检索结果-内蒙古大学图书馆

2024 International Conference on computing, Machine Learning and Data Science, CMLDS 2024

作者： Cheng, Yan Huang, Zou Wang, Guixi Lai, Jianming Xiong, Yuqi School of Software Jiangxi Normal University Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing China School of Digital Industry Jiangxi Normal University Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing China

ISBN: (纸本)9798400716393

Existing portrait segmentation methods are easily affected by the background. To address this challenge, we propose a simple convolution-based portrait segmentation algorithm to solve the problems of complex background, low accuracy and poor efficiency in real environments. Combined with multi-scale convolution, we design a multi-scale sandglass module structure (MultiScale-Sandglass-CA, MSC), which expands the depth and width of the network without increasing the number of parameters, and enhances the feature learning ability of the model for complex backgrounds;and the MSC module is used for feature extraction, and the introduction of coordinate attention mechanism not only improves the learning ability of the portrait features, but also enhances the network's ability to learn the key information. The introduction of the coordinate attention mechanism not only improves the learning ability of the portrait features, but also enhances the focusing of the network on the key information;at the same time, the introduction of the hybrid loss function, which helps to obtain clear portrait edges. Experiments are conducted on Matting and EG1800 public datasets, and the results show that the algorithm can significantly improve the mean intersection and merger ratio (mIoU) and pixel accuracy (Acc), etc. The mIoU can reach up to 97%, and the pixel accuracy can reach up to 10%. Among them, the mIoU index can reach 97.91% (Matting) and 94.72% (EG1800). Compared with the mIoU predicted by PortraitNet, it is 1.29% and 1.19% higher, respectively. In addition, experiments are conducted for the MSC structure proposed in this paper, which proves the superiority of the model in this paper. © 2024 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

2-D shape completion with shape priors

引用

Chinese Science Bulletin 2013年第27期58卷 3430-3436页

作者： GUO Ge JIANG TingTing WANG YiZhou GAO Wen Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Graduate University of Chinese Academy of Sciences National Engineering Laboratory for Video Technology Key Laboratory of Machine Perception School of EECS Peking University

We propose new techniques for 2-D shape/contour completion, which is one of the important research topics related to shape analysis and computer vision, e.g. the detection of incomplete objects due to occlusion and noises. The purpose of shape completion is to find the optimal curve segments that fill the missing contour parts, so as to acquire the best estimation of the original complete object shapes. Unlike the previous work using local smoothness or minimum curvature priors, we solve the problem under a Bayesian formulation taking advantage of global shape prior knowledge. With the priors, our methods are expert in recovering significant shape structures and dealing with large occlusion cases. There are two different priors adopted in this paper: (i) A generic prior model that prefers minimal global shape transformation (including non-rigid deformation and affine transformation with respect to a reference object shape) of the recovered complete shape; and (ii) a class-specific shape prior model learned from training examples of an object category, which prefers the reconstructed shape to follow the learned shape variation models of the category. Efficient contour completion algorithms are suggested corresponding to the two types of priors. Our experimental results demonstrate the advantage of the proposed shape completion approaches compared to the existing techniques, especially for objects with complex structure under severe occlusion.

关键词：形状结构计算机视觉贝叶斯公式电子相关最佳估计最小曲率先验知识仿射变换

来源：评论

学校读者我要写书评

暂无评论

Pixels Matching in No Obvious Feature Area in Binocular Vision Based on Peripheral Feature Points

Pixels Matching in No Obvious Feature Area in Binocular Visi...

引用

2018 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2018

作者： Chen, Renlong Liu, Mingjun Gong, Xueyan Li, Jinping Shandong College University Key Laboratory of Information Processing and Cognitive Computing in 13th Fiveyear Jinan China

ISBN: (纸本)9781728105512

In binocular vision, the pixel matching of no obvious feature refers to the matching of pixels in the area where the gray value does not change significantly or in the area where there is no significant gradient change in the gray level. The basic idea is that the position of the matching pixels in the area with no obvious features can be determined by the peripheral feature points. First, the camera is calibrated by the chessboard calibration method, and the internal and external parameters of the camera are obtained. The distortion of the left and right images is corrected by the calibration results. Then, the SIFT algorithm is used to extract the feature points, the Euclidean distance threshold is set to determine the better matching points, and the random sample consensus (RANSAC) algorithm is used to eliminate the wrong matching points. Finally, four target matching points with the same distance and direction information are obtained, and the final target matching points are obtained by averaging the four target matching points. Experiments show that any pair of pixels in the unmarked area can be matched accurately. © 2018 IEEE.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Optimizing radial basis function neural network based on rough sets and affinity propagation clustering algorithm

引用

Journal of Zhejiang University-Science C(Computers and Electronics) 2012年第2期13卷 131-138页

作者： Xin-zheng XU Shi-fei DING Zhong-zhi SHI Hong ZHU School of Computer Science and Technology China University of Mining and TechnologyXuzhou 221116China Key Laboratory of Intelligent information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China

A novel method based on rough sets (RS) and the affinity propagation (AP) clustering algorithm is developed to optimize a radial basis function neural network (RBFNN). First, attribute reduction (AR) based on RS theory, as a preprocessor of RBFNN, is presented to eliminate noise and redundant attributes of datasets while determining the number of neurons in the input layer of RBFNN. Second, an AP clustering algorithm is proposed to search for the centers and their widths without a priori knowledge about the number of clusters. These parameters are transferred to the RBF units of RBFNN as the centers and widths of the RBF function. Then the weights connecting the hidden layer and output layer are evaluated and adjusted using the least square method (LSM) according to the output of the RBF units and desired output. Experimental results show that the proposed method has a more powerful generalization capability than conventional methods for an RBFNN.

关键词： Radial basis function neural network （RBFNN） Rough sets Affinity propagation Clustering

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Framework for Secure Storage and Sharing of Resumes

引用

Computers, Materials & Continua 2022年第9期72卷 5395-5413页

作者： Huanrong Tang Changlin Hu Tianming Liu Jianquan Ouyang Key Laboratory of Intelligent Computing and Information Processing Ministry of EducationComputer Science College of Xiangtan UniversityXiangtanHunan ProvinceChina Department of Computer Science The University of GeorgiaAthensGeorgiaUSA

In response to problems in the centralized storage of personal resumes on third-party recruitment platforms,such as inadequate privacy protection,inability of individuals to accurately authorize downloads,and inability to determine who downloaded the resume and when,this study proposes a blockchain-based framework for secure storage and sharing of *** can employ an authorized access mechanism to protect their privacy *** proposed framework uses smart contracts,interplanetary file system,symmetric encryption,and digital signatures to protect,verify,and share *** keys are split and stored in multiple depositories through secret-sharing technology to improve the security of these *** key escrow incentives are implemented using smart contracts to automatically verify the correctness of keys and encourage the active participation of honest key escrow *** framework combines blockchain and searchable symmetric encryption technology to realize multikeyword search using inverted indexing and Bloom filters and verify search results on the *** search service fees are charged through *** after the search results are verified can the search service provider obtain the search fee,thus ensuring fair and efficient search for encrypted *** framework is decentralized,secure,and tamper-evident,and achieves controlled sharing while protecting personal privacy and information security.

关键词： Resume blockchain interplanetary file system secret sharing searchable encryption

来源：评论

学校读者我要写书评

暂无评论

A computational model for feature binding

引用

Science China(Life Sciences) 2008年第5期51卷 470-478页

作者： SHI ZhiWei1,2, SHI ZhongZhi1, LIU Xi1,2 & SHI ZhiPing1 1 key laboratory of intelligent information processing, Institute of computing Technology, Chinese Academy of Sciences, Beijing 100190, China 2 Graduate University of Chinese Academy of Sciences, Beijing 100049, China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100049 China

The "Binding Problem" is an important problem across many disciplines, including psychology, neuroscience, computational modeling, and even philosophy. In this work, we proposed a novel computational model, Bayesian Linking Field Model, for feature binding in visual perception, by combining the idea of noisy neuron model, Bayesian method, Linking Field Network and competitive mechanism. Simulation Experiments demonstrated that our model perfectly fulfilled the task of feature binding in visual perception and provided us some enlightening idea for future research.

关键词： Binding Problem computational model Bayesian Linking Field Model

来源：评论

学校读者我要写书评

暂无评论

Plankton Classification with Deep Convolutional Neural Networks

Plankton Classification with Deep Convolutional Neural Netwo...

引用

2016 IEEE information Technology,Networking,Electronic and Automation Control Conference(ITNEC 2016)

作者： Ouyang py Hu Hong Shi zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9781467391955

Traditional methods for measuring and monitoring plankton populations are time consuming and can not scale to the granularity or scope necessary for large-scale *** approaches are needed. Manual analysis of the imagery captured by underwater camera system is infeasible. Automated image classification using machine learning tools is an alternative to the manual approach. In this paper, we present a deep neural network model for plankton classification which exploits translational and rotational symmetry. In this work, we propose two constrains in the design of deep convolutional neural network structure to guarantee the performance gain when going ***, for each convolutional layer, its capacity of learning more complex patterns should be guaranteed;Secondly, the receptive field of the topmost layer should be no larger than the image region. We also developed a "inception layer" like structure to deal with multi-size imagery input with convolutional neural network. The experimental result on Plankton Set 1.0 imagery data set show the feasibility and effectiveness of the proposed method.

关键词： deep learning image classification convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Overlapping community‐based particle swarm optimization algorithm for influence maximization in social networks

引用

CAAI Transactions on Intelligence Technology 2023年第3期8卷 893-913页

作者： Lei Zhang Yutong Liu Haipeng Yang Fan Cheng Qi Liu Xingyi Zhang Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Intelligent Computing and Signal Processing of Ministry of EducationSchool of Computer Science and TechnologyAnhui UniversityHefeiChina School of Computer Science and Technology University of Science and Technology of ChinaHefeiChina

Influence maximization,whose aim is to maximise the expected number of influenced nodes by selecting a seed set of k influential nodes from a social network,has many applications such as goods advertising and rumour *** the existing influence maximization methods,the community‐based ones can achieve a good balance between effectiveness and ***,this kind of algorithm usually utilise the network community structures by viewing each node as a non‐overlapping *** fact,many nodes in social networks are overlapping ones,which play more important role in influence *** this end,an overlapping community‐based particle swarm opti-mization algorithm named OCPSO for influence maximization in social networks,which can make full use of overlapping nodes,non‐overlapping nodes,and their interactive information is ***,an overlapping community detection algorithm is used to obtain the information of overlapping community structures,based on which three novel evolutionary strategies,such as initialisation,mutation,and local search are designed in OCPSO for better finding influential *** results in terms of influence spread and running time on nine real‐world social networks demonstrate that the proposed OCPSO is competitive and promising comparing to several state‐of‐the‐arts(***,CMA‐IM,CIM,CDH‐SHRINK,CNCG,and CFIN).

关键词： computational intelligence data mining social network

来源：评论

学校读者我要写书评

暂无评论

Research on batch scheduling in cloud computing

引用

Telkomnika (Telecommunication computing Electronics and Control) 2016年第4期14卷 1454-1461页

作者： Jiao, Jintao Yu, Wensen Guo, Lei School of Mathematics and Computer Science Wuyi University Wuyishan354300 China The Key Laboratory of Cognitive Computing Intelligent Information Processing of Fujian Education Institutions Wuyishan354300 China Collaborative Innovation Center of Chinese Oolong Tea Industry Wuyishan354300 China

In the existing cloud computing environment, batch scheduling strategies mainly focus on the management of resources allocation. This paper provides the task scheduling algorithm based on service quality which fully considers priority and scheduling deadline. The improved algorithm combines the advantages of Min-min algorithm with higher throughput and linear programming with global optimization, considers not only all the tasks but also the high priority tasks. The experiment result shows that compared with the Min-min and DBCT the completed tasks of the improved algorithm increase about 10.6% and 22.0%, on the other hand the completed high priority tasks also increases approximately 20% and 40%. © 2016 Universitas Ahmad Dahlan.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Audio-guided self-supervised learning for disentangled visual speech representations

引用

Frontiers of Computer Science 2024年第6期18卷 277-279页

作者： Dalu FENG Shuang YANG Shiguang SHAN Xilin CHEN Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

1 *** visual speech representations from talking face videos is an important problem for several speech-related tasks,such as lip reading,talking face generation,and audiovisual speech separation[1,2].The key difficulty lies in tackling speech-irrelevant factors presented in the videos,such as lighting,resolution,viewpoints,and head motion.

关键词： such dis visual

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：