检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yazhou Liu Shiguang Shan Wenchao Zhang Xilin Chen Wen Gao School of Computer Science and Technology Harbin Institute of Technology Harbin China Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China Institute of Digital Media Peking University Beijing China

This paper proposes a novel descriptor, granularity-tunable gradients partition (GGP), for human detection. The concept granularity is used to define the spatial and angular uncertainty of the line segments in the Hough space. Then this uncertainty is backprojected into the image space by orientation-space partitioning to achieve efficient implementation. By changing the granularity parameter, the level of uncertainty can be controlled quantitatively. Therefore a family of descriptors with versatile representation property can be generated. Specifically, the finely granular GGP descriptors can represent the specific geometry information of the object (the same as Edgelet); while the coarsely granular GGP descriptors can provide the statistical representation of the object (the same as histograms of oriented gradients, HOG). Moreover, the position, orientation, strength and distribution of the gradients are embedded into a unified descriptor to further improve the GGP's representation power. A cascade structured classifier is built by boosting the linear regression functions. Experimental results on INRIA dataset show that the proposed method achieves comparable results to those of the state-of-the-art methods.

关键词： Humans Shape Uncertainty Histograms Support vector machines Support vector machine classification Boosting Detectors Covariance matrix Noise robustness

来源：评论

学校读者我要写书评

暂无评论

Linear support vector machine based on kernel function

引用

Journal of Computational information Systems 2009年第4期5卷 1089-1095页

作者： Gao, Shang Hu, Xuekun Zhang, Zaiyue Cao, Cungen School of Computer Science and Engineering Jiangsu University of Science and Technology Zhenjiang 212003 China Provincial Key Laboratory of Computer Information Processing Technology Soochow University Suzhou 215006 China Institute of Computing Technology The Chinese Academy of Sciences Beijing 100080 China

Support vector machine is kind of novel machine learning method, based on statistical learning theory, which becomes the hotspot of machine learning because of its excellent learning performance. The method of support vector machine has been developed for solving classification and regression problems. Training a support vector machine requires the solutions of a very large quadratic programming problem. The algorithm is usually slow when there are many data. In order to improve the running speed, three regression models based on kernel function are introduced. One of three models is changed into a system of linear equations problem, the other models are changed into linear programming problems and their dual problems are given. Simulation results show the effectiveness of the methods, and the computation complexity are largely reduced. The kernel function and the parameter of models selection are compared and analyzed by means of an example. © 2009 Binary information Press August, 2009.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Active Learning for Chinese Word Sense Disambiguation

Active Learning for Chinese Word Sense Disambiguation

引用

International Conference on Innovative computing, information and Control (ICICIC)

作者： Peng Jin Yunfang Wu Zuxu Dai Yi Liu Laboratory of Intelligent Information Processing and Application Leshan Normal University Leshan China Key Laboratory of Computational Linguistics Ministry of Education Peking University China College of Science Wuhan Institute of Technology Wuhan China

Word sense disambiguation (WSD) suffers from the lack of large scale corpus which annotated with word senses. The reason is that creating this corpus with human annotation is time-consuming and expensive. Active learning could save the human effort to obtain the same quality corpus. We investigate eight Chinese polysemous words and show the effectiveness of active learning for Chinese WSD.

关键词： Entropy Training data Uncertainty Laboratories Sampling methods information processing Large-scale systems Humans Testing Equations

来源：评论

学校读者我要写书评

暂无评论

Fast car detection using image strip features

Fast car detection using image strip features

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wei Zheng Luhong Liang Graduate School of Chinese Academy of Sciences Beijing China Institute of Computing Technology Chinese Academy and Sciences Beijing China Key Lab of Intelligent Information Processing Chinese Academy of Sciences (CAS) Beijing 100190 China

This paper presents a fast method for detecting multi-view cars in real-world scenes. Cars are artificial objects with various appearance changes, but they have relatively consistent characteristics in structure that consist of some basic local elements. Inspired by this, we propose a novel set of image strip features to describe the appearances of those elements. The new features represent various types of lines and arcs with edge-like and ridge-like strip patterns, which significantly enrich the simple features such as haar-like features and edgelet features. They can also be calculated efficiently using the integral image. Moreover, we develop a new complexity-aware criterion for RealBoost algorithm to balance the discriminative capability and efficiency of the selected features. The experimental results on widely used single view and multi-view car datasets show that our approach is fast and has good performance.

关键词： Strips Face detection Object detection Biological system modeling Deformable models Computer vision Content addressable storage Support vector machines Humans Wheels

来源：评论

学校读者我要写书评

暂无评论

A Novel Hebbian Rules Based Method for Computation of Sparse Coding Basis Vectors

A Novel Hebbian Rules Based Method for Computation of Sparse...

引用

International Conference on Natural Computation (ICNC)

作者： Baixian Zou Jun Miao Xiaoling Yang Lijuan Duan Yuanhua Qiao Department of Information Science and Technology College of Arts and Science of Beijing Union University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Tianjin Academy of Agricultural Science Tianjin China College of Computer Science and Technology Beijing Beijing China College of Applied Science Beijing University of Technology Beijing China

Sparse coding has high-performance encoding and ability to express images, sparse encoding basis vector plays a crucial role. The computational complexity of the most existing sparse coding basis vectors of is relatively large. In order to reduce the computational complexity and save the time to train basis vectors. A new Hebbian rules based method for computation of sparse coding basis vectors is proposed in this paper. A two-layer neural network is constructed to implement the task. The main idea of our work is to learn basis vectors by removing the redundancy of all initial vectors using Hebbian rules. The experiments on natural images prove that the proposed method is effective for sparse coding basis learning. It has the smaller computational complexity compared with the previous work.

关键词： Computer science Stability Space technology Collaboration Mathematical model Euclidean distance Extraterrestrial measurements Particle measurements Fitting Game theory

来源：评论

学校读者我要写书评

暂无评论

A ROI quality adjustable rate control scheme for low bitrate video coding

A ROI quality adjustable rate control scheme for low bitrate...

引用

Picture Coding Symposium, PCS

作者： Ling Yang Li Zhang Siwei Ma Debin Zhao Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Institute of Digital Media School of Electronic Engineering and Computer Science Peking University Beijing China Department of Computer Science and Engineering Harbin Institute of Technology Harbin China

This paper proposed a novel Region of Interest (ROI) based rate control algorithm for video communication systems, in which the subjective quality of ROI can be adjusted according to users' requirements. In the proposed scheme, in order to analyze the relationship between subjective quality and encoding parameters, a structural similarity index map - quantization parameter (SSIM-QP) model is established. Through this relation, the possible visual quality range of ROI is defined according to the range of ROI QP, which is predicted by rate control algorithm. Then, with interest levels being identified within the visual quality range, resources allocated to ROI is determined. Finally, considering both the quality of ROI and the entire frame, resource allocation is slightly adjusted. Experimental results demonstrate that the subjective visual quality of ROI in our proposed scheme can be adjustable improved compared to the existing rate control algorithms.

关键词： Bit rate Video coding Quadratic programming Humans Computer science Quantization Resource management Videoconference PSNR Data mining

来源：评论

学校读者我要写书评

暂无评论

Fea-Accu cascade for face detection

Fea-Accu cascade for face detection

引用

IEEE International Conference on Image processing

作者： Shengye Yan Shiguang Shan Xilin Chen Wen Gao Chinese Academy and Sciences Beijing China Institute of Computing Technology Digital Media Research Center Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China School of EE & CS Peking University Beijing China

Aiming at unloading the high training time burden of the popular cascaded classifier, in this paper, a novel cascade structure called Fea-Accu cascade is proposed. In Fea-Accu cascade training, the times of feature selection are largely reduced by enhancing the correlation among different stage classifiers of the cascaded classifier. In detail, for each stage classifier, before selecting new features out, the features selected out by previous stage classifiers are reused through creating new corresponding weak classifiers. To verify the efficiency and effectiveness of the proposed method, experiment is designed on frontal face detection problem. The experimental results show that it can largely reduce the training time. A frontal face detector with state-of-the-art classification performance can be learned in less than 10 hours.

关键词： Face detection Detectors Content addressable storage Design methodology information processing Computer vision Cameras Robustness Boosting Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Gene expression data classification based on non-negative matrix factorization

Gene expression data classification based on non-negative ma...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chun-Hou Zheng Ping Zhang Lei Zhang Xin-Xin Liu Ju Han College of Information and Communication Technology Qufu Normal University Rizhao Shandong China Intelligent Computing Laboratory Institute of Intelligent Machines Chinese Academy and Sciences Hefei Anhui China Institute of automation Qufu Normal University Rizhao Shandong China Biometric Research Center Department of Computing Hong Kong Polytechnic University Hong Kong China Department of Control Engineering Academy of Armored Forces Engineering Beijing China

With the advent of DNA microarrays, it is now possible to use the microarrays data for tumor classification. Yet previous works have not use the nonnegative information of gene expression data. In this paper, we propose a new method for tumor classification using gene expression data. In this method, we first select genes using nonnegative matrix factorization (NMF) and sparse NMF (SNMF). Then we extract features of the selected gene data by virtue of NMF and SNMF. At last, support vector machines (SVM) was applied to classify the tumor samples based on the extracted features. To better fit for classification aim, a modified SNMF algorithm is also proposed. The experimental results on three microarray datasets show that the method is efficient and feasible.

关键词： Gene expression Principal component analysis Independent component analysis Neoplasms Data mining Feature extraction Data analysis Humans Bioinformatics DNA

来源：评论

学校读者我要写书评

暂无评论

Automated Design of Logic Circuits with a Increasable Evolution Approach

Automated Design of Logic Circuits with a Increasable Evolut...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Guoliang He Naixue Xiong Athanasios V. Vasilakos Yuanxiang Li Zhongzhi Shi State Key Laboratory of Software Engineering Wuhan University of China Wuhan China Key Laboratory of Intelligent Information Process Institute of Computing Technology Chinese Academy and Sciences Beijing China Department of Computer Science Georgia State University USA Department of Computer Science Saint Francis Xavier University Canada

Since the scalability of logic circuits is becoming larger and more complex, the auto-design is becoming more and more difficult. In order to improve automatic design and performance evaluation of logic circuits in efficiency and capability of optimization, multiobjective simulated annealing (MSA) based increasable evolution approach is designed to evolve logic circuits automatically with an extended matrix encoding method, which can be able to reflect the potential performance of a circuit and reduce the risk of deleting a circuit with a good developing potential during evolution is devised. In the process of evolution, each individual is renewedly associated to a corresponding objective in terms of a novel adaptive evaluation method at each generation. In experiments, complicated arithmetic circuits are designed to assess the performance of MSA against other algorithms. Results indicate that the proposed method could design logic circuits efficiently.

关键词： Logic circuits Encoding Hardware Scalability Circuit simulation Simulated annealing Genetic algorithms Laboratories Computer science Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Data-deficiency-tolerated method for viewpoint independent sign language recognition

引用

Jisuanji Xuebao/Chinese Journal of Computers 2009年第5期32卷 953-961页

作者： Wang, Qi Chen, Xi-Lin Wang, Chun-Li Gao, Wen School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China School of Information Science and Technology Dalian Maritime University Dalian 116026 China School of Electronics Engineering and Computer Science Peking University Beijing 100871 China

This paper proposes a Sample-Consensus method for viewpoint independent sign language recognition under data deficiency (matched features are possibly deficient with regard to some frame pairs). The proposed method is based on the epipolar geometry and inspired by RANSAC. The basic idea is that all corresponded frames between two sequences of the same sign can be roughly considered as captured synchronously by a virtual stereo vision system and thus they will satisfy the same fundamental matrix. In addition, the fundamental matrix can be estimated from point correspondences contained by some part of corresponding frames. Experimental results demonstrate the efficiency of the proposed method. Moreover, this Sample-Consensus method can be easily extended to some similar problems, such as viewpoint independent activity analysis and rigid-motion analysis.

关键词： Stereo image processing

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：