检索结果-内蒙古大学图书馆

Application of improved virtual sample and sparse representation in face recognition

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1391-1402页

作者： Yongjun Zhang Zewei Wang Xuexue Zhang Zhongwei Cui Bob Zhang Jinrong Cui Lamin LJanneh College of Computer Science and Technology Guizhou UniversityGuiyangChina Big Data Science and Intelligent Engineering Research Institute Guizhou Education UniversityGuiyangChina School of Mathematics and Big Data Guizhou Education UniversityGuiyangChina Department of Computer and Information Science University of MacaoAvenida da UniversidadeTaipaMacaoChina School of Mathematics and Information South China Agricultural UniversityGuangzhouChina

Sparse representation plays an important role in the research of face *** a deformable sample classification task,face recognition is often used to test the performance of classification *** face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition ***,there may be significant differences between different image samples of the same face,which makes image classification very ***,how to build a robust virtual image representation becomes a vital *** solve the above problems,this paper proposes a novel image classification ***,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual ***,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,*** obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test *** two distances are converted into distance ***,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual *** fused score will determine the final classification *** experimental results show that the proposed method outperforms other typical sparse representation classification methods.

关键词： representation sample image

来源：评论

学校读者我要写书评

暂无评论

Obstacle-Avoiding Rectilinear Steiner Minimal Tree Algorithm Based on Deep Reinforcement Learning

Obstacle-Avoiding Rectilinear Steiner Minimal Tree Algorithm...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Lin, Zhenkun Zhu, Yuhan Huang, Xing Yang, Liliang Liu, Genggeng Fuzhou University College of Computer and Data Science Fuzhou China Northwestern Polytechnical University School of Computer Science Xi'an China

ISBN: (纸本)9798350312270

With the rapid development of the Industrial Internet of Things (IIoT), higher requirements have been put forward for hardware devices, and as the core part of hardware devices, the performance of chips is critical. The Obstacle-Avoiding Rectilinear Steiner Minimal Tree (OARSMT) problem is a classic issue in VLSI physical design, and having a shorter OARSMT can help reduce chip delays and energy consumption. This paper proposes a framework based on Deep Reinforcement Learning (DRL) to automatically learn and generate heuristic algorithms for solving the OARSMT problem. The core of our proposed method combines Graph Convolution Network (GCN) with DRL, where GCN extracts the graph-state feature information of Obstacle-Avoiding Steiner Tree (OAST) generated throughout the process, and DRL learns policy decisions under different graph states. Experimental results have confirmed our proposed framework outperforms existing manually designed work, indicating that our framework is a promising tool for solving the OARSMT problem. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ReCSA:a dedicated sort accelerator using ReRAM-based content addressable memory

引用

Frontiers of computer science 2023年第2期17卷 1-13页

作者： Huize LI Hai JIN Long ZHENG Yu HUANG Xiaofei LIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the increasing amount of data,there is an urgent need for efficient sorting algorithms to process large data *** sorting algorithms have attracted much attention because they can take advantage of different hardware's *** the traditional hardware sort accelerators suffer“memory wall”problems since their multiple rounds of data transmission between the memory and the *** this paper,we utilize the in-situ processing ability of the ReRAM crossbar to design a new ReCAM array that can process the matrix-vector multiplication operation and the vector-scalar comparison in the same array *** this designed ReCAM array,we present ReCSA,which is the first dedicated ReCAM-based sort *** hardware designs,we also develop algorithms to maximize memory utilization and minimize memory exchanges to improve sorting *** sorting algorithm in ReCSA can process various data types,such as integer,float,double,and *** also present experiments to evaluate the performance and energy efficiency against the state-of-the-art sort *** experimental results show that ReCSA has 90.92×,46.13×,27.38×,84.57×,and 3.36×speedups against CPU-,GPU-,FPGA-,NDP-,and PIM-based platforms when processing numeric data *** also has 24.82×,32.94×,and 18.22×performance improvement when processing string data sets compared with CPU-,GPU-,and FPGA-based platforms.

关键词： ReCAM parallel sorting architecture design processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Action Recognition Using Graph Convolutional Network with Pose Correction and Channel Topology Refinement

引用

computers, Materials & Continua 2025年第4期83卷 701-718页

作者： Yuxin Gao Xiaodong Duan Qiguo Dai School of Engineering Guangzhou College of Technology and BusinessFoshan528138China School of Computer Science and Engineering Dalian Minzu UniversityDalian116000China SEAC key Laboratory of Big Data Applied Technology Dalian Minzu UniversityDalian116000China

Graph convolutional network(GCN)as an essential tool in human action recognition tasks have achieved excellent performance in previous ***,most current skeleton-based action recognition using GCN methods use a shared topology,which cannot flexibly adapt to the diverse correlations between joints under different motion *** video-shooting angle or the occlusion of the body parts may bring about errors when extracting the human pose coordinates with estimation *** this work,we propose a novel graph convolutional learning framework,called PCCTR-GCN,which integrates pose correction and channel topology refinement for skeleton-based human action ***,a pose correction module(PCM)is introduced,which corrects the pose coordinates of the input network to reduce the error in pose feature ***,channel topology refinement graph convolution(CTR-GC)is employed,which can dynamically learn the topology features and aggregate joint features in different channel dimensions so as to enhance the performance of graph convolution networks in feature ***,considering that the joint stream and bone stream of skeleton data and their dynamic information are also important for distinguishing different actions,we employ a multi-stream data fusion approach to improve the network’s recognition *** evaluate the model using top-1 and top-5 classification *** the benchmark datasets iMiGUE and Kinetics,the top-1 classification accuracy reaches 55.08%and 36.5%,respectively,while the top-5 classification accuracy reaches 89.98%and 59.2%,*** the NTU dataset,for the two benchmark RGB+Dsettings(X-Sub and X-View),the classification accuracy achieves 89.7%and 95.4%,respectively.

关键词： Pose correction multi-stream fusion GCN action recognition

来源：评论

学校读者我要写书评

暂无评论

Inside and Inside: Efficient Anomaly Detection by Fully Capturing the Detailed Dynamics

Inside and Inside: Efficient Anomaly Detection by Fully Capt...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Tang, Ziyu Zhou, Xiren Chen, Ao Liu, Shikang Wei, Chuyang Chen, Huanhuan School of Computer Science and Technology University of Science and Technology of China Hefei China School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei China

ISBN: (纸本)9798350368741

Anomaly detection in sequential signals is gaining prominence, especially with limited training data and timeliness requirements. Fully extracting the data-inside changing information, we propose a novel Wavelet-Enhanced Reservoir Computing framework (WE-Res). Our framework uses Discrete Wavelet Transform (DWT) to decompose signals for multi-level detail and trend extraction recursively. Each level is fitted using an Echo State Network (ESN) respectively, extracting its inside dynamic features into fitted models. Integrating these dynamic features creates a "multi-level dynamic feature" that enhances signal representation, aiding in distinguishing between normal and anomalous patterns. We further introduce a dual-objective optimization to refine ESNs' reservoirs, increasing the fitting accuracy and improving category discrimination among the captured features. Validation on real-world data confirms our method's effectiveness, especially in data-limited scenarios and less training time compared to recent baselines. © 2025 IEEE.

关键词： Anomaly detection Dynamic Feature Model-Based Methods Reservoir computing Time-series signal

来源：评论

学校读者我要写书评

暂无评论

A High-Quality Adaptive Video Reconstruction Optimization Method Based on Compressed Sensing

引用

computer Modeling in Engineering & sciences 2023年第10期137卷 363-383页

作者： Yanjun Zhang Yongqiang He Jingbo Zhang Yaru Zhao Zhihua Cui Wensheng Zhang School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan030024China Department of Big Data and Intelligent Engineering Shanxi Institute of TechnologyYangquan045000China School of Computer Science Beijing University of TechnologyBeijing100124China The Institute of Automation Chinese Academy of Sciences(CAS)Beijing100049China

The video compression sensing method based onmulti hypothesis has attracted extensive attention in the research of video codec with limited ***,the formation of high-quality prediction blocks in the multi hypothesis prediction stage is a challenging *** resolve this problem,this paper constructs a novel compressed sensing-based high-quality adaptive video reconstruction *** includes the optimization of prediction blocks(OPBS),the selection of searchwindows and the use of neighborhood ***,the OPBS consists of two parts:the selection of blocks and the optimization of prediction *** combine the high-quality optimization reconstruction of foreground block with the residual reconstruction of the background block to improve the overall reconstruction effect of the video *** addition,most of the existing methods based on predictive residual reconstruction ignore the impact of search windows and reference frames on ***,Block-level search window(BSW)is constructed to cover the position of the optimal hypothesis block as much as *** maximize the availability of reference frames,Nearby reference frame information(NRFI)is designed to reconstruct the current *** proposed method effectively suppresses the influence of the fluctuation of the prediction block on reconstruction and improves the reconstruction *** results showthat the proposed compressed sensing-based high-quality adaptive video reconstruction optimization method significantly improves the reconstruction performance in both objective and supervisor quality.

关键词： Compressed sensing OPBS block-level search window nearby reference frame information evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Obstacle-Avoidance X-Architecture Steiner Minimal Tree Algorithm Based on Deep Reinforcement Learning

Obstacle-Avoidance X-Architecture Steiner Minimal Tree Algor...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： You, Jie Zhu, Yuhan Huang, Xing Yang, Liliang Liu, Genggeng Fuzhou University College of Computer and Data Science Fuzhou China Northwestern Polytechnical University School of Computer Science Xi'an China

ISBN: (纸本)9798350312270

In recent years, we have witnessed the rapid development of the Internet of Things (IoT) paradigm. A new computing paradigm, predictive intelligence, has been introduced into many IoT applications. In IoT applications, predictive intelligent devices must consider power and delay consumption. The goal of Very Large Scale Integration (VLSI) circuit routing problem is to minimize the wirelength to optimize chip delay. Therefore, VLSI routing problems have been widely applied in IoT. The X-architecture routing technology presents a promising solution that can reduce the number of vias, wirelength, and mold size significantly, thereby proving to be a highly practical approach. Moreover, with the shift of modern VLSI design towards system-on-chip paradigm, many uncrossable obstacles appear on the plane, thus Obstacle-Avoiding X-architecture Steiner Minimal Tree (OAXSMT) problem has attracted more and more attention. Most existing algorithms are troubled by poor wirelength quality or high construction time cost. Therefore, this paper proposes a method based on Deep Reinforcement Learning to construct an OAXSMT. First, an encoder based on heterogeneous graph transformer is designed to generate fixed-length encodings for each node. Second, an actor-critic decoder based on pointer network is designed to generate obstacle-avoiding X-architecture Steiner redundant tree. Finally, a fast evaluation strategy is designed to evaluate the quality of the redundant tree. Experimental results show that the routing results generated by the algorithm are superior to existing heuristic algorithms in terms of wirelength and runtime, and the algorithm also has certain generalization ability. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FusionRender: Harnessing WebGPU's Power for Enhanced Graphics Performance on Web Browsers 24

FusionRender: Harnessing WebGPU's Power for Enhanced Graphic...

引用

33rd ACM Web Conference, WWW 2024

作者： Bi, Weichen Ma, Yun Han, Yudong Chen, Yifan Tian, Deyu Du, Jiaqi Institute for Artificial Intelligence Peking University Beijing China College of Computer and Data Science Fuzhou University Fuzhou China School of Computer Science Peking University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China

ISBN: (纸本)9798400701719

Graphics rendering on web browsers serves as the foundation for numerous web applications. Compared with the widely employed WebGL, the next-generation web graphics API, WebGPU, demonstrates an enhanced capacity to adapt to modern GPU features, boasting more significant potential. However, our experiment shows that the performance of current graphics rendering frameworks based on WebGPU lags behind those built on WebGL. Such discrepancy primarily arises from an incomplete alignment with WebGPU's distinctive features. The individual rendering of each graphic leads to redundant communication between the CPU and GPU. To enhance the graphics performance on the web, we introduce the FusionRender to harness the power of WebGPU. To mitigate redundant communication, FusionRender assigns a unique signature to each object and employs these signatures for grouping, enabling the consolidation of graphics rendering whenever possible. In simulated experiments involving the rendering of multiple objects, FusionRender improves the rendering performance by 29.3%-122.1% compared with the existing optimal baseline. In real cases with more complex features, performance improvement ranges from 9.4% to 39.7%. Additionally, FusionRender exhibits robust performance enhancement across various devices and browsers. © 2024 ACM.

关键词： Web browsers

来源：评论

学校读者我要写书评

暂无评论

Latent Logic Tree Extraction for Event Sequence Explanation from LLMs 41

Latent Logic Tree Extraction for Event Sequence Explanation ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Song, Zitao Yang, Chao Wang, Chaojie An, Bo Li, Shuang School of Computer Science and Engineering Nanyang Technological University Singapore School of Data Science The Chinese University of Hong Kong Shenzhen China Skywork AI Singapore

Modern high-stakes systems, such as healthcare or robotics, often generate vast streaming event sequences. Our goal is to design an efficient, plug- and-play tool to elicit logic tree-based explanations from Large Language Models (LLMs) to provide customized insights into each observed event sequence. Built on the temporal point process model for events, our method employs the likelihood function as a score to evaluate generated logic trees. We propose an amortized Expectation-Maximization (EM) learning framework and treat the logic tree as latent variables. In the E-step, we evaluate the posterior distribution over the latent logic trees using an LLM prior and the likelihood of the observed event sequences. LLM provides a high-quality prior for the latent logic trees, however, since the posterior is built over a discrete combinatorial space, we cannot get the closed-form solution. We propose to generate logic tree samples from the posterior using a learnable GFlowNet, which is a diversity-seeking generator for structured discrete variables. The M-step employs the generated logic rules to approximate marginalization over the posterior, facilitating the learning of model parameters and refining the tunable LLM prior parameters. In the online setting, our locally built, lightweight model will iteratively extract the most relevant rules from LLMs for each sequence using only a few iterations. Empirical demonstrations showcase the promising performance and adaptability of our framework. Copyright 2024 by the author(s)

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Testing Most Distant Neighbor (MDN) Variants for Semi-Factual Explanations in XAI 32

Testing Most Distant Neighbor (MDN) Variants for Semi-Factua...

引用

Workshops at the 32nd International Conference on Case-Based Reasoning, ICCBR-WS 2024

作者： Aryal, Saugat Keane, Mark T. School of Computer Science University College Dublin Dublin Ireland Insight Centre for Data Analytics Dublin Ireland

Recently, Semi-factual explanations have gained popularity in the eXplainable AI (XAI) community. They provide "even if" justifications to indicate what key input features could change without changing the outcome. Although several methods have now been proposed to compute semi-factuals, the instance-based, Most Distant Neighbors (MDN) method has emerged in recent comprehensive tests to be quite competitive, even though was originally proposed as a naive benchmark. However, on some metrics MDN comes bottom of the class (e.g., sparsity). In this paper, we explore nine variants of the MDN method to determine whether its performance on some metrics can be improved relative to older methods by performing comprehensive tests on key metrics. The results show that there are MDN variants that perform better on some key metrics, but that some of the historical methods still do better. © 2024 Copyright for this paper by its authors.

关键词： Most Distant Neighbor Semi-Factual XAI XCBR

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：