检索结果-内蒙古大学图书馆

A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection

Machine Intelligence Research 2024年第4期21卷 684-703页

作者： Yun-Xiao Li Cheng-Li-Zhao Chen Shuai Li Ai-Min Hao Hong Qin State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China College of Computer Science and Technology China University of Petroleum(East China)Qingdao 266580China Department of Computer Science Stony Brook UniversityNew York 11794USA

Recently,a new research trend in our video salient object detection(VSOD)research community has focused on enhancing the detection results via model self-fine-tuning using sparsely mined high-quality keyframes from the given *** such a learning scheme is generally effective,it has a critical limitation,i.e.,the model learned on sparse frames only possesses weak generalization *** situation could become worse on“long”videos since they tend to have intensive scene ***,in such videos,the keyframe information from a longer time span is less relevant to the previous,which could also cause learning conflict and deteriorate the model ***,the learning scheme is usually incapable of handling complex pattern *** solve this problem,we propose a divide-and-conquer framework,which can convert a complex problem domain into multiple simple ***,we devise a novel background consistency analysis(BCA)which effectively divides the mined frames into disjoint *** for each group,we assign an individual deep model on it to capture its key attribute during the fine-tuning *** the testing phase,we design a model-matching strategy,which could dynamically select the best-matched model from those fine-tuned ones to handle the given testing *** experiments show that our method can adapt severe background appearance variation coupling with object movement and obtain robust saliency detection compared with the previous scheme and the state-of-the-art methods.

关键词： Video salient object detection background consistency analysis weakly supervised learning long-term information background shift.

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Automated Test Generation Tools for Java:Effectiveness and Challenges

引用

Journal of computer science & technology 2024年第3期39卷 715-736页

作者：刘相君余萍马晓星 State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China CCF ACM IEEE

Automated test generation tools enable test automation and further alleviate the low efficiency caused by writing hand-crafted test ***,existing automated tools are not mature enough to be widely used by software testing *** paper conducts an empirical study on the state-of-the-art automated tools for Java,i.e.,EvoSuite,Randoop,JDoop,JTeXpert,T3,and *** design a test workflow to facilitate the process,which can automatically run tools for test generation,collect data,and evaluate various ***,we conduct empirical analysis on these six tools and their related techniques from different aspects,i.e.,code coverage,mutation score,test suite size,readability,and real fault detection *** discuss about the benefits and drawbacks of hybrid techniques based on experimental ***,we introduce our experience in setting up and executing these tools,and summarize their usability and ***,we give some insights into automated tools in terms of test suite readability improvement,meaningful assertion generation,test suite reduction for random testing tools,and symbolic execution integration.

关键词： automated test generation search-based software testing random testing symbolic execution

来源：评论

学校读者我要写书评

暂无评论

Nonlinear dynamics of a circular curved cantilevered pipe conveying pulsating fluid based on the geometrically exact model

引用

Applied Mathematics and Mechanics(English Edition) 2024年第2期45卷 261-276页

作者： Runqing CAO Zilong GUO Wei CHEN Huliang DAI Lin WANG Department of Engineering Mechanics School of Aerospace EngineeringHuazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory for Engineering Structural Analysis and Safety Assessment Wuhan 430074China State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China

Due to the novel applications of flexible pipes conveying fluid in the field of soft robotics and biomedicine,the investigations on the mechanical responses of the pipes have attracted considerable *** fluid-structure interaction(FSI)between the pipe with a curved shape and the time-varying internal fluid flow brings a great challenge to the revelation of the dynamical behaviors of flexible pipes,especially when the pipe is highly flexible and usually undergoes large *** this work,the geometrically exact model(GEM)for a curved cantilevered pipe conveying pulsating fluid is developed based on the extended Hamilton's *** stability of the curved pipe with three different subtended angles is examined with the consideration of steady fluid *** attention is concentrated on the large-deformation resonance of circular pipes conveying pulsating fluid,which is often encountered in practical *** constructing bifurcation diagrams,oscillating shapes,phase portraits,time traces,and Poincarémaps,the dynamic responses of the curved pipe under various system parameters are *** mean flow velocity of the pulsating fluid is chosen to be either subcritical or *** numerical results show that the curved pipe conveying pulsating fluid can exhibit rich dynamical behaviors,including periodic and quasi-periodic *** is also found that the preferred instability type of a cantilevered curved pipe conveying steady fluid is mainly in the flutter of the second *** a moderate value of the mass ratio,however,a third-mode flutter may occur,which is quite different from that of a straight pipe system.

关键词： curved pipe conveying fluid pulsating fluid geometrically exact model(GEM) nonlinear dynamics parametric vibration flutter

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Framework for Expensive Multitask Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Tan, Shenglian Wang, Yong Sun, Guangyong Pang, Tong Tang, Ke School of Automation Central South University Changsha China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

This paper proposes a surrogate-assisted evolutionary framework (called SELF) to solve expensive multitask optimization problems (ExMTOPs). SELF consists of two main phases: global knowledge transfer phase and local knowledge transfer phase. In the former, a multitask Gaussian process model (MTGP) is established by fusing previously evaluated solutions of multiple optimization tasks. MTGP can capture task-relevant information and the knowledge of landscapes. Then, differential evolution assisted with MTGP is proposed to preselect high-quality candidates. During the preselection, the knowledge of landscapes is transferred among multiple optimization tasks for locating promising regions quickly. In the latter, for each optimization task, Bayesian optimization is adopted to improve the quality of the best individual in the population. Moreover, the improved best individuals in the populations of multiple optimization tasks are adaptively transferred based on a transfer probability, which is computed through the task-relevant information provided by MTGP. By combining these two phases, SELF not only achieves the tradeoff between exploration and exploitation, but also utilizes the global and local knowledge transfer to improve the efficiency for solving ExMTOPs. We test SELF on seven benchmark test problems in the IEEE CEC2017 evolutionary multitask optimization competition. The results demonstrate that the performance of SELF is better than that of other seven advanced methods. In addition, we also apply SELF to deal with two real-world ExMTOPs. The designs provided by SELF exhibit the best performance among all the compared methods, verifying the potential of SELF in practical engineering applications. IEEE

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Control of 2-D Semi-Markov Jump systems:A View from Mode Generation Mechanism

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 258-260页

作者： Yunzhe Men Jian Sun Jie Chen the National Key Laboratory of Autonomous Intelligent Unmanned Systems the School of AutomationBeijing Institute of TechnologyBeijing 100081 the Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China the Department of Control Science and Engineering Tongji UniversityShanghai 201804 the National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China

Dear Editor,Two-dimensional(2-D) systems have wide applications in image data processing,gas absorption and fluid dynamics analysis [1]-[3].When there exist abrupt changes in 2-D systems,they are usually modeled by 2-D Markov jump systems(MJSs) or 2-D semi-Markov jump systems(SMJSs).This letter investigates the control of 2-D SMJSs based on a novel mode generation mechanism,which could avoid mode ambiguousness phenomenon caused by the evolution of system mode in two different *** criterion that guarantees the almost surely exponential stability of the system is obtained.A thermal process is studied to demonstrate the availability of the proposed method.

关键词： Markov mode system

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Learning Algorithm Under Adversary Eavesdropping

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 448-456页

作者： Lei Xu Danya Xu Xinlei Yi Chao Deng Tianyou Chai Tao Yang the State Key Laboratory of Synthetical Automation for Process Industries Northeastern University the Department of Mechanical Engineering University of Victoria Shanghai Institute of Intelligent Science and Technology Tongji University IEEE the Institute of Advanced Technology Nanjing University of Posts and Telecommunications

In this paper, we study the decentralized federated learning problem, which involves the collaborative training of a global model among multiple devices while ensuring data *** classical federated learning, the communication channel between the devices poses a potential risk of compromising private information. To reduce the risk of adversary eavesdropping in the communication channel, we propose TRADE(transmit difference weight) concept. This concept replaces the decentralized federated learning algorithm's transmitted weight parameters with differential weight parameters, enhancing the privacy data against eavesdropping. Subsequently, by integrating the TRADE concept with the primal-dual stochastic gradient descent(SGD)algorithm, we propose a decentralized TRADE primal-dual SGD algorithm. We demonstrate that our proposed algorithm's convergence properties are the same as those of the primal-dual SGD algorithm while providing enhanced privacy protection. We validate the algorithm's performance on fault diagnosis task using the Case Western Reserve University dataset, and image classification tasks using the CIFAR-10 and CIFAR-100 datasets,revealing model accuracy comparable to centralized federated learning. Additionally, the experiments confirm the algorithm's privacy protection capability.

关键词： Adversary eavesdropping decentralized federated learning privacy protection stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

Will the fibers of the future be considered fibers?

引用

National science Review 2024年第10期11卷 15-17页

作者： Dewen Xu Ya Liu Hailiang Wang Wei Yan Changjun Jiang Meifang Zhu State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and Engineering Donghua University Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Department of Computer Science and Technology Tongji University

Fiber materials are key materials that have changed human history and promoted the progress of human civilization. In ancient times, humans used feathers and animal skins for clothing, and later they widely employed natural fibers such as cotton, hemp, silk and wool to make fabrics(Fig. 1a). Chinese ancestors had mastered the art of natural fiber weaving as early as the Neolithic *** thousand years ago, people were already familiar with and adept at techniques for spinning natural fibers [1].

关键词： future will considered fibers

来源：评论

学校读者我要写书评

暂无评论

A zeroth-order algorithm for distributed optimization with stochastic stripe observations

引用

science China(Information sciences) 2023年第9期66卷 297-298页

作者： Yinghui WANG Xianlin ZENG Wenxiao ZHAO Yiguang HONG School of Automation and Electrical Engineering University of Science and Technology Beijing Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Department of Control Science and Engineering Tongji University

Recent years have seen a rising interest in distributed optimization problems because of their widespread applications in power grids, multi-robot control, and regression *** the last few decades, many distributed algorithms have been developed for tackling distributed optimization problems. In these algorithms, agents over the network only have access to their own local functions and exchange information with their neighbors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Action Recognition using Spatiotemporal, Adaptive, and Attention-guided Refining-Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期6卷 1-12页

作者： Yin, Xinpeng Zhang, Cheng Huang, ZiXu He, Zhihai Cao, Wenming State Key Laboratory of Radio Frequency Heterogeneous IntegrationDepartment of Electronics and Information EngineeringShenzhen University Department of Computer Science and EngineeringSouthern University of Science and Technology Department of Electronic and Electrical EngineeringSouthern University of Science and Technology

Previous works on unsupervised skeleton-based action recognition primarily focused on strategies for utilizing features to drive model optimization through methods like contrastive learning and reconstruction. However, designing application-level strategies poses challenges. This paper shifts the focus to the generation-level modelings and introduces the Spatiotemporal Adaptively Attentions-guided Refining Network (AgRNet). AgRNet approaches the reduction of costs and enhancement of efficiency by constructing the Adaptive Activity- Guided Attention (AAGA) and Adaptive Dominant-Guided Attenuation (ADGA) modules. The AAGA leverages the sparsity of the correlation matrix in the attention mechanism to adaptively filter and retain the active components of the sequence during the modeling process. The ADGA embeds the local dominant features of the sequence, obtained through convolutional distillation, into the globally dominant features under the attention mechanism, guided by the defined attenuation factor. Additionally, the Progressive Feature Modeling (PFM) module is introduced to complement the progressive features in motion sequences that were overlooked by AAGA and ADGA. AgRNet shows efficiency on three public datasets, NTU-RGBD 60, NTU-RGBD 120, and UWA3D. IEEE

关键词： Time series analysis

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：