检索结果-内蒙古大学图书馆

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

Shape-based web image clustering for unsupervised object detection?

Shape-based web image clustering for unsupervised object det...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wei Zheng Changhu Wang Xilin Chen Graduate School Chinese Academy and Sciences Beijing China Microsoft Research Asia Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

ISBN: (纸本)9781612843483

Automatic object detection for an arbitrary class is an important but very challenging problem, due to the countless kinds of objects in the world and the large amount of labeling work for each object. In this work, we target at solving the problem of automatic object detection for an arbitrary class without the laborious human effort. Motivated by the explosive growth of Web images and the phenomenal success of search techniques, we develop an unsupervised object detection framework by automatically training the object detector on the top returns of certain image search engine queried by the name of the object class. In order to automatically isolate the objects from the Web images for training, only clipart images with simple background are used, which preserve most of the shape information of the objects. A two-stage shape-based clustering algorithm is proposed to mine typical shapes of the object, in which the inner-class variance of object shapes is considered and undesired images are filtered out. In order to reduce the gap between clipart images and real-world images, we introduce an efficient algorithm to synthesize the real-world images from clipart images, and only shape feature is used in the detector training part. Finally, the synthetic images could be used to train object detectors by an off-the-shelf discriminative algorithm, e.g., boosting or SVM. Extensive experiments show the effectiveness of the proposed framework on objects with simple and representative shapes, and the proposed framework could be considered as a good beginning of solving this challenging problem.

关键词： Shape Clustering algorithms Training Detectors Image edge detection Object detection Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Context constrained facial landmark localization based on discontinuous Haar-like feature

Context constrained facial landmark localization based on di...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Xiaowei Zhao Xiujuan Chai Zhiheng Niu Cherkeng Heng Shiguang Shan Chinese Academy and Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Panasonic Singapore Laboratories Private Limited (PSL) Singapore

Facial landmark localization is well known as one of the bottlenecks in face recognition. This paper proposes a novel facial landmark localization method, which introduces facial context constrains into cascaded AdaBoost framework. The motivation of our method lies in the basic human physiology observation that not only the local texture information but also the global context information is used together for human to realize the landmark location task. Therefore, in our solution, a novel type of Haar-like feature, called discontinuous Haar-like feature, is proposed to characterize the facial context, i.e. the cooccurrence relationship between target facial landmark and other local texture patterns within face region (including other landmarks, facial organs and also smoothing regions). For the locating task, traditional Haar-like features (characterizing local texture information) and discontinuous Haar-like features (characterizing context constrains in global sense) are combined together to form more powerful representations. Through Real AdaBoost learning, distinctive features are selected automatically and used for facial landmark detection. Our experiments on BioID and Cohn-Kanade databases have validated the proposed method by comparing with other state-of-the-art results.

关键词： Context Face Feature extraction Mouth Databases Pixel Accuracy

来源：评论

学校读者我要写书评

暂无评论

Stereoscopic learning for disparity estimation

Stereoscopic learning for disparity estimation

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhebin Zhang Yizhou Wang Tingting Jiang Wen Gao National Engineering Laboratory for Video Technology Peking University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Key Laboratory of Machine Perception (MoE) School of EECS Peking University Beijing China Peking University Beijing Beijing CN

In this paper, we propose a learning based approach to estimating pixel disparities from the motion information extracted out of input monoscopic video sequences. We represent each video frame with superpixels, and extract the motion features from the superpixels and the frame boundary. These motion features account for the motion pattern of the superpixel as well as camera motion. In the learning phase, given a pair of stereoscopic video sequences, we employ a state-of-the-art stereo matching method to compute the disparity map of each frame as ground truth. Then a multi-label SVM is trained from the estimated disparities and the corresponding motion features. In the testing phase, we use the learned SVM to predict the disparity for each superpixel in a monoscopic video sequence. Experiment results show that the proposed method achieves low error rate in disparity estimation.

关键词： Pixel Three dimensional displays Cameras Feature extraction Histograms Support vector machines Optical imaging

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

A NOVEL FRAMEWORK OF ONLINE NETWORK CODING FOR MULTICAST SWITCHES WITH CONSTRAINED BUFFERS

引用

Journal of Electronics(China) 2011年第4期28卷 460-467页

作者： Wang Wei Yu Li Zhu Guangxi Li Hui Wuhan National Laboratory for Optoelectronics Division of Communiction ＆ Intelligent NetworksDepartment of Electronics and Information Engineering Huazhong University of Science and Technology Wuhan 430074 China Shenzhen Key Lab of Cloud Computing Technology ＆ Application Shenzhen Graduate School Peking University Shenzhen 518055 China

Network coding is able to address output conflicts when fanout splitting is allowed for multicast ***,it successfully achieves a larger rate region than non-coding approaches in crossbar ***,network coding requires large coding buffers and a high computational cost on encoding and *** this paper,we propose a novel Online Network Coding framework called Online NC for multicast switches,which is adaptive to constrained ***,it enjoys a much lower decoding complexity by a Vandermonde matrix based approach,as compared to conven-tional randomized network coding Our approach realizes online coding with one coding algo-rithm that synchronizes buffering and ***,we significantly reduce requirements on buffer space,while also sustaining high *** confirm the superior advantages of our contributions using empirical studies.

关键词： Packet switching Multicast Network coding Vandermonde matrix

来源：评论

学校读者我要写书评

暂无评论

Roughness in vector spaces

Roughness in vector spaces

引用

IEEE International Conference on Granular computing (GRC)

作者： Mingfen Wu Xiangyun Xie School of Computer Science Wuyi University Guangdong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Mathematics and Computational Science Wuyi University China

Rough set theory proposed by Pawlak, is a complementary generalization of classical set theory. The relations between rough sets and algebraic systems endowed with two binary operations such as rings, groups and semigroups have been already considered. Wu, Xie and Cao defined a pair of rough approximation operators based on a sub-space. In this paper we do the further study about the upper (lower)approximations. We propose concepts of W-upper(lower) rough subspaces in an approximation space and give some properties of the upper(lower) and rough subspaces. Some characterizations of the upper(lower) rough subspace are expressed with addition and intersection operations of subspaces. At the same time, some counterexamples are offered to illustrate the relevant results.

关键词： Approximation methods Rough sets Vectors Educational institutions Laboratories

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

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

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：