检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Liu, Xuejing Li, Liang Wang, Shuhui Zha, Zheng-Jun Su, Li Huang, Qingming 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 School of Information Science and Technology University of Science and Technology of China Hefei China

Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown in the training stage. In referring expressions, people usually describe a target entity in terms of its relationship with other contextual entities as well as visual attributes. However, previous weakly supervised REG methods rarely pay attention to the relationship between the entities. In this paper, we propose a knowledge-guided pairwise reconstruction network (KPRN), which models the relationship between the target entity (subject) and contextual entity (object) as well as grounds these two entities. Specifically, we first design a knowledge extraction module to guide the proposal selection of subject and object. The prior knowledge is obtained in a specific form of semantic similarities between each proposal and the subject/object. Second, guided by such knowledge, we design the subject and object attention module to construct the subject-object proposal pairs. The subject attention excludes the unrelated proposals from the candidate proposals. The object attention selects the most suitable proposal as the contextual proposal. Third, we introduce a pairwise attention and an adaptive weighting scheme to learn the correspondence between these proposal pairs and the query. Finally, a pairwise reconstruction module is used to measure the grounding for weakly supervised learning. Extensive experiments on four large-scale datasets show our method outperforms existing state-of-the-art methods by a large margin1. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Extensive Techniques to Detect Defects in Tyres through Radiography

Extensive Techniques to Detect Defects in Tyres through Radi...

引用

IEEE International Conference on Multi Topic

作者： Muhammad Ahmad Shabir Muhammad Umair Hassan Xiangru Yu Jinping Li Shandong College and University Key Laboratory of Information Processing and Cognitive Computing in 13th Five-year Jinan China School of Information Science and Engineering Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China

ISBN: (数字)9781728140018

ISBN: (纸本)9781728140025

The present paper highlights the experimentation procedure and decomposition of vehicle tyres through the extensive technique of radiography by the incorporation of total changes occurring in the image, transformation of curvelet that is based on image enlargement, and moreover, canny edge detection will examine the patterns through outer surfaces and poor defects in different types of tyres. Keeping into knowledge, the feature appeared after proceeding radiography are decomposed into pattern recognition. In the present paper, the splitting of the tyre into various segments of pattern recognition through image processing is focused on the clear image for selection to detect defects. It is done because the images occurred in the form of segments and recognition to detect the defects in continuity becomes simpler. Suitable modifications is made around the corners of the image appeared and is enhanced by the help of curvelet coefficients initially before the image detection algorithm is carried out. In addition, the result of the analysis is also drawn by incorporating the method of detection called, canny edge and is helpful for the detection of abnormal textures. Moreover, the operator of Sobel and many other detection methods like canny edge algorithms are effective for making comparative and precise discussion on the results of the analysis in brief. It is indicated by the results of analysis through X-ray detection method that outer surfaces of tyre and weak defects inside the tyres are the two different types of detection procedures located clearly by the help of proposed methods.

关键词： Tires Radiography Feature extraction Image edge detection Wires Image segmentation Electronics packaging

来源：评论

学校读者我要写书评

暂无评论

Tyre Defect Detection Based on GLCM and Gabor Filter

Tyre Defect Detection Based on GLCM and Gabor Filter

引用

IEEE International Conference on Multi Topic

ISBN: (数字)9781728140018

ISBN: (纸本)9781728140025

Defect detection is a crucial issue at industrial level, and generally, the designers have to find out a way to select suitable features to detect the defects in textured material images. This work reports this issue using the gray-level co-occurrence matrix (GLCM) and Gabor filter texture segmentation. We first analyze the defects in the corresponding tyre texture images using GLCM and then we apply Gabor filter texture segmentation to illustrate further the impurities found in the material. Our proposed method matches the abnormal textured images with standard texture images, and we use the 5 GLCM features to calculate the score for an abnormal texture image. Further, our proposed method decides the defected tyres and presents the texture segmentation of abnormal image. We found that our proposed method performs well when compares with other methods of tyre images data.

关键词： Gabor filters Feature extraction Tires Inspection Image segmentation Fabrics Filter banks

来源：评论

学校读者我要写书评

暂无评论

Pose-adaptive hierarchical attention network for facial expression recognition

arXiv

引用

arXiv 2019年

作者： Liu, Yuanyuan Peng, Jiyao Zeng, Jiabei Shan, Shiguang School of Geography and Information Engineering China University of Geosciences Wuhan430074 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Center for Excellence in Brain Science and Intelligence Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Multi-view facial expression recognition (FER) is a challenging task because the appearance of an expression varies in poses. To alleviate the influences of poses, recent methods either perform pose normalization or learn separate FER classifiers for each pose. However, these methods usually have two stages and rely on good performance of pose estimators. Different from existing methods, we propose a pose-adaptive hierarchical attention network (PhaNet) that can jointly recognize the facial expressions and poses in unconstrained environment. Specifically, PhaNet discovers the most relevant regions to the facial expression by an attention mechanism in hierarchical scales, and the most informative scales are then selected to learn the poseinvariant and expression-discriminative representations. PhaNet is end-to-end trainable by minimizing the hierarchical attention losses, the FER loss and pose loss with dynamically learned loss weights. We validate the effectiveness of the proposed PhaNet on three multi-view datasets (BU-3DFE, Multi-pie, and KDEF) and two in-the-wild FER datasets (AffectNet and SFEW). Extensive experiments demonstrate that our framework outperforms the state-of-the-arts under both within-dataset and cross-dataset settings, achieving the average accuracies of 84.92%, 93.53%, 88.5%, 54.82% and 31.25% respectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

SEBF: A single-chain based extension model of blockchain for fintech 29

SEBF: A single-chain based extension model of blockchain for...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Ji, Yimu Gu, Weiheng Chen, Fei Xiao, Xiaoying Sun, Jing Liu, Shangdong He, Jing Li, Yunyao Zhang, Kaixiang Mei, Fen Wu, Fei School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing China Institue of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing China Nanjing Center of HPC China Nanjing China Jiangsu HPC and Intelligent Processing Engineer Research Center Nanjing China Institute of Information Technology Nanjing University of Finance and Economics Nanjing China School of Software and Electrical Engineering Swinburne University of Technology Hawthorn Australia WeBank Co. Ltd. Shenzhen China College of Automation Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9780999241165

The traditional blockchain has the shortcoming that a single-chain can only deal with one or a few specific data types. The research question of how to make blockchain be able to deal with various data types has not been well studied. In this paper, we propose a single-chain based extension model of blockchain for fintech (SEBF). In the financial environment, we design a four-layer architecture for this model. By employing the external trusted oracle group and a financial regulator agency, a variety types of data can be effectively stored in the blockchain, such that the data type extension based on a single-chain is realized. The experimental results indicate that the proposed model can improve the efficiency of simplified payment verification. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Automated Selection of Evolutionary Multi-objective Optimization Algorithms

Automated Selection of Evolutionary Multi-objective Optimiza...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Ye Tian Shichen Peng Tobias Rodemann Xingyi Zhang Yaochu Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Honda Research Institute Europe Offenbach/Main Germany Department of Computer Science University of Surrey Guildford Surrey United Kingdom

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

In the last two decades, many evolutionary algorithms have shown promising performance in solving a variety of multi-objective optimization problems (MOPs). Since there does not exist an evolutionary algorithm having the best performance on all the MOPs, it is unreasonable to use a single evolutionary algorithm to tackle all the MOPs. Since many real-world MOPs are computationally expensive, selecting the best evolutionary algorithm from multiple candidates via empirical comparisons is also impractical. To address the above issues, this paper proposes an automated algorithm selection method for choosing the most suitable evolutionary algorithm for a given MOP. The proposed method establishes a predictor based on the performance of a set of candidate evolutionary algorithms on multiple benchmark MOPs, where the inputs of the predictor are the explicit and implicit features of an MOP, and the output is the index of the evolutionary algorithm having the best performance on the MOP. Experimental results indicate that the evolutionary algorithm suggested by the proposed method is highly competitive among all the candidate evolutionary algorithms, demonstrating the practical value of the proposed method for engineers to select an evolutionary algorithm for their applications.

关键词： Evolutionary computation Benchmark testing Feature extraction Optimization Prediction algorithms Convergence Linear programming

来源：评论

学校读者我要写书评

暂无评论

Fair and autonomous sharing of federate learning models in mobile Internet of Things

arXiv

引用

arXiv 2020年

作者： Hao, Xiaohan Ren, Wei Xiong, Ruoting Zheng, Xianghan Zhu, Tianqing Xiong, Neal N. School of Computer Science China University of Geoscience Wuhan China Guangxi Key Laboratory of Cryptography and Information Security Guilin541004 China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Mingbyte Technology QingDao China School of Software University of Technology Sydney UltimoNSW2007 Australia Dept. of Mathematics and Computer Science Northeastern State University United States

Federate learning can conduct machine learning as well as protect the privacy of self-owned training data on corresponding ends, instead of having to upload to a central trusted data aggregation server. In mobile scenarios, a centralized trusted server may not be existing, and even though it exists, the delay will not be manageable, e.g., smart driving cars. Thus, mobile federate learning at the edge with privacy-awareness is attracted more and more attentions. It then imposes a problem - after data are trained on a mobile terminal to obtain a learned model, how to share the model parameters among others to create more accurate and robust accumulative final model. This kind of model sharing confronts several challenges, e.g., the sharing must be conducted without a third trusted party (autonomously), and the sharing must be fair as model training (by training data)is valuable. To tackle the above challenges, we propose a smart contract and IPFS (Inter-Planetary File System) based model sharing protocol and algorithms to address the challenges. The proposed protocol does not rely on a trusted third party, where individual-learned models are shared/stored in corresponding ends. Conducted through extensive experiments, three main steps of the proposed protocol are evaluated. The average executive time of the three steps are 0.059s, 0.060s and 0.032s, demonstrating its efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

An improved Gaussian Mixture Model algorithm for background representation

An improved Gaussian Mixture Model algorithm for background ...

引用

作者： Ping Wang Shaoxiong Dong School of Electrical Engineering and Electronic Information Xihua University Artificial Intelligence Key Laboratory of Sichuan Province Sichuan University of Science and Engineering Science Computing Intelligent Information Processing of GuangXi higher education key laboratory Guangxi Teachers Education University

Initializing a background frame for Gaussian Mixture Model requires no moving objects in the background scene. In this paper, in order to obtain an initial frame when there is a moving object in the background scene, filtering algorithm is used for background frame initialization. This paper proposes an improved method for updating Gaussian mixture *** the initial stage of the GMM, the update rate of the mean and variance is taken as a larger value, so that the model mean and variance update speed becomes faster, and the model learning speed is accelerated;after training for a period of time with a large update rate, let The mean update rate is unchanged, and the variance update rate becomes smaller, so that the background model can be more stable.

关键词： frame Gaussian An improved Gaussian Mixture Model algorithm for background representation Model

来源：评论

学校读者我要写书评

暂无评论

Edge-guided non-local fully convolutional network for salient object detection

arXiv

引用

arXiv 2019年

作者： Tu, Zhengzheng Ma, Yan Li, Chenglong Tang, Jin Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China Institute of Physical Science and Information Technology Anhui University Hefei230601 China

Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN-based methods still suffer from continuous striding and pooling operations leading to loss of spatial structure and blurred edges. To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge-guided feature learning for accurate salient object detection. In a specific, we extract hierarchical global and local information in FCN to incorporate non-local features for effective feature representations. To preserve good boundaries of salient objects, we propose a guidance block to embed edge prior knowledge into hierarchical feature maps. The guidance block not only performs feature-wise manipulation but also spatial-wise transformation for effective edge embeddings. Our model is trained on the MSRA-B dataset and tested on five popular benchmark datasets. Comparing with the state-of-the-art methods, the proposed method achieves the best performance on all datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Syntactic and Semantic Features Based Relation Extraction in Agriculture Domain 15th

Syntactic and Semantic Features Based Relation Extraction in...

引用

15th Web information Systems and Applications Conference, WISA 2018

作者： Liu, Zhanghui Chen, Yiyan Dai, Yuanfei Guo, Chenhao Zhang, Zuwen Chen, Xing College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

ISBN: (纸本)9783030029333

Relation extraction plays an important role in many natural language processing tasks, such as knowledge graph and question answering system. Up to the present, many of the former relation methods work directly on the raw word sequence, so it is often subject to a major limitation: the lack of semantic information, which leads to the problem of the wrong category. This paper presents a novel method to extract relation from Chinese agriculture text by incorporating syntactic parsing feature and word embedding feature. This paper uses word embedding to capture the semantic information of the word. On the basis of the traditional method, this paper integrates the dependency parsing, the core predicate and word embedding features, using the naive Bayes model, support vector machine (SVM) and decision tree to build experiment. We use the websites knowledge base to construct a dataset and evaluate our approach. Experimental results show that our proposed method achieves good performance on the agriculture dataset. The dataset and the word vectors trained by Word2Vec are available at Github (https://***/A-MuMu/*** ). © 2018, Springer Nature Switzerland AG.

关键词： Agriculture

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：