检索结果-内蒙古大学图书馆

International Conference on data engineering

作者： Wentao Zhang Xinyi Gao Ling Yang Meng Cao Ping Huang Jiulong Shan Hongzhi Yin Bin Cui Center for Machine Learning Research Peking University Institute of Advanced Algorithms Research Shanghai National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Key Lab of High Confidence Software Technologies Peking University Apple Inc. Institute of Computational Social Science Peking University Qingdao

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score.

关键词： Training Industries data engineering Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Scientific Value Weights more than Being Open or Toll Access:An analysis of the OA advantage in Nature and Science

引用

Journal of data and Information Science 2021年第4期6卷 62-75页

作者： Howell Y.Wang Shelia X.Wei Cong Cao Xianwen Wang Fred Y.Ye International Joint Informatics Laboratory&Jiangsu Key Laboratory of Data Engineering and Knowledge Service School of Information ManagementNanjing UniversityNanjing 210023China Nottingham University Business School China University of Nottingham Ningbo ChinaNingbo315100China WISE Lab. Dalian University of TechnologyDalian 116024China

Purpose:We attempt to find out whether OA or TA really affects the dissemination of scientific ***/methodology/approach:We design the indicators,hot-degree,and R-index to indicate a topic OA or TA ***,according to the OA classification of the Web of Science(WoS),we collect data from the WoS by downloading OA and TA articles,letters,and reviews published in Nature and Science during 2010–*** papers are divided into three broad disciplines,namely biomedicine,physics,and ***,taking a discipline in a journal and using the classical Latent Dirichlet Allocation(LDA)to cluster 100 topics of OA and TA papers respectively,we apply the Pearson correlation coefficient to match the topics of OA and TA,and calculate the hot-degree and R-index of every OA-TA topic ***,characteristics of the discipline can be *** qualitative comparison,we choose some high-quality papers which belong to Nature remarkable papers or Science breakthroughs,and analyze the relations between OA/TA and citation ***:The result shows that OA hot-degree in biomedicine is significantly greater than that of TA,but significantly less than that of TA in *** on the R-index,it is found that OA advantages exist in biomedicine and TA advantages do in ***,the dissemination of average scientific discoveries in all fields is not necessarily affected by OA or ***,OA promotes the spread of important scientific discoveries in high-quality *** limitations:We lost some citations by ignoring other open sources such as arXiv and *** limitation came from that Nature employs some strong measures for access-promoting subscription-based articles,on which the boundary between OA and TA became *** implications:It is useful to select hot topics in a set of publications by the hotdegree *** finding comprehensively reflects the differences of OA and TA in different disciplines,which is a u

关键词： Open access Toll access Scientific discovery Academic dissemination data analysis

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Animal Pose Estimation with Skeleton Anomaly-Aware Learning

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Han, Le Chen, Kaixuan Zhao, Lei Jiang, Yangbo Wang, Pengfei Zheng, Nenggan Zhejiang Hangzhou310007 China Zhejiang University College of Computer Science and Technology Zhejiang Hangzhou310007 China Zhejiang University State Key Laboratory of Blockchain and Data Security Zhejiang Hangzhou310007 China Institute of Blockchain and Data Security. China Zhejiang University School of Software Technology Ningbo China Zhejiang University State Key Lab of Brain-Machine Intelligence Hangzhou310007 China Zhejiang Provincial Government ZJU Collaborative Innovation Center for Artificial Intelligence by MOE Hangzhou310007 China Bengbu University School of Computer and Information Engineering Bengbu233030 China

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning. The UDARP-9.4K dataset is available here. © 1991-2012 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic geometric latent diffusion model for graph generation 24

Hyperbolic geometric latent diffusion model for graph genera...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xingcheng Fu Yisen Gao Yuecen Wei Qingyun Sun Hao Peng Jianxin Li Xianxian Li Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China and Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Canonical Shape Reconstruction with SE(3) Equivariance Learning for Weakly-Supervised Object Pose Estimation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhou, Jun Chen, Kai Wei, Mingqiang Zhang, Xiao-Ping Dou, Qi Qin, Jing Hong Kong Polytechnic University Center of Smart Health School of Nursing Hong Kong Hong Kong Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Hong Kong Nanjing University of Aeronautics and Astronautics School of Computer Science and Technology Nanjing China Tsinghua University Shenzhen Ubiquitous Data Enabling Key Lab Shenzhen International Graduate School Shenzhen China

6D object pose estimation from a single RGB-D image is a fundamental problem in computer vision and robot manipulation. Despite recent advancements, existing methods still suffer several limitations. First of all, the object shape representation extracted from the depth map is often less expressive because the object point cloud parsed from the depth map is highly incomplete due to the object self-occlusion and noisy due to the sensor artifacts. This shape representation issue further intensifies when lacking sufficient labeled data for model training, which unfortunately is another typical problem for object pose estimation considering the heavy annotation cost for real-world pose labeling. In this study, we propose to tackle the above issues in a unified way. First, we enhance the object shape representation from the partial point cloud with a novel canonical shape reconstruction module, in which an implicit canonical frame is established by incorporating the SE(3) equivariance, achieving implicit feature alignment of the partial point cloud inputs, leading to robust shape recovery. Second, based on the enhanced object representation, we further utilize the decanonicalized and pose-dependent completed object shape as the training signal, and develop a novel weakly-supervised learning framework to leverage both labeled synthetic data and unlabeled real data to train the pose estimation model in a label-efficient way. Extensive experiments on three widely used benchmarks demonstrate the effectiveness, and superiority of our framework over state-of-the-art methods. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "DSTF: A diversified spatio-temporal feature extraction model for traffic flow prediction" [Neurocomputing 621 (2025) 129280] (Neurocomputing (2025) 621, (S0925231224020514), (10.1016/***.2024.129280))

引用

Neurocomputing 2025年 638卷

作者： Wang, Xing Wang, Xiaojun Huang, Faliang Zou, Fumin Liao, Lyuchao Zeng, Ruihao Fujian Normal University College of Computer and Cyber Security China Fujian Normal University Digital Fujian Institute of Big Data Security Technology China Nanning Normal University Guangxi Key Lab of Human-machine Interaction and Intelligent Decision China Fujian University of Technology Fujian Key Laboratory of Automotive Electronic and Electrical Drive Technology China The University of Sydney School of Civil Engineering Sydney Australia

The authors regret to inform that: (1) During the resubmission stage of the revised manuscript, in compliance with reviewers' recommendations to show standard deviations in the experimental results (In Section 5. Experiment implementation), a batch replacement operation (intended to replace "+" with "±" for data formatting) inadvertently replaced the "+" symbols in the mathematical formulas and the explanatory text with "±" symbols (In Section 3. Problem statement and Section 4. Methodology). (2) In proof stage, we sincerely apologize for failing to identify this issue during the final proofreading stage. Correction statement and details: As this error may affect readers' understanding, we request a corrigendum to rectify this error. In Section 3. Problem statement and Section 4. Methodology, all instances of "±" symbols within mathematical formulas and their explanatory text should be reverted to the original "+" symbols. The authors would like to apologize for any inconvenience caused. © 2025 The Authors

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fission: Autonomous, Scalable Sharding for IoT Blockchain

Fission: Autonomous, Scalable Sharding for IoT Blockchain

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Chaoran Luo Yueyang Hu Su Zhang Ying Zhang Yi Liu Xingchun Diao Gang Huang Key Lab of High Confidence Software Technologies Peking University Beijing China School of Software and Microelectronics Peking University Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China Advanced Institute of Big Data Beijing China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

IoT blockchain suffers heavy performance issues because of the massive transactions generated by various IoT nodes. By dividing nodes into different shards, sharding can produce blocks in parallel and hence improve the throughput of the blockchain system. Unlike the traditional blockchain system, IoT blockchain mainly consists of smart devices and the transactions are usually generated from the real world, such as the sensor data, photos taken by cameras, and so on. In IoT blockchain, closer nodes usually share a lower network latency and the transactions they generate are more related. Therefore, location-based sharding is an effective approach to improve the performance of IoT blockchain. Traditionally, IoT nodes are di-vided into different shards based on geographical locations or the connected edge server. However, the key challenge of sharding in IoT blockchain is how to guarantee the equality of shards division as to the unpredictable distribution and the dynamic behavior of IoT nodes. On one hand, shards can not be pre-divided because we can not predict the number or the distribution of the IoT nodes. On the other hand, nodes continuously joining or quitting shards will also break the equality of the shards division. In this paper, we propose Fission, a sharding mechanism designed for IoT blockchain. Fission divide shards based on the Voronoi diagram without any preknowledge about the nodes distribution, and support dynamic, autonomous sharding adjustment based on distributed Delaunay Triangulation. In addition, Fission uses a new diffusion-based consensus algorithm to achieve the linear scalability of throughput. The experimental results show that Fission can construct and adjust shards at a very low cost and can execute in a decentralized manner. The throughput can reach 1900tps in 500 nodes with only 5M bps bandwidth, and can scale linearly as the nodes increase.

关键词： Scalability Software algorithms Consensus algorithm Throughput Cameras Software Blockchains

来源：评论

学校读者我要写书评

暂无评论

A WOA Based Switching PID Control for Overhead Crane 42

A WOA Based Switching PID Control for Overhead Crane

引用

42nd Chinese Control Conference, CCC 2023

作者： Yu, Haoyong Sun, Zhe Xu, Yuhua Xu, Lei Gong, Guangfu Xie, Xiangpeng Sun, Zhixin Post Industry Technology Research and Development Center of the State Posts Bureau Nanjing University of Posts and Telecommunications Nanjing210023 China Nanjing University of Posts and Telecommunications Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing210023 China Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing210023 China Anhui Yougu Express Intelligent Technology Co. LTD Anhui Nanling241300 China

ISBN: (纸本)9789887581543

Aiming at the problem that the amplitude of load oscillation is not easy to control in the movement process of overhead crane, this paper designs a switching PID control method based on whale optimization algorithm(WOA) to improve the performance of position control and anti-swing control for overhead crane. WOA is used to better adjust the parameters of PID controllers. The switching control is realized by a switching module, which defaults to the output of the Position PID Controller to provide control force for the trolley. When the absolute value of the load swing angle fed back by the crane system exceeds the warning value, the switching module immediately blocks the output of the Position PID Controller, and uses the Angle PID Controller to determine the control force. In addition, through theoretical analysis and simulation experiments under different conditions, the results verify the effectiveness of the WOA based switching control in position control and anti-swing control for overhead crane. Improve the efficiency and safety of overhead crane in practical industrial applications. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

3D Object Detection for Autonomous Driving: A Survey

arXiv

引用

arXiv 2021年

作者： Qian, Rui Lai, Xin Li, Xirong Key Lab of Data Engineering and Knowledge Engineering Renmin University of China Beijing100872 China School of Mathematics Renmin University of China Beijing100872 China

Autonomous driving is regarded as one of the most promising remedies to shield human beings from severe crashes. To this end, 3D object detection serves as the core basis of perception stack especially for the sake of path planning, motion prediction, and collision avoidance etc. Taking a quick glance at the progress we have made, we attribute challenges to visual appearance recovery in the absence of depth information from images, representation learning from partially occluded unstructured point clouds, and semantic alignments over heterogeneous features from cross modalities. Despite existing efforts, 3D object detection for autonomous driving is still in its infancy. Recently, a large body of literature have been investigated to address this 3D vision task. Nevertheless, few investigations have looked into collecting and structuring this growing knowledge. We therefore aim to fill this gap in a comprehensive survey, encompassing all the main concerns including sensors, datasets, performance metrics and the recent state-of-the-art detection methods, together with their pros and cons. Furthermore, we provide quantitative comparisons with the state of the art. A case study on fifteen selected representative methods is presented, involved with runtime analysis, error analysis, and robustness analysis. Finally, we provide concluding remarks after an in-depth analysis of the surveyed works and identify promising directions for future work. © 2021, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Research on the Loading Method of Logistics Vehicle and Cargo Based on IPSO Algorithm 42

Research on the Loading Method of Logistics Vehicle and Carg...

引用

42nd Chinese Control Conference, CCC 2023

作者： Zhao, Zewei Wang, Huqing Sun, Zhe Xu, Lei Gong, Guangfu Xie, Xiangpeng Sun, Zhixin Post Industry Technology Research and Development Center of the State Posts Bureau Nanjing University of Posts and Telecommunications Nanjing210023 China Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing210023 China Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing210023 China Anhui Yougu Express Intelligent Technology Co. LTD Anhui Nanling241300 China

ISBN: (纸本)9789887581543

Logistics vehicle and cargo matching problem is a typical combination optimization problem, which has important theoretical and application value in the field of logistics distribution. The proved particle swarm optimization (PSO) algorithm is one of the most extensive optimization methods studied in recent years, with excellent global search ability and convergence speed. Based on the IPSO algorithm, this paper proposes an effective IPSO algorithm model for the matching problem of logistics vehicles and goods, and conducts the corresponding comparative experiment. The final experimental results show that the algorithm has good results in practical application and can provide a feasible optimization method for solving the problem of logistics vehicles and goods. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Particle swarm optimization (PSO)

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：