检索结果-内蒙古大学图书馆

35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence

作者： Peng, Qi Zheng, Changmeng Cai, Yi Wang, Tao Xie, Haoran Li, Qing South China Univ Technol Sch Software Engn Guangzhou Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China Kings Coll London Dept Biostat & Hlth Informat London England Lingnan Univ Dept Comp & Decis Sci Hong Kong Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

ISBN: (纸本)9781577358664

Existing methods for named entity recognition are critically relied on labeled data. To handle the situation that the data is fully-unlabeled, we propose an entity-aware adversarial domain adaptation network, which utilizes the labeled source data and then adapts to unlabeled target domain. We first apply adversarial training to reduce the distribution gap between different domains. Furthermore, we introduce an entity-aware attention to guide adversarial process to achieve the alignment of entity features. The experiment shows that our model outperforms the state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving uncertain nonlinear complementarity problem by using a new penalty method

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第2期83卷 49-58页

作者： Li, Ming Li, Cunlin Jia, Zhifu Panatik, Siti Aisyah Gao, Yuanboyi School of Business North Minzu University Ningxia750021 China Department of Mathematics Nanjing University of Aeronautics and Astronautics Nanjing China Faculty of Social Sciences and Humanities Universiti Teknologi Malaysia Johor81310 Malaysia La Sapienza university of Roma faculty of economic. Via del Castro Laurenziano 9 Roma RM00161 Italy Ningxia Key Laboratory of intelligent information and Big Data Processing Governance and social management research center of Northwest Ethnic regions North Minzu University Yinchuan China

In this paper, we develop a new class of uncertain nonlinear complemen-tarity problem (UNCP), that is, the uncertain nonlinear complementarity problem based on uncertainty theory in finite Euclidean spaces. It can be regarded as the generalization of classical nonlinear complementarity problem. In order to find the solution of the UNCP, we firstly convert it into an uncertain mathematical program with equilibrium constraints (UMPECs) by the expected value of uncertain variables. To go one step further, we construct an auxiliary function, which is used to convert the UMPECs into the reformulation of the problem. Then, we present a new penalty method for solving the UNCP. Finally, it is another core of the paper that the rigorous convergence of the penalty method has been proofed. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

ER: Equivariance Regularizer for Knowledge Graph Completion

arXiv

引用

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Tensor factorization and distanced based models play important roles in knowledge graph completion (KGC). However, the relational matrices in KGC methods often induce a high model complexity, bearing a high risk of overfitting. As a remedy, researchers propose a variety of different regularizers such as the tensor nuclear norm regularizer. Our motivation is based on the observation that the previous work only focuses on the "size" of the parametric space, while leaving the implicit semantic information widely untouched. To address this issue, we propose a new regularizer, namely, Equivariance Regularizer (ER), which can suppress overfitting by leveraging the implicit semantic information. Specifically, ER can enhance the generalization ability of the model by employing the semantic equivariance between the head and tail entities. Moreover, it is a generic solution for both distance based models and tensor factorization based models. The experimental results indicate a clear and substantial improvement over the state-of-the-art relation prediction methods. © 2022, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Geometry Interaction Knowledge Graph Embeddings

arXiv

引用

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks. Previous work usually embeds KGs into a single geometric space such as Euclidean space (zero curved), hyperbolic space (negatively curved) or hyperspherical space (positively curved) to maintain their specific geometric structures (e.g., chain, hierarchy and ring structures). However, the topological structure of KGs appears to be complicated, since it may contain multiple types of geometric structures simultaneously. Therefore, embedding KGs in a single space, no matter the Euclidean space, hyperbolic space or hyperspheric space, cannot capture the complex structures of KGs accurately. To overcome this challenge, we propose Geometry Interaction knowledge graph Embeddings (GIE), which learns spatial structures interactively between the Euclidean, hyperbolic and hyperspherical spaces. Theoretically, our proposed GIE can capture a richer set of relational information, model key inference patterns, and enable expressive semantic matching across entities. Experimental results on three well-established knowledge graph completion benchmarks show that our GIE achieves the state-of-the-art performance with fewer parameters. © 2022, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Aspect-Based Capsule Network With Mutual Attention for Recommendations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2021年第3期2卷 228-237页

作者： Yang, Zhenyu Wang, Xuesong Cheng, Yuhu Liu, GuoJing The School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The Qilu University of Technology Shandong Academy of Sciences Software Integration Institute Jinan250353 China The Engineering Research Center of Intelligent Control for Underground Space Ministry of Education Xuzhou Key Laboratory of Artificial Intelligence and Big Data School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The School of Computer Science and Technology Qilu University of Technology Jinan250353 China

Review text is a valuable source of information for recommendation systems and often contains rich semantics with user preferences and item attributes. Recently, mainstream recommendation approaches have been using deep learning techniques to utilize review text. These efforts employ an affinity matrix to model the correlations between users and items and in turn aggregate the contextual features of users and items to form latent representations with some interpretability. However, constructing this simple interaction does not capture the complex correlations between users and items. Furthermore, a single representation of latent features is not sufficient to express user preferences and item attributes in reviews with multiple granularities. To this end, we propose an aspect-based capsule network and mutual attention for recommendation systems, named Acapnet. We design a novel contextual mutual attention mechanism for modeling the fine-grained correlations in the contextual features of users and items. We employ reverse dynamic routing to aggregate user and item context features into aspect features (capsules) for rating predictions;the vector length of a capsule can be used as a basis for estimating aspect importance. Extensive experiments are conducted on five real-world datasets with different features. The results show that the proposed Acapnet is superior to recent state-of-the-art models in terms of performance. Further analysis reveals that our model effectively mitigates the homogeneity among various aspect capsules with strong interpretability. © 2021 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Restoration of User Videos Shared on Social Media

arXiv

引用

arXiv 2022年

作者： Luo, Hongming Zhou, Fei Lam, Kin-Man Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Department of Electronic and Information Engineering The Hong Kong Polytechnic University China Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Key Laboratory of Digital Creative Technology China Shenzhen Institute for Artificial Intelligence and Robotics for Society China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication China

User videos shared on social media platforms usually suffer from degradations caused by unknown proprietary processing procedures, which means that their visual quality is poorer than that of the originals. This paper presents a new general video restoration framework for the restoration of user videos shared on social media platforms. In contrast to most deep learning-based video restoration methods that perform end-to-end mapping, where feature extraction is mostly treated as a black box, in the sense that what role a feature plays is often unknown, our new method, termed Video restOration through adapTive dEgradation Sensing (VOTES), introduces the concept of a degradation feature map (DFM) to explicitly guide the video restoration process. Specifically, for each video frame, we first adaptively estimate its DFM to extract features representing the difficulty of restoring its different regions. We then feed the DFM to a convolutional neural network (CNN) to compute hierarchical degradation features to modulate an end-to-end video restoration backbone network, such that more attention is paid explicitly to potentially more difficult to restore areas, which in turn leads to enhanced restoration performance. We will explain the design rationale of the VOTES framework and present extensive experimental results to show that the new VOTES method outperforms various state-of-the-art techniques both quantitatively and qualitatively. In addition, we contribute a large scale real-world database of user videos shared on different social media platforms. Codes and datasets are available at https://***/luohongming/***. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Multi-Object Tracking Based on Anchor-Free Detection and Message Passing Association

Multi-Object Tracking Based on Anchor-Free Detection and Mes...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Zhou Fang Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9781665409858

Due to the current multi-target tracking work, in the scene of dense and staggered targets, the tracked targets are prone to ID switch, which greatly affects the tracking effect. Aiming at this problem, this paper proposed a new multi-target tracking algorithm: using an improved anchor-free detection method and extracting features from multiple aspects, combined with the message passing graph neural network to participate in the data association process to further improve the exchange of feature information, so as to improve the algorithm's ability to associate target information data between frames and improve the tracking accuracy. After conducting quantitative analysis and comparison experiments on datasets such as MOT17 and MOT20, the experimental results show that the algorithm in this paper can effectively improve the problem of target ID switching and provide better tracking accuracy and performance.

关键词： Industrial electronics Target tracking Statistical analysis Message passing Switches Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Face Recognition System with Face Presentation Attack Detection on Raspberry Pi

An Implementation of Face Recognition System with Face Prese...

引用

IEEE International Conference on e-Business Engineering (ICEBE)

作者： Wenjun Wang Xiangkang Huang Xin Shu Shuping Li Huichou Huang Qingyao Wu School of Software Engineering South China University of Technology Guangzhou China School of Data Science and Information Engineering Guizhou Minzu University Guiyang China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China City University of Hong Kong Hong Kong China Pazhou Lab Guangzhou China

ISBN: (纸本)9781665444194

With the popularity of unlocking and payment of using the face-swiping function, the era of face recognition has arrived. However, the current face recognition technology can identify the identity of the face image but cannot accurately distinguish the authenticity of the input face on embedded devices. Recently, face recognition with face presentation attack detection has become a research hotspot. In this paper, we develop an intelligent face recognition system on Raspberry Pi to handle this issue. Specifically, we first add a face presentation attack detection process to form a three-stage face recognition method to realize face recognition with face anti-spoofing. Second, we select a face detection model, a face presentation attack detection model and a face recognition model suitable for Raspberry Pi, and transplant these models previously trained in the Python environment to the C++ environment. Then we integrate and deploy these three models on Raspberry Pi and use the NCNN inference framework for efficient reasoning within limited memory and computing resources. Finally, we implement the face recognition system and conduct real-world tests to verify the performance. The experimental results demonstrate that our system can be applied in practice, and can achieve good effects.

关键词： Face recognition Computational modeling Conferences Memory management C++ languages Cognition Organ transplantation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection with evolutionary sparsity

引用

NEURAL NETWORKS 2025年 189卷 107512页

作者： Zhou, Shixuan Xiang, Yi Huang, Han Huang, Pei Peng, Chaoda Yang, Xiaowei Song, Peng South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130012 Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Guangzhou 510006 Peoples R China Guangdong Engn Ctr Large Model & GenAI Technol Guangzhou 510006 Peoples R China Guangdong Univ Finance & Econ Sch Informat Sci Guangzhou 510006 Peoples R China South China Agr Univ Sch Math & Informat Guangzhou 510006 Peoples R China Yantai Univ Sch Comp & Control Engn Yantai 264005 Peoples R China

The t2,0-norm is playing an increasingly important role in unsupervised feature selection. However, existing algorithm for optimization problem with t2,0-norm constraint has two problems: First, they cannot automatically determine the sparsity, also known as the number of key features. Second, they have the risk of converging towards local optima, therefore selecting trivial (less informative) features. To address these problems, this paper proposes an unsupervised feature selection method with evolutionary sparsity (EVSP), which integrates the feature selection process with a sparse projection matrix and population search mechanisms into a unified unsupervised feature selection framework. Specifically, the level of sparsity is encoded as population individuals, and subsequently, a multi-objective evolutionary algorithm based on binary encoding is introduced to recursively determine the optimal level of sparsity, thus unsupervisedly guiding the learning of an optimal row-sparse projection matrix. Moreover, by utilizing the feature weights learned through sparse projection, a two-stage strategy called the mutation-repair operator is designed to steer the evolution of the population, aiming to generate high-quality candidate solutions. Comprehensive experiments on eleven benchmark datasets, with a maximum dimensionality of 10304 features and a maximum size of 9298 samples, demonstrate that the proposed EVSP method can effectively determine the optimal sparsity level, significantly outperforming several state-of-the-art methods.

关键词： Unsupervised feature selection Multi-objective evolution Sparse projection

来源：评论

学校读者我要写书评

暂无评论

MBNN: A Multi-Branch Neural Network Capable of Utilizing Industrial Sample Unbalance for Fast Inference

引用

IEEE SENSORS JOURNAL 2021年第2期21卷 1809-1819页

作者： Wang, Qizhao Wang, Kai Li, Qing Yang, Zuye Jin, Guangshu Wang, Hong Chinese Acad Sci Key Lab Networked Control Syst Shenyang 110169 Peoples R China Chinese Acad Sci Shenyang Inst Automat Shenyang 110169 Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110169 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Microcyber Corp Ind Cloud Div Res & Dev Prod Direct Cloud Comp Big Data & Artif Shenyang 110179 Peoples R China Microcyber Corp Prod Div Ind Commun Prod & Instruments Shenyang 110179 Peoples R China

Deep neural networks has been widely used in industrial equipment fault diagnosis. The accuracy of deep neural network is usually proportional to the complexity, but the high inference delay and energy consumption caused by the complex model make it difficult to be applied in the industrial environment of real-time demand. At the same time, in the diagnosis of industrial equipment, different categories of samples have unbalanced characteristics in terms of number, difficulty of identification, and demand of identification. In order to solve this problem, this paper designs Multi-Branch Neural Network (MBNN), which is a new type neural network architecture that can use the unbalance of sample categories in industrial equipment fault diagnosis for fast inference. MBNN has multiple sub-networks with different complexity, and each branch is responsible for processing different categories of samples. Categories with large numbers, easy to process, and high demand of identification are processed through simple branches, such as normal samples. Categories with small numbers, difficult to identification, and low demand of identification are processed through complex branches, such as potential failure samples. The feasibility of MBNN has been verified on motor bearing fault diagnosis and gearbox fault diagnosis, and its performance has been evaluated on multiple computing platforms. The results show that MBNN can greatly improve the inference speed while ensuring the recognition accuracy, especially on resource-constrained platforms.

关键词： Fault diagnosis Neural networks Complexity theory Computational modeling Sensors Optimization Real-time systems Neural network architecture fault diagnosis fast inference unbalance sample

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：