检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lijuan Duan Chunpeng Wu Jun Miao Laiyun Qing Yu Fu College of Computer Science and Technology Beijing University of Technology Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China School of Information Science and Engineering Chinese Academy and Sciences Beijing China Department of Computing University of Surrey Guildford Surrey UK

In this paper, a new visual saliency detection method is proposed based on the spatially weighted dissimilarity. We measured the saliency by integrating three elements as follows: the dissimilarities between image patches, which were evaluated in the reduced dimensional space, the spatial distance between image patches and the central bias. The dissimilarities were inversely weighted based on the corresponding spatial distance. A weighting mechanism, indicating a bias for human fixations to the center of the image, was employed. The principal component analysis (PCA) was the dimension reducing method used in our system. We extracted the principal components (PCs) by sampling the patches from the current image. Our method was compared with four saliency detection approaches using three image datasets. Experimental results show that our method outperforms current state-of-the-art methods on predicting human fixations.

关键词： Humans Color Visualization Image color analysis Principal component analysis Correlation Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A fuzzy support vector machine algorithm with dual membership based on hypersphere

引用

Journal of Computational information Systems 2011年第6期7卷 2028-2034页

作者： Ding, Shifei Gu, Yaxiang School of Computer Science and Technology China University of Mining and Technology Xuzhou 221116 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100080 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China

In traditional fuzzy support vector machine(FSVM), membership function is established in global scope will reduce the membership of support vectors, and the FSVM based dismissing margin increases the training speed, but will remove some support vector artificially. So, a new algorithm of Fuzzy Support Vector Machine with Dual Membership based on Hypersphere (HDM-FSVM) is proposed. In this algorithm, the two classes of hyperspheres are divided into two parts respectively. Then, according to most support vectors are in the hemispheres which close together, we use the membership function that can enhance the membership of support vector, and because of there are a few of support vectors in other hemispheres, we must ensure the high membership of support vectors and reduce the membership of non-support vector. In order to removal noise and outliers, we introduce a radius controlling factor to control size of hyperspheres, the samples that outside of hyperspheres are considered as noise and outliers. Experimental results show that HDM-FSVM can enhance the classification accuracy rate of the sample sets that contain noise and outliers. Copyright © 2011 Binary information Press.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Topic level sampling towards optimized locality sensitive vocabulary coding

Topic level sampling towards optimized locality sensitive vo...

引用

International Conference on information, Communications and Signal processing

作者： Jie Chen Ling-Yu Duan Bing Li Rongrong Ji Wen Gao Institute of Digital Media School of Electronic Engineering and Computer Science Peking University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781457700293

We propose a novel locality sensitive vocabulary coding scheme to extract compact descriptors for low bit rate visual search. We employ Latent Dirichlet Allocation (LDA) to learn the topic vocabularies of lower dimension to generate compact descriptors. To deal with diverse datasets, LDA model is introduced to subdivide a dataset into groups of images with a topic model, where the code word distributions in each group produce coherent statistics from generative learning. Moreover, our empirical study has shown that the original Bag-of-Word (BoW) is sparse, and the occurrences of non-zero words is coherent within a topic. Our proposed topic-wise vocabulary learning yields a more compact yet discriminative codebook to search images. Given a query image, multiple topics are determined, which is fed into the topic vocabularies to generate more compact topical descriptor. Comparison experiments show our topic-wise locality sensitive vocabulary coding produces more compact and discriminative descriptors than the state-of-the-arts.

关键词： Vocabulary Visualization Encoding Mobile communication Image coding Histograms Bit rate

来源：评论

学校读者我要写书评

暂无评论

一种基于模型共享的半监督多标签图像学习法

一种基于模型共享的半监督多标签图像学习法

引用

第十二届中国虚拟现实大会

作者： ZHANG Da-peng 张大鹏 WEN Jia 闻佳 LIU Xi 刘曦 Institute of Information Science and Engineering Yanshan University Qinhuangdao 066004 China Guan 燕山大学信息科学与工程学院秦皇岛 066004 桂林电子科技大学广西可信软件重点实验室桂林 541004 Institute of Information Science and Engineering Yanshan University Qinhuangdao 066004 China 燕山大学信息科学与工程学院秦皇岛 066004 The Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese 中国科学院计算技术研究所智能信息处理重点实验室北京 100190

提出一种快速且有效的半监督多标签学习方法：模型共享半监督推举。该方法能发现、共享并组合多个基模型，每个基模型是在某个标签上利用半监督支持向量机(S3VM)上学习的。通过使用模型共享，标签关联被显示地利用且对于每个标签来说只... 详细信息

提出一种快速且有效的半监督多标签学习方法：模型共享半监督推举。该方法能发现、共享并组合多个基模型，每个基模型是在某个标签上利用半监督支持向量机(S3VM)上学习的。通过使用模型共享，标签关联被显示地利用且对于每个标签来说只需要少量的基模型即可生成最后的决策结果。在Core15k和Mediamill数据集上评估方法，实验结果显示的方法与当前流行的监督和半监督多标签学习方法是可比的。

关键词：信息处理半监督多标签学习算法模型共享支持向量机

来源：评论

学校读者我要写书评

暂无评论

Attention driven face recognition: A combination of spatial variant fixations and glance

Attention driven face recognition: A combination of spatial ...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Chongxiu Wang Laiyun Qing Jun Miao Fang Fang Xilin Chen University of the Chinese Academy of Sciences Beijing Beijing CN Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China

This paper proposes a novel face recognition algorithm inspired by the selective attention of Human Visual System (HVS). We record four observers' eye movements when they are viewing 100 FRGC [1] frontal view face images and find that the observers are highly consistent in the regions fixated. Inspired by the fact that fovea of HVS has a much higher spatial acuity than the periphery, a face recognition algorithm based on spatial variant sampling is proposed to simulate such foveated imaging phenomenon, where more information is reserved for the fixated regions. Moreover, information extracted from glance which adopts the low spatial frequency components of the image is integrated into the face recognition system to elicit a percept that occurs before any fixations. The experimental results on FERET database [2] demonstrate that the proposed method not only reduces the computational cost, but also achieves comparable performance, which shows that the characteristics of the HVS provide valuable insights into face recognition.

关键词： Face Face recognition Observers Humans Pixel Databases Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An improved neural architecture for gaze movement control in target searching

An improved neural architecture for gaze movement control in...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jun Miao Lijuan Duan Laiyun Qing Yuanhua Qiao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China College of Computer Science and Technology Beijing University of Technology Beijing China School of Information Science and Engineering Graduate University of Chinese Academy of Sciences Beijing China College of Applied Science Beijing University of Technology Beijing China

This paper presents an improved neural architecture for gaze movement control in target searching. Compared with the four-layer neural structure proposed in [14], a new movement coding neuron layer is inserted between the third layer and the fourth layer in previous structure for finer gaze motion estimation and control. The disadvantage of the previous structure is that all the large responding neurons in the third layer were involved in gaze motion synthesis by transmitting weighted responses to the movement control neurons in the fourth layer. However, these large responding neurons may produce different groups of movement estimation. To discriminate and group these neurons' movement estimation in terms of grouped connection weights form them to the movement control neurons in the fourth layer is necessary. Adding a new neuron layer between the third layer and the fourth lay is the measure that we solve this problem. Comparing experiments on target locating showed that the new architecture made the significant improvement.

关键词： Neurons Visualization Image coding Encoding Context Feature extraction Equations

来源：评论

学校读者我要写书评

暂无评论

Attention driven face recognition, learning from human vision system

引用

International Journal of Computer science Issues 2011年第5 5-2期8卷 8-13页

作者： Fang, Fang Qing, Laiyun Wang, Chongxiu Miao, Jun Chen, Xilin Gao, Wen School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China Graduate University of Chinese Academy of Science Beijing 100049 China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Digital Media Peking University Beijing 100871 China

This paper proposes a novel face recognition algorithm inspired by Human Visual System (HVS). Firstly, we learn where people look by recording observers' eye movements when they are viewing face images. We find that the observers are consistent in the regions fixated and such fixated regions are selected as the salient regions. Secondly, we represent the face images by four scales of Local Binary Gabor Patterns (LGBPs) for the salient regions whereas one scale LGBPs for the others, inspired by the fact that fovea of HVS has a higher spatial acuity than the periphery. Thirdly, we integrate the global information of face images in face recognition. The experimental results demonstrate that the proposed method learning from human beings is comparable with those learned with machine learning algorithms, which shows that the characteristics of the HVS provide valuable insights into face recognition.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Sparsely Encoded Local Descriptor for face recognition

Sparsely Encoded Local Descriptor for face recognition

引用

International Conference on Automatic Face and Gesture Recognition

作者： Zhen Cui Shiguang Shan Xilin Chen Lei Zhang School of Computer Science and Technology Huaqiao University Xiamen China Chinese Academy and Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN Department of Computing Hong Kong Polytechnic University Hong Kong China

In this paper, a novel Sparsely Encoded Local Descriptor (SELD) is proposed for face recognition. Compared with K-means or Random-projection tree based previous methods, sparsity constraint is introduced in our dictionary learning and sequent image encoding, which implies more stable and discriminative face representation. Sparse coding also leads to an image descriptor of summation of sparse coefficient vectors, which is quite different from existing code-words appearance frequency(/histogram)-based descriptors. Extensive experiments on both FERET and challenging LFW database show the effectiveness of the proposed SELD method. Especially on the LFW dataset, recognition accuracy comparable to the best known results is achieved.

关键词： Face Dictionaries Pixel Training Feature extraction Face recognition Databases

来源：评论

学校读者我要写书评

暂无评论

Assessment of genetically modified food security-first results

引用

Journal of information and Computational science 2011年第12期8卷 2493-2500页

作者： Chai, Jie Wu, Jiyi Cong, Jiang Sun, Xiaohong Kang, Bingyi Deng, Yong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China Hangzhou Key Laboratory of E-Business and Information Security Hangzhou Normal University Zhejiang 310036 China College of Food Science and Technology Shanghai Ocean University Shanghai 201306 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 China Key Subject Laboratory of National Defense for Radioactive Waste and Environmental Security Southwest University of Science and Technology Mianyang 621010 China College of Computer and Information Sciences Southwest University Chongqing 400715 China

With the development of Genetically Modified (GM) food, security issue is being paid increasing attention. In this paper, a comprehensive model taking account factors which influencing GM food security is proposed. Analytical Hierarchy Process (AHP) is used to derive the weight of each attribute in different levels according to their importance. Basic Probability Assignment (BPA) function is generated by the safety degree of each element, then we use BPA function of the Dempster-Shafer evidence to represent the inclination of the elements. The safety degree of GM food will be get when weight was used as the discount factor and each attribute data was combined based on discount combination rule. 1548-7741/Copyright © 2011 Binary information Press.

关键词： Safety factor

来源：评论

学校读者我要写书评

暂无评论

A method for translating belief function models to probability models

引用

Journal of information and Computational science 2011年第10期8卷 1817-1823页

作者： Xu, Peida Wu, Jiyi Li, Ya Cong, Jiang Sun, Xiaohong Kang, Bingyi Deng, Yong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China Hangzhou Key Laboratory of E-Business and Information Security Hangzhou Normal University Zhejiang 310036 China College of Food Science and Technology Shanghai Ocean University Shanghai 201306 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 China Key Subject Laboratory of National defense for Radioactive Waste and Environmental Security Southwest University of Science and Technology Mianyang 621010 China College of Computer and Information Sciences Southwest University Chongqing 400715 China

One of the key issues in the applications of Dempster-Shafer evidence theory is how to make a decision based on Basic Probability Assignment (BPA). The conventional method is Pignistic Probability Transformation (PPT), which transforms BPA to probability distribution with equally assignment. To solve the existing problems of pignistic probability transformation, a new transformation method using an optimization algorithm based on the conflict coefficient k is proposed in this paper. The obtained probability has the minimum conflict coefficient with the original BPA. Numerical examples are used to illustrate the efficiency of the proposed method. © 2011 by Binary information Press.

关键词： Decision making

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：