检索结果-内蒙古大学图书馆

KubeSPT: Stateful Pod Teleportation for Service Resilience with Live Migration

IEEE Transactions on Services Computing 2025年第03期18卷 1500-1514页

作者： Zhang, Hansheng Wu, Song Fan, Hao Huang, Zhuo Xue, Weibin Yu, Chen Ibrahim, Shadi Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong China

Container orchestration systems, such as Kubernetes, streamline containerized application deployment. As more and more applications are being deployed in Kubernetes, there is an increasing need for rescheduling - relocating a running pod to different nodes - due to system upgrades, node failures, and load-balancing optimizations. Live migration, which transfers services from source nodes to target nodes with minimal downtime, is the ideal support for rescheduling. However, implementing live migration for pods that run stateful services is challenging, because Kubernetes manages pods as stateless. First, the current pod's network namespace initialization process causes a mismatch in the network state between the migrated pod and internal containers. Second, migrating the memory state results in extended downtime. Third, Kubernetes operations on pods do not consider preserving the state of the pods. Therefore, we propose KubeSPT to achieve live migration of stateful pods in rescheduling scenarios. Firstly, we synchronize the network state of pods and internal containers by controlling packet flow and implement fast service redirection. Secondly, we introduce a Hot data and Lazy-Restore method for memory restoration to reduce migration downtime. Finally, we decouple pod migration operations from other Kubernetes operations to ensure compatibility with live migration. Experimental results show that KubeSPT reduces downtime by 86%-93% compared to current rescheduling methods. © 2008-2012 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Sparse representation scheme with enhanced medium pixel intensity for face recognition

引用

CAAI Transactions on Intelligence technology 2024年第1期9卷 116-127页

作者： Xuexue Zhang Yongjun Zhang Zewei Wang Wei Long Weihao Gao Bob Zhang State Key Laboratory of Public Big Data Institute for Artificial IntelligenceCollege of Computer Science and TechnologyGuizhou UniversityGuiyangGuizhouChina Department of Computer and Information Science University of MacaoAvenida da UniversidadeTaipaMacaoChina

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test *** has been widely used in various image classification *** in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for *** deformable images such as human faces,pixels at the same location of different images of the same subject usually have different ***,extracting features and correctly classifying such deformable objects is very ***,the lighting,attitude and occlusion cause more *** the problems and challenges listed above,a novel image representation and classification algorithm is ***,the authors’algorithm generates virtual samples by a non-linear variation *** method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable *** combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the ***,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion *** weighting coefficients in the score fusion scheme are set entirely ***,the algorithm classifies the samples based on the final *** experimental results show that our method performs better classification than conventional sparse representation algorithms.

关键词： computer vision face recognition image classification image representation

来源：评论

学校读者我要写书评

暂无评论

Face Forgery Detection Based on Fine-Grained Clues and Noise Inconsistency

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 144-158页

作者： Zhang, Dengyong He, Ruiyi Liao, Xin Li, Feng Chen, Jiaxin Yang, Gaobo Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation the School of Computer and Communication Engineering Changsha410114 China Hunan University Changsha410082 China

Deepfake detection has gained increasing research attention in media forensics, and a variety of works have been produced. However, subtle artifacts might be eliminated by compression, and the convolutional neural networks (CNNs)-based detectors are invalidated for fake face images with compression. In this work, we propose a two-stream network for deepfake detection. We observed that high-frequency noise features and spatial features are inherently complementary to each other. Thus, both spatial features and high-frequency noise features are exploited for face forgery detection. Specifically, we design a double-frequency transformer module (DFTM) to guide the learning of spatial features from local artifact regions. To effectively fuse spatial features and high-frequency noise features, a dual-domain attention fusion module (DDAFM) is designed. We also introduce a local relationship constraint loss, which requires only image-level labels, for model training. We evaluate the proposed approach on five large-scale benchmark datasets, and extensive experimental results demonstrate the proposed approach outperforms most SOTA works. © 2024 IEEE.

关键词： Frequency domain analysis

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

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs 41

Keypoint-based Progressive Chain-of-Thought Distillation for...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Feng, Kaituo Li, Changsheng Zhang, Xiaolu Zhou, Jun Yuan, Ye Wang, Guoren Beijing Institute of Technology China Ant Group China Hebei Province Key Laboratory of Big Data Science and Intelligent Technology China

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Tokens within a rationale vary in significance, and treating them equally may fail to accurately mimic keypoint tokens, leading to reasoning errors. (ii) They usually distill knowledge by consistently predicting all the steps in a rationale, which falls short in distinguishing the learning order of step generation. This diverges from the human cognitive progression of starting with easy tasks and advancing to harder ones, resulting in sub-optimal outcomes. To this end, we propose a unified framework, called KPOD, to address these issues. Specifically, we propose a token weighting module utilizing mask learning to encourage accurate mimicry of keypoint tokens by the student during distillation. Besides, we develop an in-rationale progressive distillation strategy, starting with training the student to generate the final reasoning steps and gradually extending to cover the entire rationale. To accomplish this, a weighted token generation loss is proposed to assess step reasoning difficulty, and a value function is devised to schedule the progressive distillation by considering both step difficulty and question diversity. Extensive experiments on four reasoning benchmarks illustrate our KPOD outperforms previous methods by a large margin. Copyright 2024 by the author(s)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Structural insights, synthesis, and electrocatalysis of high entropy nanoparticles for fuel cell, metal-air battery, and water-splitting applications

引用

Progress in Natural science:Materials International 2024年第3期34卷 512-523页

作者： Xin Tong Hao Ye Yunrou Wu Xinxing Zhan Manqi Gu Shixia Luo Jiangning Gong Juan Tiana Yadian Xie School of Chemistry and Material Science Guizhou Normal University Center for the Physics of Low-Dimensional Materials School of Physics and Electronics School of Future Technology Henan University Key Laboratory of Low-Dimensional Materials and Big Data Guizhou Minzu University

High-entropy alloy nanoparticles(HEA-NPs) have recently sparked great interest in materials science. Their solidsolution states, derived from distinct HEA configurations, make them promising candidates for catalysts with exceptional activity, stability, and tunable performance. However, a comprehensive understanding of the underlying mechanisms governing their electrocatalytic behavior is still lacking, hindering the rational design of HEA electrocatalysts. This review summarizes the fundamental knowledge of HEA-NPs, including the structureactivity correlations of HEA-NPs, diverse synthesis strategies, and applications in electrochemical catalysis. The design strategies for guiding improvements in tunable performance were highlighted. The article concludes with insights, perspectives, and future directions, encapsulating the state-of-the-art knowledge and paving the way for further exploration in this dynamic field.

关键词： High-entropy alloy nanoparticles Structure-activity correlations Synthesis strategies Electrochemical catalysis

来源：评论

学校读者我要写书评

暂无评论

RUP2S- YOLO: An Improved YOLOv8-Based Algorithm for Dense Pedestrian Detection 5

RUP2S- YOLO: An Improved YOLOv8-Based Algorithm for Dense Pe...

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Wang, Juanmin Huang, Kun Pi, Jianyong College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guizhou Guiyang China

ISBN: (纸本)9798350385557

Dense pedestrian detection is a key research direction in the field of computer vision, which plays a significant role in large-scale crowded public spaces. It provides strong technical support for security assurance, traffic management, and behavioral analysis in public areas. To address the issue of missed detection of small-sized occluded pedestrians in dense scenarios, this paper proposes an improved detection algorithm based on YOLOv8, named RUP2S-YOLO. For the backbone network, the RFCBAM module is used to replace the convolution module to enhance the capability of capturing subtle features and better extract the characteristics of small-scale pedestrians;for the C2f module, the UKMS module is designed as a substitution aiming to improve the model's capacity to process information of different scales;for the detection head, the P2S module is introduced for the accurate positioning of small-scale targets. Experiments on dense pedestrian datasets show that the improved RUP2S-YOLO outperforms the original algorithm in terms of performance, achieving an AP50 of 82.8%, and an AP50:95 of 55.8%, which represents an increase of 2.2% and 2.8% respectively compared to the original algorithm. Meanwhile, in comparison with other leading pedestrian detection models, the improved YOLOv8 algorithm presented in this article also demonstrates competitive advantages. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Based Video Colorization Method Fusing Local Self-attention and Bidirectional Optical Flow 10th

A Transformer-Based Video Colorization Method Fusing Local S...

引用

10th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2024

作者： Yuan, Lin Duan, Xun Xiang, Lingjie Kong, Guangqian Wu, Yun State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9789819787456

Video colorization encounters two principal challenges: colorization quality and temporal flicker. Balancing colorization quality and temporal consistency is a significant challenge. To address the aforementioned issues, we employ the transformer model in the field of video colorization and introduce a pioneering video colorization method named VCTR. Initially, to guarantee the quality of video coloring, we employ a pretrained image coloring network to add color to the grayscale video frame. Next, the feature extraction module for VCTR is utilized to perform feature extraction and propagation on the color frames during the colorization process. Finally, the transformer module is designed to fully leverage local information via the local feature self-attention layer. Additionally, motion information from bidirectional optical flow is utilized to identify correlations across video frames for feature fusion, guaranteeing both the coloring effect and temporal consistency. The experimental results demonstrate that VCTR outperforms existing methods on two publicly available datasets, namely, DAVIS and Videvo. VCTR attains the top ranking in the long-series dataset, Videvo, based on the CTBI (Colorization and Temporal-Consistency Balance Index). This achievement underscores VCTR’s ability to strike a commendable balance between colorization quality and temporal consistency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Electricity Carbon Quota Trading Scheme based on Certificateless Signature and Blockchain

引用

Computer Modeling in Engineering & sciences 2024年第2期138卷 1695-1712页

作者： Xiaodong Yang Runze Diao Tao Liu Haoqi Wen Caifen Wang College of Computer Science and Engineering Northwest Normal UniversityLanzhou730070China Institute of China TelecomWanwei China TelecomWanwei Information Technology Co.Ltd.Lanzhou730030China College of Big Data and Internet Shenzhen Technology UniversityShenzhen518118China Key Laboratory of Cryptography and Data Analytics Northwest Normal UniversityLanzhou730070China

The carbon tradingmarket can promote“carbon peaking”and“carbon neutrality”at low cost,but carbon emission quotas face attacks such as data forgery,tampering,counterfeiting,and replay in the electricity trading *** signatures are a new cryptographic technology that can address traditional cryptography’s general essential certificate requirements and avoid the problem of crucial escrowbased on identity ***,most certificateless signatures still suffer fromvarious security *** present a secure and efficient certificateless signing scheme by examining the security of existing certificateless signature *** ensure the integrity and verifiability of electricity carbon quota trading,we propose an electricity carbon quota trading scheme based on a certificateless signature and *** scheme utilizes certificateless signatures to ensure the validity and nonrepudiation of transactions and adopts blockchain technology to achieve immutability and traceability in electricity carbon quota *** addition,validating electricity carbon quota transactions does not require time-consuming bilinear pairing *** results of the analysis indicate that our scheme meets existential unforgeability under adaptive selective message attacks,offers conditional identity privacy protection,resists replay attacks,and demonstrates high computing and communication performance.

关键词： Electricity carbon trading certificateless signature blockchain forgery attack carbon quota

来源：评论

学校读者我要写书评

暂无评论

NEURON-ENHANCED AUTOENCODER MATRIX COMPLETION AND COLLABORATIVE FILTERING: THEORY AND PRACTICE 12

NEURON-ENHANCED AUTOENCODER MATRIX COMPLETION AND COLLABORAT...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Fan, Jicong Chen, Rui Zhang, Zhao Ding, Chris H.Q. School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China School of Computer Science & Information Engineering Hefei University of Technology China

Neural networks have shown promising performance in collaborative filtering and matrix completion but the theoretical analysis is limited and there is still room for improvement in terms of the accuracy of recovering missing values. This paper presents a neuron-enhanced autoencoder matrix completion (AEMC-NE) method and applies it to collaborative filtering. Our AEMC-NE adds an element-wise autoencoder to each output of the main autoencoder to enhance the reconstruction capability. Thus it can adaptively learn an activation function for the output layer to approximate possibly complicated response functions in real data. We provide theoretical analysis for AEMC-NE as well as AEMC to investigate the generalization ability of autoencoder and deep learning in matrix completion, considering both missing completely at random and missing not at random. We show that the element-wise neural network has the potential to reduce the generalization error bound, the data sparsity can be useful, and the prediction performance is closely related to the difference between the numbers of variables and samples. The numerical results on synthetic data and five benchmark datasets demonstrated the effectiveness of AEMC-NE in comparison to many baselines. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Collaborative filtering

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：