检索结果-内蒙古大学图书馆

20th ACM International Conference on Multimedia, MM 2012

作者： Bu, Jiajun Xu, Bin Wu, Chenxia Chen, Chun Zhu, Jianke Cai, Deng He, Xiaofei Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781450310895

Recently, the task of unsupervised face-name association has received a considerable interests in multimedia and information retrieval communities. It is quite different with the generic facial image annotation problem because of its unsupervised and ambiguous assignment properties. Specifically, the task of face-name association should obey the following three constraints: (1) a face can only be assigned to a name appearing in its associated caption or to null;(2) a name can be assigned to at most one face;and (3) a face can be assigned to at most one name. Many conventional methods have been proposed to tackle this task while suffering from some common problems, eg, many of them are computational expensive and hard to make the null assignment decision. In this paper, we design a novel framework named face-name association via commute distance (FACD), which judges face-name and face-null assignments under a unified framework via commute distance (CD) algorithm. Then, to further speed up the on-line processing, we propose a novel anchor-based commute distance (ACD) algorithm whose main idea is using the anchor point representation structure to accelerate the eigen-decomposition of the adjacency matrix of a graph. Systematic experiment results on a large scale and real world image-caption database with a total of 194,046 detected faces and 244,725 names show that our proposed approach outperforms many state-of-the-art methods in performance. Our framework is appropriate for a large scale and real-time system. © 2012 ACM.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Document summarization based on data reconstruction 26

Document summarization based on data reconstruction

引用

26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference, AAAI-12 / IAAI-12

作者： He, Zhanying Chen, Chun Bu, Jiajun Wang, Can Zhang, Lijun Cai, Deng He, Xiaofei Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou 310027 China State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou 310058 China

ISBN: (纸本)9781577355687

Document summarization is of great value to many real world applications, such as snippets generation for search results and news headlines generation. Traditionally, document summarization is implemented by extracting sentences that cover the main topics of a document with a minimum redundancy. In this paper, we take a different perspective from data reconstruction and propose a novel framework named Document Summarization based on Data Reconstruction (DSDR). Specifically, our approach generates a summary which consist of those sentences that can best reconstruct the original document. To model the relationship among sentences, we introduce two objective functions: (1) linear reconstruction, which approximates the document by linear combinations of the selected sentences;(2) nonnegative linear reconstruction, which allows only additive, not subtractive, linear combinations. In this framework, the reconstruction error becomes a natural criterion for measuring the quality of the summary. For each objective function, we develop an efficient algorithm to solve the corresponding optimization problem. Extensive experiments on summarization benchmark data sets DUC 2006 and DUC 2007 demonstrate the effectiveness of our proposed approach. Copyright © 2012, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Efficient online learning for large-scale sparse Kernel logistic regression 26

Efficient online learning for large-scale sparse Kernel logi...

引用

26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference, AAAI-12 / IAAI-12

作者： Zhang, Lijun Jin, Rong Chen, Chun Bu, Jiajun He, Xiaofei Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou 310027 China Department of Computer Science and Engineering Michigan State University East Lansing MI 48824 United States State Key Lab of CADandCG College of Computer Science Zhejiang University Hangzhou 310058 China

ISBN: (纸本)9781577355687

In this paper, we study the problem of large-scale Kernel Logistic Regression (KLR). A straightforward approach is to apply stochastic approximation to KLR. We refer to this approach as non-conservative online learning algorithm because it updates the kernel classifier after every received training example, leading to a dense classifier. To improve the sparsity of the KLR classifier, we propose two conservative online learning algorithms that update the classifier in a stochastic manner and generate sparse solutions. With appropriately designed updating strategies, our analysis shows that the two conservative algorithms enjoy similar theoretical guarantee as that of the non-conservative algorithm. Empirical studies on several benchmark data sets demonstrate that compared to batch-mode algorithms for KLR, the proposed conservative online learning algorithms are able to produce sparse KLR classifiers, and achieve similar classification accuracy but with significantly shorter training time. Furthermore, both the sparsity and classification accuracy of our methods are comparable to those of the online kernel SVM. Copyright © 2012, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A new one-bit diFFerence collision attack on HAVAL-128

引用

science China(Information sciences) 2012年第11期55卷 2521-2529页

作者： ZHANG WenYing1,2,3,LI YanYan1 & WU Lei1 1School of Information science and Engineering,Shandong Normal University,Jinan 250014,China 2state key lab of Information Security,Institute of Information Engineering,Chinese Academy of sciences,Beijing 100093,China 3Shandong Provincial key laboratory for Novel Distributed computer Software Technology,Jinan 250014,China School of Information Science and Engineering Shandong Normal University Jinan China State Key Lab of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China

In this paper,we give a new fast attack on *** attack includes many present methods of constructing hash ***,we present a neighborhood *** propose a new difference path different from the previous *** conclusion is that,when the output of each step satisfies our condition,the message m can collide with m'= m + Δm,where Δm =(0,0,0,0,231,0,...,0).There is only one bit difference between m and m'.Two pairs of collision examples for HAVAL-128 are *** order to improve the probability of collision,we use four tricks of message *** attack's running time is less than 225.83 2-pass HAVAL computations,which is the best result for one-bit collision of HAVAL so far.

关键词： cryptography hash function HAVAL-128 collision message modification

来源：评论

学校读者我要写书评

暂无评论

Tele-AR system based on real-time camera tracking

Tele-AR system based on real-time camera tracking

引用

2012 International Conference on Virtual Reality and Visualization, ICVRV 2012

作者： Wang, Yanke Zhong, Fan Li, Chao Xiang, Hui Peng, Qunsheng Qin, Xueying School of Computer Science and Technology Shandong University Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan China State Key Lab. of CAD and CG Zhejiang University Hangzhou China

ISBN: (纸本)9780769548364

We propose a visual tele-AR system, which is a combination of tele-existence and AR techniques. By wearing a video see-through HMD and moving his head, a user in this system is able to tele-operate a remote pan-tilt platform to observe the remote scene. Unlike traditional tele-existence systems which use mechanical or magnetic sensors for tele-operation, we propose a novel tele-operation method based on real-time tracking of master and slave cameras. The master camera is a component of the video see-through HMD mounted in front of user's eyes, while the slave camera is carried by a remote platform. We estimate use's head motion by tracking the master camera in real time, and translate head motions into motion commands to drive the remote pan-tilt platform. Ideally, motion of the remote platform will be exactly the same as user's head. Unfortunately, motion speed of the slave platform is usually limited by their mechanical capability, which may cause pose inconsistence between master and slave cameras, especially when user's head moves fast. We solve this problem by also tracking slave camera in real time, and warping video images according to difference between master and slave camera pose. Since slave camera is tracked, we can integrate virtual objects into remote scene, giving the user an augmented visual sense. To reduce system delay, our implementation is accelerated GPU parallel computation. Experimental results show the efficiency and robustness of our method. © 2012 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Modeling the locality in graph traversals

Modeling the locality in graph traversals

引用

41st International Conference on Parallel Processing, ICPP 2012

作者： Yuan, Liang Ding, Chen Štefankovič, Daniel Zhang, Yunquan Lab. of Parallel Software and Computational Science Institute of Software Chinese Academy of Sciences China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Graduate University of Chinese Academy of Sciences China Computer Science Department University of Rochester United States

ISBN: (纸本)9780769547961

An increasing number of applications in physical and social sciences require the analysis of large graphs. The efficiency of these programs strongly depends on their memory usage especially the locality of graph data access. Intuitively, the locality in computation should reflect the locality in graph topology. Existing locality models, however, operate either at program level for regular loops and arrays or at trace level for arbitrary access streams. They are not sufficient to characterize the relation between locality and connectivity. This paper presents a new metrics called the vertex distance and uses it to model the locality in breadth-first graph traversal (BFS). It shows three models that use the average node degree and the edge distribution to predict the number of BFS levels and the reuse distance distribution of BFS. Finally, it evaluates the new models using random and non-random graphs. © 2012 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Two new local search strategies for minimum vertex cover 26

Two new local search strategies for minimum vertex cover

引用

26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference, AAAI-12 / IAAI-12

作者： Cai, Shaowei Su, Kaile Sattar, Abdul Key Laboratory of High Confidence Software Technologies Peking University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Institute for Integrated and Intelligent Systems Griffith University Brisbane QLD Australia ATOMIC Project Queensland Research Lab. NICTA Australia

ISBN: (纸本)9781577355687

In this paper, we propose two new strategies to design efficient local search algorithms for the minimum vertex cover (MVC) problem. There are two main drawbacks in state-of-the-art MVC local search algorithms: First, they select a pair of vertices to be exchanged simultaneously, which is time consuming;Second, although they use edge weighting techniques, they do not have a strategy to decrease the weights. To address these drawbacks, we propose two new strategies: two stage exchange and edge weighting with forgetting. The two stage exchange strategy selects two vertices to be exchanged separately and performs the exchange in two stages. The strategy of edge weighting with forgetting not only increases weights of uncovered edges, but also decreases some weights for each edge periodically. We utilize these two strategies to design a new algorithm dubbed NuMVC. The experimental results show that NuMVC significantly outperforms existing state-of-the-art heuristic algorithms on most of the hard DIMACS instances and all instances in the hard random BHOSLIB benchmark. Copyright © 2012, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Kernel Approach to Multi-Task Learning with Task-Specific Kernels

引用

Journal of computer science & Technology 2012年第6期27卷 1289-1301页

作者：武威李航胡云华金榕 MOE-Microsoft Key Laboratory of Statistics and Information Technology Department of Probability and Statistics School of Mathematical SciencesPeking University Beijing International Center for Mathematical Research Peking University Noah's Ark Lab HuaweiHong Kong Science Park Microsoft Research Asia Department of Computer Science and Engineering Michigan State UniversityEast LansingMI 48824U.S.A.

Several kernel-based methods for multi-task learning have been proposed, which leverage relations among tasks as regularization to enhance the overall learning accuracies. These methods assume that the tasks share the same kernel, which could limit their applications because in practice different tasks may need different kernels. The main challenge of introducing multiple kernels into multiple tasks is that models from different reproducing kernel Hilbert spaces （RKHSs） are not comparable, making it difficult to exploit relations among tasks. This paper addresses the challenge by formalizing the problem in the square integrable space （SIS）. Specially, it proposes a kernel-based method which makes use of a regularization term defined in SIS to represent task relations. We prove a new representer theorem for the proposed approach in SIS. We further derive a practical method for solving the learning problem and conduct consistency analysis of the method. We discuss the relationship between our method and an existing method. We also give an SVM （support vector machine）- based implementation of our method for multi-label classification. Experiments on an artificial example and two real-world datasets show that the proposed method performs better than the existing method.

关键词： multi-task learning kernel method square integrable space support vector machine

来源：评论

学校读者我要写书评

暂无评论

Resource-distortion modeling for video streaming over mesh networks with priority-based packet scheduling

Resource-distortion modeling for video streaming over mesh n...

引用

2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012

作者： Zhang, Yongfei Zhang, Yunsheng Qin, Shiyin He, Zhihai Beijing Key Lab. of Digital Media School of Computer Science and Engineering Beihang University Beijing 100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China Graduate School at Shenzhen Tsinghua University Shenzhen 518055 China Department of Electrical and Computer Engineering University of Missouri Columbia MO 65211 United States

ISBN: (纸本)9781467316590

Video streaming over mesh networks operates under stringent network resource constraints, with a large number of video sessions competing for limited network resources. In this work, we aim to establish so-called resource-distortion models to characterize the inherent relationship between the allocated network resources to each video session and its end-to-end video distortion or presentation quality at the receiver end. We observed that priority-based packet scheduling has significant impact on such resource-distortion relationship. Using ANN-based learning methods, we develop an end-to-end packet delay bound violation (PDBV) probability model for video streaming over multi-hop networks with priority-based packet scheduling. We then derive a quadratic video transmission distortion model to capture the unique behavior of priority-based packet scheduling and its impact on the end-to-end video distortion. Based on these resource-distortion models, we are able to predict the end-to-end distortion for video streaming over multi-hop networks with priority-based packet scheduling. Our extensive experimental results demonstrate that the proposed method is very accurate. © 2012 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Finger vein verification using Occurrence Probability Matrix (OPM)

Finger vein verification using Occurrence Probability Matrix...

引用

International Joint Conference on Neural Networks

作者： Darun Tang Beining Huang Rongfeng Li Wenxin Li Xiaoming Li Key Laboratory of Machine Perception (MOE) School of Electronics Engineering and Computer Science Peking University State Key Lab of Virtual Reality Technology and Systems Beihang University

ISBN: (纸本)9781467314886

We found that the discrepancy between different finger vein templates of the same finger affects the identification results more seriously than the similarity of templates of different fingers does. Some areas on templates have stable values while some other areas are variable. We propose the Occurrence Probability Matrix (OPM), which is a property of a finger, to define the stability. When matching two templates using OPM, the areas of higher stability make more contribution to the result and those of lower stability make less contribution. In this way, OPM can enhance the similarity of templates of the same finger and drop off the influence of the unsteady areas. In a finger vein verification system running for a long time, we can get enough templates of every finger to generate an effective OPM. But it does not mean that using more templates can get a better OPM. So, we fatherly propose a strategy to select typical templates purposely from all templates of a finger to calculate the OPM. Experimental results show that by simply using OPM calculated from all existing templates, the EER of the system is reduced from 9.8% to 7.6%. And by using the OPM calculated from selected typical templates by our strategy, the EER of the system is further reduced from 7.6% to 3.1%.

关键词： OPM Finger vein Template Stability Selection

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：