired results due to the challenges associated with formulating precise prompts and selecting specialized prompts. To overcome the challenges, three new components are designed in LLM4CBI. First, LLM4CBI utilizes a program complexity-guided prompt production component, which leverages data and control flow analysis to identify the most valuable variables and locations in programs for mutation. Second, LLM4CBI employs a memorized prompt selection component, which adopts reinforcement learning to select specialized prompts for mutating test programs continuously. Third, a test program validation component is proposed to select specialized feedback prompts to avoid repeating the same mistakes during the mutation process. Compared with the state-of-theart approaches (DiWi and RecBi) over 120 real bugs from the two most popular compilers, namely GCC and LLVM, our evaluation demonstrates the advantages of LLM4CBI: It can isolate 69.70%/21.74% and 24.44%/8.92% more bugs than DiWi and RecBi within Top-1/Top-5 ranked results. Additionally, we demonstrate that the LLMs component (i.e., GPT-3.5) used in LLM4CBI can be easily replaced by other LLMs while still achieving re

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A straightforward method to judge the completeness of a polymorphic gate set

arXiv

引用

arXiv 2017年

作者： Li, Zhifang Luo, Wenjian Yue, Lihua Wang, Xufa School of Computer Science and Technology University of Science and Technology of China Hefei230027 China Anhui Key Laboratory of Software in Computing and Communication University of Science and Technology of China Hefei230027 China

Polymorphic circuits are a special kind of circuits which possess some different build-in functions and these functions are activated by environment parameters, like light and VDD. Some theories have been proposed to guide the design of polymorphic circuits, including the definition of complete polymorphic gate sets and algorithms to judge the completeness of a polymorphic gate set. However, the previous algorithms have to enumerate all the polymorphic signals for judging the completeness of a polymorphic gate set, and it is not easy to be conducted manually. In this paper, a straightforward method is proposed to judge the completeness of a polymorphic gate set. And the correctness of the straightforward method is proved theoretically. Some examples are given to show that the proposed method could be conducted step by step. Its actual computing cost is usually low, and it is suitable for manual operation. Copyright © 2017, The Authors. All rights reserved.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Localized Adaptive Channel and Power Selection With TinyML (LACPSA) in Dense IEEE 802.11 WLANs

Localized Adaptive Channel and Power Selection With TinyML (...

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Khalid Ibrahim Qureshi Cheng Lu Ruoheng Luo Muhammad Ali Lodhi Lei Wang Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University China

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

In dense IEEE 802.11 WLANs, optimized channel allocation and transmission power control are crucial for miti- gating interference and congestion. Traditional approaches face significant challenges due to limited channels and dynamic traffic patterns. To address these issues, we propose a novel scheme wherein TinyML models are directly integrated into access points (APs) for adaptive channel optimization and transmission power control. This distributed approach empowers APs to optimize settings autonomously based on their local information, reducing reliance on central controllers and enhancing scalability. Leveraging compact TinyML models enables rapid decision- making, allowing APs to adapt to network changes promptly. By dynamically adjusting channel optimization and transmission power based on signal strength, interference levels, and traffic load, interference can be minimized, thereby improving network performance. Through extensive simulations, we demonstrate a significant reduction in interference compared to traditional approaches. Our proposed distributed solution enhances network resilience and flexibility, making it more suitable for real-world deployment scenarios where conditions change rapidly. The integration of TinyML into the network presents a promising approach for future WLAN optimization efforts.

关键词： Adaptation models Wireless LAN Tiny machine learning Power control Interference Channel allocation Traffic control Optimization IEEE 802.11 Standard Load modeling

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach for scalable sub-tree anonymization over big data using MapReduce on cloud

A hybrid approach for scalable sub-tree anonymization over b...

引用

作者： Zhang, Xuyun Liu, Chang Nepal, Surya Yang, Chi Dou, Wanchun Chen, Jinjun Faculty of Engineering and Information Technology University of Technology Sydney PO Box 123 Broadway NSW 2007 Australia Centre for Information and Communication Technologies Commonwealth Scientific and Industrial Research Organisation Cnr Vimiera and Pembroke Roads Marsfield NSW 2122 Australia State Key Laboratory for Novel Software Technology Nanjing University 22 Hankou Road Nanjing Jiangsu Province 210093 China

In big data applications, data privacy is one of the most concerned issues because processing large-scale privacy-sensitive data sets often requires computation resources provisioned by public cloud services. Sub-tree data anonymization is a widely adopted scheme to anonymize data sets for privacy preservation. Top-Down Specialization (TDS) and Bottom-Up Generalization (BUG) are two ways to fulfill sub-tree anonymization. However, existing approaches for sub-tree anonymization fall short of parallelization capability, thereby lacking scalability in handling big data in cloud. Still, either TDS or BUG individually suffers from poor performance for certain valuing of k-anonymity parameter. In this paper, we propose a hybrid approach that combines TDS and BUG together for efficient sub-tree anonymization over big data. Further, we design MapReduce algorithms for the two components (TDS and BUG) to gain high scalability. Experiment evaluation demonstrates that the hybrid approach significantly improves the scalability and efficiency of sub-tree anonymization scheme over existing approaches. © 2014 Elsevier Inc.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Learning aggregated transmission propagation networks for haze removal and beyond

arXiv

引用

arXiv 2017年

作者： Liu, Risheng Fan, Xin Hou, Minjun Jiang, Zhiying Luo, Zhongxuan Zhang, Lei DUT-RU International School of Information Science and Engineering Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian University of Technology Dalian Department of Computing Hong Kong Polytechnic University

Single image dehazing is an important low-level vision task with many applications. Early researches have inves-tigated different kinds of visual priors to address this problem. However, they may fail when their assumptions are not valid on specific images. Recent deep networks also achieve relatively good performance in this task. But unfortunately, due to the disappreciation of rich physical rules in hazes, large amounts of data are required for their training. More importantly, they may still fail when there exist completely different haze distributions in testing images. By considering the collaborations of these two perspectives, this paper designs a novel residual architecture to aggregate both prior (i.e., domain knowledge) and data (i.e., haze distribution) information to propagate transmissions for scene ra-diance estimation. We further present a variational energy based perspective to investigate the intrinsic propagation behavior of our aggregated deep model. In this way, we actually bridge the gap between prior driven models and data driven networks and leverage advantages but avoid limitations of previous dehazing approaches. A lightweight learning framework is proposed to train our propagation network. Finally, by introducing a task-aware image separation formulation with a flexible optimization scheme, we extend the proposed model for more challenging vision tasks, such as underwater image enhancement and single image rain removal. Experiments on both synthetic and real-world images demonstrate the effectiveness and efficiency of the proposed framework. Copyright © 2017, The Authors. All rights reserved.

关键词： Domain Knowledge

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：