检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： Jiehui Deng Sheng Wan Xiang Wang Enmei Tu Xiaolin Huang Jie Yang Chen Gong PCA Lab the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Hong Kong Polytechnic University Hong Kong SAR China

Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.

关键词： Deep learning Fuses Estimation Switches Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

FCM-RDpA: TSK fuzzy regression model construction using fuzzy C-means clustering, regularization, droprule, and powerball adabelief

arXiv

引用

arXiv 2020年

作者： Shi, Zhenhua Wu, Dongrui Guo, Chenfeng Zhao, Changming Cui, Yuqi Wang, Fei-Yue Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

To effectively optimize Takagi-Sugeno-Kang (TSK) fuzzy systems for regression problems, a mini-batch gradient descent with regularization, DropRule, and AdaBound (MBGD-RDA) algorithm was recently proposed. This paper further proposes FCM-RDpA, which improves MBGD-RDA by replacing the grid partition approach in rule initialization by fuzzy c-means clustering, and AdaBound by Powerball AdaBelief, which integrates recently proposed Powerball gradient and AdaBelief to further expedite and stabilize parameter optimization. Extensive experiments on 22 regression datasets with various sizes and dimensionalities validated the superiority of FCM-RDpA over MBGD-RDA, especially when the feature dimensionality is higher. We also propose an additional approach, FCM-RDpAx, that further improves FCM-RDpA by using augmented features in both the antecedents and consequents of the rules. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based number detection and recognition for gas meter reading

引用

IEIE Transactions on Smart processing and Computing 2019年第5期8卷 367-372页

作者： Son, Changeui Park, Seokmok Lee, JaeMin Paik, Joonki Department of Image Engineering Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul06974 Korea Republic of

The meter reading-system field has been researched from conventional methods centered on image processing technology to techniques based on learning methods such as machine learning or deep learning. The biggest problem for meter reading systems based on computer vision is difficulty in recognizing the various kinds of meters. In fact, there are more than five major manufacturers for the meters installed in Korea. There are different meter reading areas, ID regions, and number formats by version. Because of these problems, most of the meter reading is still done hands-on. In this paper, we present an automatic meter-reading system that can work simply and efficiently, compared to existing meter reading systems that need a skilled worker. Our meter reading system consists of three parts: i) detection of meter-reading and ID regions using You Only Look Once (YOLO), ii) digit segmentation for recognition, and iii) convolutional neural network (CNN)-based digit recognition. It is possible to robustly detect and recognize various meter types by using the method presented here. Therefore, it can provide an environment where gas meter checkers can work efficiently without inconvenient procedures. Copyrights © 2019 The Institute of Electronics and Information Engineers

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Variational low-light image enhancement based on a haze model

引用

IEIE Transactions on Smart processing and Computing 2018年第4期7卷 325-331页

作者： Shin, Joongchol Park, Hasil Park, Jinho Ha, Jinsol Paik, Joonki Image Processing and Intelligent Systems Laboratory Department of Image Engineering Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University / Seoul Korea Republic of Department of Integrative Engineering Chung-Ang University Seoul Korea Republic of

Under low-illumination conditions, an acquired image is degraded by a limited dynamic range and noise in signal amplification. To solve this problem, we propose a haze model-based variational low-light image-enhancement method. The proposed method includes two steps: i) estimation of the initial transmission map using block-based dark channel prior and a Gaussian pyramid, and ii) L2-norm regularized optimization based on the haze model. Experimental results show that the proposed enhancement method outperforms conventional state-of-the-art methods in terms of visible contrast without noise amplification. Copyrights © 2018 The Institute of Electronics and Information Engineers.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robust kernelized correlation filter using adaptive feature weight

引用

IEIE Transactions on Smart processing and Computing 2018年第6期7卷 433-439页

作者： Kim, Yeongbin Park, Hasil Paik, Joonki Image Processing and Intelligent Systems Laboratory Department of Image Engineering Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Republic of Department of Integrative Engineering Chung-Ang University Seoul Korea Republic of

In this paper, we propose a robust tracking method for fast motion and background noise via improved kernelized correlation filters (KCFs). The proposed tracking algorithm consists of four steps: i) generate a Gaussian blurred image of the input image, ii) compute each correlation response and weight update score, iii) compute adaptive feature weight using a weight update score, and iv) integrate features using the adaptive feature weight, and train a correlation filter using the integrated features. As a result, the proposed tracking method can robustly track fast motion and background noise. The proposed tracking algorithm can be applied to video surveillance systems and intelligent vehicles. © 2018 Institute of Electronics and Information Engineers. All Rights Reserved.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

arXiv

引用

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Deep tracking using convolutional features and adaptive frame update 8

Deep tracking using convolutional features and adaptive fram...

引用

8th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018

作者： Kim, Yeongbin Park, Hasil Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Republic of

ISBN: (纸本)9781538660959

This paper presents a robust tracking algorithm using convolutional features. The proposed tracking algorithm consists of three steps: I) training correlation filters using features extracted by a convolutional neural network, ii) localizing the target position in the next frame by multiplying weight and correlation response of each layer, and iii) re-training correlation filters every 10-frame using the proposed position error score. Experimental results show that the proposed algorithm outperforms an existing deep learning-based tracker. © 2018 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Contrast enhancement for low-light image enhancement: A survey

引用

IEIE Transactions on Smart processing and Computing 2018年第1期7卷 36-48页

作者： Park, Seonhee Kim, Kiyeon Yu, Soohwan Paik, Joonki Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul06974 Korea Republic of Department of Integrative Engineering Chung-Ang University Seoul06974 Korea Republic of

In this paper, various contrast and low-light image enhancement methods are described and classified into three categories: I) histogram-based, ii) transmission map-based, and iii) retinexbased. The performance of the image enhancement algorithms is evaluated by comparing the resulting images using low-contrast and low-light images acquired under different illumination conditions. Various image enhancement algorithms are analyzed for both performance and efficiency. The described image enhancement algorithms can be applied to various visual surveillance or video analytics applications with low-light, low-contrast video input. © 2018 The Institute of Electronics and Information Engineers.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

BoostTree and BoostForest for Ensemble Learning

arXiv

引用

arXiv 2020年

作者： Zhao, Changming Wu, Dongrui Huang, Jian Yuan, Ye Zhang, Hai-Tao Peng, Ruimin Shi, Zhenhua Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China The Autonomous Intelligence Unmanned Systems Engineering Research Center of Ministry of Education of China The State Key Lab of Digital Manufacturing Equipment and Technology Wuhan China

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This paper proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

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：