检索结果-内蒙古大学图书馆

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zihan Wang Siyang Song Cheng Luo Yuzhi Zhou Shiling Wu Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Computing and Mathematical Sciences University of Leicester

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence; (ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation; and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://***/wzh125/ABAW-5.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Load Forecasting in Mountainous Cities Considering Traffic Behavior

Electric Vehicle Load Forecasting in Mountainous Cities Cons...

引用

2023 China Automation Congress, CAC 2023

作者： Long, Hongyu Yin, Xiao Liu, Chao Xu, Yuansen Tian, Tian Ye, Fan School of Automation School of Industrial Internet Chongqing University of Posts and Telecommunications Key Laboratory of Big Data Intelligent Computing Chongqing China School of Automation School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China Institute of State Grid Chongqing Electric Power Company Economic and Technical Research Chongqing China

ISBN: (纸本)9798350303759

In response to the unique topographical challenges posed by mountainous environments, this paper investigates a probabilistic model of electric vehicle charging load, taking into account the unique traffic behavior and regional characteristics of mountainous cities. Regarding the traffic behavior, first, a traffic road network model for mountainous cities is proposed. Next, the travel chain theory is combined with the road chain to consider the functional partition of the city, which can better describe the travel patterns and charging behavior of users. Based on the analysis of traffic behavior, by exploring the influences of ambient temperature, road grade, and the undulating nature of mountainous roads, an improved Floyd shortest path algorithm is used for path decision-making, leading to the development of an EV power consumption model specifically tailored for mountainous cities. Based on this model, the prediction of EV load in mountainous cities is subsequently conducted. Overall, this study proposes a more realistic EV load prediction model by integrating traffic behavior, regional characteristics and user travel patterns, and the simulation results demonstrate the adaptability as well as the effectiveness of the method for application in mountainous cities. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Matching Knowledge Graphs in Entity Embedding Spaces: An Experimental Study [Extended Abstract]

Matching Knowledge Graphs in Entity Embedding Spaces: An Exp...

引用

International Conference on data Engineering

作者： Weixin Zeng Xiang Zhao Zhen Tan Jiuyang Tang Xueqi Cheng Laboratory for Big Data and Decision National University of Defense Technology China Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology China Institute of Computing Technology CAS China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Entity alignment (EA) identifies equivalent entities that locate in different knowledge graphs (KGs), and has attracted growing research interests over the last few years with the advancement of KG embedding techniques. Although a pile of embedding-based EA frameworks have been developed, they mainly focus on improving the performance of entity representation learning, while largely overlook the subsequent stage that matches $KGs$ in entity embedding spaces. Nevertheless, accurately matching entities based on learned entity representations is crucial to the overall alignment performance, as it coordinates individual alignment decisions and determines the global matching result. Hence, it is essential to understand how well existing solutions for matching KGs in entity embedding spaces perform on present benchmarks, as well as their strengths and weaknesses. To this end, in this article we provide a comprehensive survey and evaluation of matching algorithms for KGs in entity embedding spaces in terms of effectiveness and efficiency on both classic settings and new scenarios that better mirror real-life challenges. Based on in-depth analysis, we provide useful insights into the design trade-offs and good paradigms of existing works, and suggest promising directions for future development.

关键词： Surveys Representation learning Knowledge graphs Benchmark testing data engineering Mirrors

来源：评论

学校读者我要写书评

暂无评论

Efficient distributed algorithms for holistic aggregation functions on random regular graphs

引用

Science China(Information Sciences) 2022年第5期65卷 32-50页

作者： Lin JIA Qiang-Sheng HUA Haoqiang FAN Qiuping WANG Hai JIN 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 TechnologyHuazhong University of Science and Technology Institute for Interdisciplinary Information Science Tsinghua University

In this paper, we propose efficient distributed algorithms for three holistic aggregation functions on random regular graphs that are good candidates for network topology in next-generation data *** three holistic aggregation functions include SELECTION（select the k-th largest or smallest element）,DISTINCT（query the count of distinct elements）, MODE（query the most frequent element）. We design three basic techniques — Pre-order Network Partition, Pairwise-independent Random Walk, and Random Permutation Delivery, and devise the algorithms based on the techniques. The round complexity of the distributed SELECTION is Θ（log N） which meets the lower bound where N is the number of nodes and each node holds a numeric element. The round complexity of the distributed DISTINCT and MODE algorithms are O（log3N/log log N） and O（log2N log log N） respectively. All of our results break the lower bounds obtained on general graphs and our distributed algorithms are all based on the CON GE S T model, which restricts each node to send only O（log N） bits on each edge in one round under synchronous communications.

关键词： distributed algorithms holistic aggregation function random regular graph ${\cal C}{\cal O}{\cal N}{\cal G}{\cal E}{\cal S}{\cal T}$ model communication complexity round complexity

来源：评论

学校读者我要写书评

暂无评论

SimSIMS: Simulation-based Supernova Ia Model Selection with thousands of latent variables

arXiv

引用

arXiv 2023年

作者： Karchev, Konstantin Trotta, Roberto Weniger, Christoph Theoretical and Scientific Data Science SISSA Trieste Italy Department of Physics Imperial College London United Kingdom Italian Research Center on High Performance Computing Big Data and Quantum Computing Italy National Institute for Nuclear Physics Trieste Italy GRAPPA Institute University of Amsterdam Netherlands

We present principled Bayesian model comparison through simulation-based neural classification applied to SN Ia analysis. We validate our approach on realistically simulated SN Ia light curve data, demonstrating its ability to recover posterior model probabilities while marginalizing over > 4000 latent variables. The amortized nature of our technique allows us to explore the dependence of Bayes factors on the true parameters of simulated data, demonstrating Occam’s razor for nested models. When applied to a sample of 86 low-redshift SNæ Ia from the Carnegie Supernova Project, our method prefers a model with a single dust law and no magnitude step with host mass, disfavouring different dust laws for low- and high-mass hosts with odds in excess of 100:1. Copyright © 2023, The Authors. All rights reserved.

关键词： Supernovae

来源：评论

学校读者我要写书评

暂无评论

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution 39

Efficient Language-instructed Skill Acquisition via Reward-P...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Changxin Chang, Yanbin Lin, Junfan Liang, Junyang Zeng, Runhao Li, Jianqiang National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Peng Cheng Laboratory Shenzhen China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China

ISBN: (纸本)157735897X

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it’s challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by retraining policies from scratch placing an undue burden on the reward function, expecting it to be effective throughout the whole policy improvement process. We argue for a more practical strategy in robotic autonomy, focusing on refining existing policies with policy-dependent reward functions rather than a universal one. To this end, we propose a novel reward-policy co-evolution framework where the reward function and the learned policy benefit from each other’s progressive on-the-fly improvements, resulting in more efficient and higher-performing skill acquisition. Specifically, the reward evolution process translates the robot’s previous best reward function, descriptions of tasks and environment into text inputs. These inputs are used to query LLMs to generate a dynamic amount of reward function candidates, ensuring continuous improvement at each round of evolution. For policy evolution, our method generates new policy populations by hybridizing historically optimal and random policies. Through an improved Bayesian optimization, our approach efficiently and robustly identifies the most capable and plastic reward-policy combination, which then proceeds to the next round of co-evolution. Despite using less data, our approach demonstrates an average normalized improvement of 95.3% across various high-dimensional robotic skill learning tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserve

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Local Regression-Based SLA-Aware Energy-Efficient Virtual Machine Consolidation Algorithm in data Centers

A Local Regression-Based SLA-Aware Energy-Efficient Virtual ...

引用

International Conference on big data computing and Communications (bigCOM)

作者： Xiaodong Wu Ronghai Wang Guoxin Lin School of Mathmatics and Computer Science Quanzhou Normal University Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian Provincial Big Data Research Institute of Intelligent Manufacturing Quanzhou China

Virtual Machine Consolidation (VMC) is an effective means to improve the resource utilization and reduce energy consumption of data centers. However, the VMC optimization that only considers energy consumption may lead to SLA (Service-Level Agreements) violations and thus fail to guarantee the QoS (Quality of Service) provided. Therefore, it is necessary to consider both energy saving and SLA violations in the process of VMC. In this paper, we propose an energy and SLA-aware VMC algorithm that considers both energy saving and SLA violation optimization in data centers. The proposed algorithm uses the local regression method to predict the utilization of virtual machines, based on which it determines whether the host will be overloaded, so as to make the decision of virtual machine migrations. The proposed VMC algorithm is evaluated with CloudSim toolkit. Simulation results demonstrate that our algorithm has good energy saving performance and can effectively reduce SLA violation in cloud data center. Considering energy consumption and SLA violation, the ESV can be reduced by 7.57% on average and 16.36% at most compared with other algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics

arXiv

引用

arXiv 2023年

作者： Zhang, Boning Liu, Dongzhu Simeone, Osvaldo Zhu, Guangxu School of Computing Science University of Glasgow United Kingdom Department of Engineering King's College London United Kingdom Shenzhen Research Institute of Big Data China

The recent development of scalable Bayesian inference methods has renewed interest in the adoption of Bayesian learning as an alternative to conventional frequentist learning that offers improved model calibration via uncertainty quantification. Recently, federated averaging Langevin dynamics (FALD) was introduced as a variant of federated averaging that can efficiently implement distributed Bayesian learning in the presence of noiseless communications. In this paper, we propose wireless FALD (WFALD), a novel protocol that realizes FALD in wireless systems by integrating over-the-air computation and channel-driven sampling for Monte Carlo updates. Unlike prior work on wireless Bayesian learning, WFALD enables (i) multiple local updates between communication rounds;and (ii) stochastic gradients computed by mini-batch. A convergence analysis is presented in terms of the 2-Wasserstein distance between the samples produced by WFALD and the targeted global posterior distribution. Analysis and experiments show that, when the signal-to-noise ratio is sufficiently large, channel noise can be fully repurposed for Monte Carlo sampling, thus entailing no loss in performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Research on the Quantity Evaluation of Speech datasets for Model Training

Research on the Quantity Evaluation of Speech Datasets for M...

引用

2021 International Conference on Intelligent computing, Automation and Systems, ICICAS 2021

作者： Li, Sun Cao, Feng Liu, Zishan Institute of Cloud Computing and Big Data China Academy of Information and Communications Technology Beijing China Institute of Technology and Standards China Academy of Information and Communications Technology Beijing China

ISBN: (纸本)9781665428101

With the maturity of intelligent speech technology and product application, the demand for high-quality speech datasets is increasing. There have been some researchers put effort on the quality evaluation of the structured data, but there are few standards appeared for the speech datasets. By analyzing the construction principle of speech algorithm model and analyzing the construction demand of speech datasets, a unified quality assessment framework for the speech datasets is presented. The framework proposes to evaluate the speech datasets in terms of four dimensions: breadth coverage, anthology distinction, professional field depth and data integrity. By proposing specific speech datasets quality evaluation metrics, calculation methods and evaluation steps, and analyzing the experimental examples and results of speech datasets quality evaluation in vehicle application field, this paper provides a reference basis for evaluating speech datasets quality and promoting datasets construction. Considering the diversified applicability, privacy issues, efficiency and automation requirements of speech datasets construction, some suggestions for the future development of high-quality speech datasets construction are put forward. © 2021 IEEE.

关键词： Speech

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a 3D dynamic geometric global coordinate system 16

Design and implementation of a 3D dynamic geometric global c...

引用

16th IEEE International Conference on Computer Science and Education, ICCSE 2021

作者： Mai, Ce Rao, Yongsheng Guan, Hao Zhang, Linjing Zhao, Jietong Zhang, Chuanjun Institute of Computing Science and Technology Guangzhou University Guangzhou China Fuzhou Administration Institute Fuzhou China Guizhou Education University School of Mathematics and Big Data Guiyang China

ISBN: (纸本)9781665414685

The three-dimensional dynamic geometry system (3D DGS) can intuitively present three-dimensional spatial and is widely used in solid geometry teaching. The design and implementation of the coordinate system in three-dimensional space is its essential foundation. The coordinate system of the existing 3D DGS can't be moved, rotated, zoomed, which make the DGS not meet teaching needs. In this paper, we analyze the transformation requirements and the design goal of the coordinate system. And we propose a method of the coordinate transformation of DGS and introduce the transformation process among the pixel coordinate system, the image coordinate system, the camera coordinate system and the world coordinate system. Based on the above coordinate transformation method, the movement, rotation, and zoom of the coordinate system are implemented in NetPad 3D. Finally, the comparison of a teaching case demonstrates that users develop resources conveniently with NetPad 3D. © 2021 IEEE.

关键词： Geometry

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：