检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Zeng, Yuning Zhu, Xizhong Xiang, Guoqing Hao, Zhijian Zhang, Peng Huang, Xiaofeng Yan, Wei Peking University School of Software and Microelectronics Beijing China Advanced Institute of Information Technology Peking University Beijing China Peking University Shenzhen Guraduate School School of Electronic and Computer Engineering Shenzhen China Fudan University State Key Laboratory of ASIC System Shanghai China Hangzhou Dianzi University School of Communication Engineering Hangzhou China

ISBN: (纸本)9781665441544

The latest generation of video coding standards has significantly improved video coding performance. The third generation of audio video coding standards (AVS3) is one of these latest standards. However, due to the more flexible block partition mechanism in AVS3, the computational overhead brought by fractional-pixel motion estimation (FME) increases significantly, making it more difficult to implement a real-time FME hardware. In this paper, a parallel and pipelined hardware architecture supporting block sizes from 4x4 to 64x64 is proposed for FME in AVS3, and it is specially designed for coding tree unit (CTU)-level pipelined architecture of AVS3 encoder. Three necessary modules are developed in this architecture. The first module concerns derivation of motion vector predictors (MVPs). The second module is used to derive fractional-pixel motion vectors (FMVs) of coding units (CUs) partitioned by Binary-tree (BT) and Quad-Tree (QT) mechanisms. And a motion vector substitution (MVS) module is proposed to substitute the FMVs of the remaining CUs with the FMVs derived in the second module. Experimental results show that the proposed methods suffer only 0.62% performance degradation in BD-Rate. Furthermore, the architecture is implemented on XILINX ALVEO U250 FPGA at 400 MHz and the presented FME hardware design can support the real-time encoding of 4K@30fps. © 2022 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Camouflaged Object Segmentation

Few-Shot Camouflaged Object Segmentation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziqiu Wang Yuying Li Yang Yang Yamin Li Gaoyang Liu Key Laboratory of Intelligent Sensing System and Security (Ministry of Education) School of Artificial Intelligence Hubei University Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In the domain of computer vision, Camouflaged Object Segmentation (COS) is a crucial task aimed at identifying objects that blend into their surroundings, with applications spanning diverse sectors such as military, medical, and beyond. Traditional COS techniques, which primarily depend on supervised learning, necessitate large-scale labeled datasets. However, the acquisition of sufficient camouflage images for such purposes is often constrained due to their scarcity and the high cost of manual annotation. Additionally, these conventional methods frequently struggle to generalize to novel, unseen classes. In response to these challenges, this paper proposes the Camouflage Few-Shot (CAMFS) framework, an innovative approach integrating few-shot learning into COS. The CAMFS framework comprises two main components: the Camouflaged-Meta module, which converts the semantic information of camouflaged objects into compact feature vectors to facilitate knowledge transfer from support to query images; and the Camouflaged-Base module, focused on refining edge detection and enhancing the contrast between foreground and background elements. To overcome the limitations of existing COS datasets, which are primarily designed for supervised learning, we have developed the COS-FSS dataset, the first public few-shot COS dataset. It is based on the COD10K dataset and supplemented with approximately 3200 additional camouflage images. We conducted extensive evaluations of our CAMFS framework on the COS-FSS dataset. Compared to existing COS models, CAMFS demonstrates an average improvement of 5.7% in S α and 14.02% in $F_\beta ^w$, while against few-shot segmentation models, it achieves a 5.97% increase in m-IoU. The dataset and additional resources are available at https://***/CAM-FSS/FSS-COD.

关键词： Image segmentation Military computing Supervised learning Semantics Refining Neural networks Object segmentation

来源：评论

学校读者我要写书评

暂无评论

BLDTS: Blockchain-based Lightweight Data Trusted Sharing Scheme for Internet of Vehicles

BLDTS: Blockchain-based Lightweight Data Trusted Sharing Sch...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Haoran Lin Zhongyuan Yu Guijuan Wang Anming Dong Xiang Tian School of Computer Science Qufu Normal University Rizhao China School of Information Science and Engineering Lanzhou University Lanzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Ensuring safe and reliable data sharing is crucial for the development of Internet of Vehicles (IoV) technology. To provide a trusted data environment for IoV and enable traditional consensus algorithms to meet the high dynamic requirements of the IoV. In this article, we propose a blockchain-based data sharing scheme for IoV (BLDTS) to achieve secure and trusted sharing. First, we design a false information identification strategy that utilizes a bayesian inference model to determine the authenticity of shared data with the assistance of reputation value. Second, the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is used to construct a novel lightweight consensus mechanism based on vehicle reputation values and traffic environment factors, and the nodes with high scores were selected as participants in the consensus, which can reduce the computational overhead. Finally, experimental results show that our scheme has advantages in improving the accuracy of false message identification and consensus efficiency.

关键词： Data privacy Federated learning Heuristic algorithms Bayes methods Consensus protocol Reliability Vehicle dynamics Protection Fake news Internet of Vehicles

来源：评论

学校读者我要写书评

暂无评论

SFDE-net: A Spatial-Frequency Domain Feature Enhancement Network for Cloud Detection

SFDE-net: A Spatial-Frequency Domain Feature Enhancement Net...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Baotong Su Siyan Li Wenguang Zheng Yao Chen The School of Computer Science and Engineering Tianjin University of Technology Tianjin China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences and Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Cloud detection is a crucial step in the preprocessing of satellite remote sensing images. Existing methods tend to have misjudgments when dealing with specific scenarios, such as challenges in distinguishing thin clouds from the background and addressing missing cloud boundaries. To solve this problem, we designed a novel Spatial–Frequency Domain Feature Enhancement Block (SFDE) embedded in a U-shaped network called SFDE-net. SFDE consists of three units: the Dual Frequency Feature Unit (DFF), the Spatial Domain Feature Unit (SDF), and the Cross-Domain Feature Fusion Unit (CDF). DFF globally learns the boundaries and overall structure of clouds in the frequency domain, SDF captures fine-grained information in the spatial domain, and CDF adaptively fuses features from both DFF and SDF. Our method’s effectiveness was evaluated on two public datasets, GF-1 WFV and LandSat8. Extensive experiments demonstrated that the proposed SFDE-net achieved accurate detection accuracy and outperformed several state-of-the-art methods.

关键词： Earth Accuracy Satellites Artificial satellites Fuses Frequency-domain analysis Merging

来源：评论

学校读者我要写书评

暂无评论

Dockformer: A transformer-based molecular docking paradigm for large-scale virtual screening

arXiv

引用

arXiv 2024年

作者： Yang, Zhangfan Ji, Junkai He, Shan Li, Jianqiang He, Tiantian Bai, Ruibin Zhu, Zexuan Ong, Yew Soon School of Computer Science University of Nottingham Ningbo Ningbo315199 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore138632 Singapore School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom School of Computer Science and Engineering Nanyang Technological University Nanyang Avenue 639798 Singapore

Molecular docking is a crucial step in drug development, which enables the virtual screening of compound libraries to identify potential ligands that target proteins of interest. However, the computational complexity of traditional docking models increases as the size of the compound library increases. Recently, deep learning algorithms can provide data-driven research and development models to increase the speed of the docking process. Unfortunately, few models can achieve superior screening performance compared to that of traditional models. Therefore, a novel deep learning-based docking approach named Dockformer is introduced in this study. Dockformer leverages multimodal information to capture the geometric topology and structural knowledge of molecules and can directly generate binding conformations with the corresponding confidence measures in an end-to-end manner. The experimental results show that Dockformer achieves success rates of 90.53% and 82.71% on the PDBbind core set and PoseBusters benchmarks, respectively, and more than a 100-fold increase in the inference process speed, outperforming almost all state-of-the-art docking methods. In addition, the ability of Dockformer to identify the main protease inhibitors of coronaviruses is demonstrated in a real-world virtual screening scenario. Considering its high docking accuracy and screening efficiency, Dockformer can be regarded as a powerful and robust tool in the field of drug design. © 2024, CC BY-NC-ND.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

Downstream-agnostic Adversarial Examples

引用

International Conference on computer Vision (ICCV)

作者： Ziqi Zhou Shengshan Hu Ruizhi Zhao Qian Wang Leo Yu Zhang Junhui Hou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan University School of Information and Communication Technology Griffith University Department of Computer Science City University of Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial *** this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://***/CGCL-codes/AdvEncoder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Method for constructing multi-dimensional feature map of malicious code 5

Method for constructing multi-dimensional feature map of mal...

引用

2020 5th International Seminar on computer Technology, Mechanical and Electrical engineering, ISCME 2020

作者： Ma, Haocong Zhang, Ji Zhou, Junhua Zhai, Xiang Xue, Junjie Ji, Hang State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing100854 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing100854 China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing100854 China

Malicious code is characterized by a large number of types, rapid increase in number, continuous update of transmission routes, and continuous enhancement of back analysis and back detection methods. Therefore, how to effectively detect and analyze malicious code has been a problem of great concern. This paper studies the features of binary file and disassembly file of malicious code, introduces the concept of information gain, and proposes a method to construct the multi-dimensional characteristic graph of malicious code. Finally, the convolutional neural network is used to classify the multi-dimensional feature graph of malicious code, which provides a new idea for the feature extraction of malicious code. © Published under licence by IOP Publishing Ltd.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

A LiDAR-Assist Yaw Misalignment Compensation Method Based on Machine Learning Algorithms

A LiDAR-Assist Yaw Misalignment Compensation Method Based on...

引用

Chinese Control Conference (CCC)

作者： Pei Chen Zhongwei Lin Zihan Zhang Zhen Xie State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing P. R. China

Yaw misalignment is common in the yaw system control of wind turbines, resulting in reduced power generation efficiency and increased load. The advantage of LiDAR is that the accuracy of wind measurement is greatly improved, while its disadvantage is that the cost remains high. In this paper, an efficient machine learning method for estimating LiDAR measurement, XGBoost, is used to establish the data-driven wind turbine yaw misalignment compensation framework. To choose a suitable algorithm, four machine learning algorithms are studied, namely Linear Regression, Random Forest, Gradient Boosting and XGBoost. Moreover, to verify the effectiveness of the proposed method, a 2MW WT was taken as the research object for filed testing, and the power generation was quantitatively evaluated under the three strategies of wind vane control, LiDAR control and ML algorithm control. The results show that the proposed yaw misalignment compensation method is feasible for field application. In this way, the yaw-to-wind error can be mitigated even after the LiDAR is removed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PseudoSC: A Binary Approximation to Stochastic Computing within Latent Operation-Space for Ultra-Lightweight on-Edge DNNs 23

PseudoSC: A Binary Approximation to Stochastic Computing wit...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Jihe Wang Zhaoqing Wang Danghui Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350323481

Recently, stochastic computing (SC) is increasingly popular in constructing MAC for on-edge DNNs benefiting from its outstanding energy-efficiency, including its adequate precision and gatelevel operation. However, current SC-DNN systems always include a lot of costly SNGs/APCs for inevitably switches between binary and stochastic domains, which mortgages incongruous resources to pay the "bill" of the domain-switches and impedes highly-concurrent deployments. In this work, PseudoSC, a binary approximation to low-discrepancy SC, is proposed to totally remove the domain-switch for SNG/APC-free SC-DNNs. Its basic idea is to virtually re-arrange a couple of stochastic operands into a 2-D latent op-space, in which, original Monte Carlo sampling can be partitioned into three sub-ops, i.e., two fixed binary-ops and a fractal recursion. In theory, the recursion forms an isomorphic partition of the sampling repeated in smaller scales until the binary base-case achieved, as a result, a SC-op is well approximated only with binary-ops. Based on above theory, a multi-lane micro-architecture is designed to unroll the recursion within a few cycles and its advantages on hardware saving is verified under popular DNNs. The evaluation shows that the DNN-models with our schemes achieve 98.7% accuracy of the fixed-point implementations, which significantly outperform other SOTA methods. In addition, its reduced structure improves the power efficiency by 3.67 times on average.

关键词： stochastic computing

来源：评论

学校读者我要写书评

暂无评论

Robust Phase Retrieval from Quantized and Noisy Measurements

Robust Phase Retrieval from Quantized and Noisy Measurements

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Yihong Gao Luteng Zhu Zhuoyang An Mingjie Shao Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong SAR China School of Information Science and Engineering Shandong University Qingdao China Computer School Beijing Information Science and Technology University Beijing China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331519315

ISBN: (纸本)9798331519322

The phase retrieval (PR) problem involves recovering a signal from amplitude-only measurements and has been extensively studied in various physical measurement and signal processing systems. Recently, there has been increasing interest in the quantized phase retrieval (QPR) problem, where the observed amplitude is quantized to binary values. The existing studies have focused on the noiseless case. In this paper, we address a robust QPR problem that accounts for both quantization and noise. We formulate the robust QPR problem using maximum-likelihood estimation (MLE), which results in a non-convex and challenging optimization problem due to the complexity of its likelihood function. To obtain a high-quality solution, we develop an expectation-maximization (EM) algorithm combined with the Wirtinger flow, allowing us to convert the problem into a more manageable form at each iteration. Our method is implemented on both randomly generated synthetic data and image reconstruction tasks. The results demonstrate that our approach significantly enhances signal recovery performance under the combined effects of quantization and noise. Additionally, the proposed method exhibits better runtime efficiency compared to existing approaches.

关键词： Maximum likelihood estimation Phase measurement Quantization (signal) Runtime Noise Signal processing algorithms Noise measurement Speech processing Optimization Synthetic data

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：