检索结果-内蒙古大学图书馆

FIFAWC:a dataset with detailed annotation and rich semantics for group activity recognition

Frontiers of computer science 2024年第6期18卷 271-272页

作者： Duoxuan PEI Di HUANG Yunhong WANG State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Intelligent Recognition and Image Processing Lab. School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

1 *** Activity Recognition(GAR),which aims to identify activities performed collectively in videos,has gained significant attention *** conventional action recognition centered on single individuals,GAR explores the c... 详细信息

关键词： has collective gained

来源：评论

学校读者我要写书评

暂无评论

Safe Exit Controllers Synthesis for Continuous-time Stochastic Systems 63

Safe Exit Controllers Synthesis for Continuous-time Stochast...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Xue, Bai State Key Lab. of Computer Science Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350316339

This paper tackles the problem of generating safe exit controllers for continuous-time systems described by stochastic differential equations (SDEs). The primary aim is to develop controllers that maximize the lower bounds of the exit probability that the system escapes from a safe but uncomfortable set within a specified time frame and guide it towards a comfortable set. The paper considers two distinct cases: one in which the boundary of the safe set is a subset of the boundary of the uncomfortable set, and the other where the boundaries of the two sets do not intersect. To begin, we present a sufficient condition for establishing lower bounds on the exit probability in the first case. This condition serves as a guideline for constructing a point-wise optimization using linear programs. The linear programming problem is designed to implicitly synthesize an optimal exit controller online that maximizes the lower bounds of the exit probability. The method employed in the first case is then extended to the second one. Finally, we demonstrate the effectiveness of the proposed approaches on one example. © 2024 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Quantum search with prior knowledge

引用

science China(Information sciences) 2024年第9期67卷 321-329页

作者： Xiaoyu HE Xiaoming SUN Jialing ZHANG State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences

The combination of contextual side information and search is a powerful paradigm in the scope of artificial intelligence. The prior knowledge enables the identification of possible solutions but may be imperfect. Contextual information can arise naturally, for example in game AI where prior knowledge is used to bias move decisions. In this work we investigate the problem of taking quantum advantage of contextual information, especially searching with prior knowledge. We propose a new generalization of Grover's search algorithm that achieves the optimal expected success probability of finding the solution if the number of queries is fixed. Experiments on small-scale quantum circuits verify the advantage of our algorithm. Since contextual information exists widely, our method has wide applications. We take game tree search as an example.

关键词： quantum computing quantum search quantum query algorithm prior knowledge

来源：评论

学校读者我要写书评

暂无评论

Interference mitigation and target detection for automotive FMCW radar with range-Doppler sparse regularization

引用

science China(Information sciences) 2024年第9期67卷 342-343页

作者： Yan HUANG Yunxuan WANG Xiao ZHOU Hui ZHANG Yuan MAO Guisheng LIAO Wei HONG State Key Lab of Millimeter Waves Southeast University Department of Computer Science University College London National Key Lab of Radar Signal Processing Xidian University

The invention of vehicles has shaped our modern society and accelerated our economy while causing many tragic incidents simultaneously. Some advanced driver-assistance systems(ADAS) based on surrounding environment se... 详细信息

关键词： Radar interference

来源：评论

学校读者我要写书评

暂无评论

Hybrid mesh-neural representation for 3D transparent object reconstruction

引用

Computational Visual Media 2025年第1期11卷 123-140页

作者： Jiamin Xu Zihan Zhu Hujun Bao Weiwei Xu College of Computer Science Hangzhou Dianzi UniversityHangzhou 310018China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310058China College of Computer Science ETH ZurichZurich 8092Switzerland.

In this study,we propose a novel method to reconstruct the 3D shapes of transparent objects using images captured by handheld cameras under natural lighting *** combines the advantages of an explicit mesh and multi-layer perceptron(MLP)network as a hybrid representation to simplify the capture settings used in recent *** obtaining an initial shape through multi-view silhouettes,we introduced surface-based local MLPs to encode the vertex displacement field(VDF)for reconstructing surface *** design of local MLPs allowed representation of the VDF in a piecewise manner using two-layer MLP networks to support the optimization *** local MLPs on the surface instead of on the volume also reduced the search *** a hybrid representation enabled us to relax the ray–pixel correspondences that represent the light path constraint to our designed ray–cell correspondences,which significantly simplified the implementation of a single-image-based environment-matting *** evaluated our representation and reconstruction algorithm on several transparent objects based on ground truth *** experimental results show that our method produces high-quality reconstructions that are superior to those of state-of-the-art methods using a simplified data-acquisition setup.

关键词： transparent object 3D reconstruction environment matting neural rendering

来源：评论

学校读者我要写书评

暂无评论

Detecting Element Accessing Bugs in C++ Sequence Containers 24

Detecting Element Accessing Bugs in C++ Sequence Containers

引用

39th ACM/IEEE International Conference on Automated Software Engineering, ASE 2024

作者： Li, Zhilin Ma, Xutong Hu, Mengze Yan, Jun State Key Lab. of Computer Science Ins. of Software CAS University of Chinese Academy of Sciences Beijing China State Key Lab. of Computer Science Ins. of Software CAS Beijing China State Key Lab. of Computer Science Ins. of Software CAS Tech. Center of Software Eng. Ins. of Software CAS University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798400712487

ISBN: (纸本)9798400712487

Sequence Containers (SC) in the C++ Standard Template Library (STL), such as the vector, are widely used in large-scale projects for their maintainability and flexibility. However, accessing the elements in an SC is bug-prone, as such operations will not check their boundaries during compilation or execution, which can lead to memory errors, such as buffer overflow problems. And these bugs are difficult to detect with availab.e static analyzers, since the size of SCs and the target of iterators cannot be precisely tracked without accurate analysis of the behavior of SCs and *** address this problem, we propose a combined model of SC sizes and iterator targets by tracking them simultaneously through a set of meta-operations extracted from corresponding method calls, and report improper operation usages according to three bug patterns. We implement the approach as a static analyzer, Scasa, on the top of the Clang Static Analyzer (CSA) framework, and evaluate its effectiveness and efficiency against CSA and other state-of-the-art static analyzers on a benchmark composed of 2,230 manually created code snippets and eight popular open-source C++ projects with a lot of SC usages. The experimental results reveal that Scasa effectively identifies nearly all inherent bugs within the manual code snippets and generates 125 reports for these projects (with a time loss of 5 - 85%) where 72 of them are marked as correct with a manual revision. And to further confirm these correct reports, we also select some important ones for developers. These results show that accessing elements of SCs is bug-prone, and cooperatively tracking SC sizes and iterator targets can accurately detect these bugs with acceptable overhead. Copyright held by the owner/author(s).

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training

引用

ACM Transactions on Knowledge Discovery from Data 2024年第9期18卷 1-30页

作者： Liu, Yonghao Li, Mengyu Li, Ximing Huang, Lan Giunchiglia, Fausto Liang, Yanchun Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China University of Trento Trento Italy Zhuhai Lab. of the Key Lab. of Symbolic Computation and Knowledge Eng. of the Ministry of Education Zhuhai College of Science and Technology Zhuhai China

Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning with graph neural networks to solve few-shot node classification on graphs. Despite their promising performance, some limitations remain. First, they employ the node encoding mechanism of homophilic graphs to learn node embeddings, even in heterophilic graphs. Second, existing models based on meta-learning ignore the interference of randomness in the learning process. Third, they are trained using only limited lab.led nodes within the specific task, without explicitly utilizing numerous unlab.led nodes. Finally, they treat almost all sampled tasks equally without customizing them for their uniqueness. To address these issues, we propose a novel framework for few-shot node classification called Meta-GPS. Specifically, we first adopt an efficient method to learn discriminative node representations on homophilic and heterophilic graphs. Then, we leverage a prototype-based approach to initialize parameters and contrastive learning for regularizing the distribution of node embeddings. Moreover, we apply self-Training to extract valuable information from unlab.led nodes. Additionally, we adopt S (scaling and shifting) transformation to learn transferable knowledge from diverse tasks. The results on real-world datasets show the superiority of Meta-GPS. Our code is availab.e here. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LPW: an efficient data-aware cache replacement strategy for Apache Spark

引用

science China(Information sciences) 2023年第1期66卷 77-96页

作者： Hui LI Shuping JI Hua ZHONG Wei WANG Lijie XU Zhen TANG Jun WEI Tao HUANG State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Nanjing Institute of Software Technology

Caching is one of the most important techniques for the popular distributed big data processing framework Spark. For this big data parallel computing framework, which is designed to support various applications based on in-memory computing, it is not possible to cache every intermediate result due to the memory size limitation. The arbitrariness of cache application programming interface(API) usage,the diversity of application characteristics, and the variability of memory resources constitute challenges to achieving high system execution performance. Inefficient cache replacement strategies may cause different performance problems such as long application execution time, low memory utilization, high replacement frequency, and even program execution failure resulting from out of memory. The cache replacement strategy currently adopted by Spark is the least recently used(LRU) strategy. Although LRU is a classical algorithm and has been widely used, it lacks consideration for the environment and workloads. As a result, it cannot achieve good performance under many scenarios. In this paper, we propose a novel cache replacement algorithm, least partition weight(LPW). LPW takes comprehensive consideration of different factors affecting system performance, such as partition size, computational cost, and reference count. The LPW algorithm was implemented in Spark and compared against the LRU as well as other state-of-the-art mechanisms. Our detailed experiments indicate that LPW obviously outperforms its counterparts and can reduce the execution time by up to 75% under typical workloads. Furthermore, the decreasing eviction frequency also shows the LPW algorithm can generate more reasonable predictions.

关键词： Spark memory cache replacement least partition weight data-aware

来源：评论

学校读者我要写书评

暂无评论

Learning-Driven Dynamic Multimodal Optimization Algorithm for Real-Time Traceability of Water Pollution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2472-2481页

作者： Yan, Xuesong Guo, Xing Chen, Jin Hu, Chengyu Gong, Wenyin Gao, Liang China University of Geosciences School of Computer Science Wuhan430074 China Huazhong University of Science and Technology State Key Lab of Digital Manufacturing Equipment and Technology Wuhan430074 China

In recent years, water quality safety problems caused by sudden urban drinking water contamination events have attracted the attention of experts in China and abroad. After an occurrence of urban water pollution, it is challenging to locate the pollution source in real time according to the information collected by water quality sensors and then quickly deduce the injection location, injection concentration quality, and other characteristics of the pollution source. In this article, we propose a learning-driven dynamic multimodal optimization algorithm framework that combines various machine learning algorithms. First, it uses the support vector machine (SVM) model to scale down and perform node probability estimation for a large-scale water supply pipeline network. Second, by predicting the uncertainty parameters of the pipe network when setting the pipe network simulation parameters, the framework can narrow the gap between simulation and real conditions, giving the pollution source characteristics obtained by the algorithm solution a higher confidence level. The experimental results show that the algorithm framework can achieve real-time traceability of water pollution for large-scale, uncertain pipe network environments, and can obtain better accuracy and real-time performance than other dynamic algorithms. © 2020 IEEE.

关键词： Water pollution

来源：评论

学校读者我要写书评

暂无评论

Crowd2: Multi-agent Bandit-based Dispatch for Video Analytics upon Crowdsourcing 42

Crowd2: Multi-agent Bandit-based Dispatch for Video Analytic...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Chen, Yu Zhang, Sheng Yan, Yuting Jin, Yibo Chen, Ning Ji, Mingtao Xiao, Mingjun Nanjing University State Key Lab. for Novel Software Technology China University of Science and Technology of China School of Computer Science and Technology China

ISBN: (纸本)9798350334142

Many crowdsourcing platforms are emerging, leveraging the resources of recruited workers to execute various outsourcing tasks, mainly for those computing-intensive video analytics with high quality requirements. Although the profit of each platform is strongly related to the quality of analytics feedback, due to the uncertainty on diverse performance of workers and the conflicts of interest over platforms, it is non-trivial to determine the dispatch of tasks with maximum benefits. In this paper, we design a decentralized mechanism for a Crowd of Crowdsourcing platforms, denoted as Crowd2, optimizing the worker selection to maximize the social welfare of these platforms in a long-term scope, under the consideration of both proportional fairness and dynamic flexibility. Concretely, we propose a video analytics dispatch algorithm based on multi-agent bandit, for which the more accurate profit estimates are attained via the decoupling of multi-knapsack based mapping problem. Via rigorous proofs, a sub-linear regret bound for social welfare of crowdsourcing profits is achieved while both fairness and flexibility are ensured. Extensive trace-driven experiments demonstrate that Crowd2 improves the social welfare by 36.8%, compared with other alternatives. © 2023 IEEE.

关键词： Profitability

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：