检索结果-内蒙古大学图书馆

IEEE International Conference on Performance, computing and Communications (IPCCC)

作者： Tingting Zeng Meng Shen Mingzhong Wang Liehuang Zhu Fan Li Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Institute of Technology P. R. China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education P. R. China Faculty of Arts and Business University of the Sunshine Coast Queensland Australia

Communication privacy and latency perceived by users have become great concerns for delay-sensitive Internet services. Existing anonymous communication systems either provide high anonymity at an expense of prolonged latency (e.g., mix-net), or offer better real-time performance by sacrificing the ability against traffic analysis attacks (e.g., Onion Routing). The emerging Software-Defined Networking (SDN) introduces additional challenges to communication anonymity, due to the existence of a centralized controller that has a global view of the entire network traffic. In this paper, we propose a new anonymous communication scheme for delay-sensitive services under SDN scenarios, which can simultaneously protect communication privacy and reduce the end-to-end latency. A self-adaptive method based on the mix-net framework is designed to dynamically modify the waiting threshold of mix nodes, which helps to reduce the communication latency. In order to preserve the degree of anonymity, the self-adaptive method is incorporated with a random walking strategy for packets forwarding. Both theoretical analysis and experimental results prove that our scheme provides a moderate degree of anonymity and effectively reduces the latency derived from mix-net by up to 50%.

关键词： Real-time systems Relays Entropy Lead Distance measurement Annealing Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Report on the FG 2015 Video Person Recognition Evaluation

Report on the FG 2015 Video Person Recognition Evaluation

引用

International Conference on Automatic Face and Gesture Recognition

作者： J. Ross Beveridge Hao Zhang Bruce A. Draper Patrick J. Flynn Zhenhua Feng Patrik Huber Josef Kittler Zhiwu Huang Shaoxin Li Yan Li Meina Kan Ruiping Wang Shiguang Shan Xilin Chen Haoxiang Li Gang Hua Vitomir Štruc Janez Križaj Changxing Ding Dacheng Tao P. Jonathon Phillips Colorado State University Fort Collins CO USA University of Notre Dame Notre Dame IN USA University of Surrey United Kingdom University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing China Stevens Institute of Technology Hoboken NJ USA University of Ljubljana Ljubljana Slovenia Univerza v Ljubljani Ljubljana SI University of Technology Sydney Sydney Australia National Institute of Standards and Technology Gaithersburg MD USA

This report presents results from the Video Person Recognition Evaluation held in conjunction with the 11th IEEE International Conference on Automatic Face and Gesture Recognition. Two experiments required algorithms to recognize people in videos from the Point-and-Shoot Face Recognition Challenge Problem (PaSC). The first consisted of videos from a tripod mounted high quality video camera. The second contained videos acquired from 5 different handheld video cameras. There were 1401 videos in each experiment of 265 subjects. The subjects, the scenes, and the actions carried out by the people are the same in both experiments. Five groups from around the world participated in the evaluation. The video handheld experiment was included in the International Joint Conference on Biometrics (IJCB) 2014 Handheld Video Face and Person Recognition Competition. The top verification rate from this evaluation is double that of the top performer in the IJCB competition. Analysis shows that the factor most effecting algorithm performance is the combination of location and action: where the video was acquired and what the person was doing.

关键词： Face Feature extraction Face recognition Cameras Training Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Stacked Progressive Auto-Encoders (SPAE) for Face Recognition Across Poses

Stacked Progressive Auto-Encoders (SPAE) for Face Recognitio...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Meina Kan Shiguang Shan Hong Chang Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology

ISBN: (纸本)9781479951192

Identifying subjects with variations caused by poses is one of the most challenging tasks in face recognition, since the difference in appearances caused by poses may be even larger than the difference due to identity. Inspired by the observation that pose variations change non-linearly but smoothly, we propose to learn pose-robust features by modeling the complex non-linear transform from the non-frontal face images to frontal ones through a deep network in a progressive way, termed as stacked progressive auto-encoders (SPAE). Specifically, each shallow progressive auto-encoder of the stacked network is designed to map the face images at large poses to a virtual view at smaller ones, and meanwhile keep those images already at smaller poses unchanged. Then, stacking multiple these shallow auto-encoders can convert non-frontal face images to frontal ones progressively, which means the pose variations are narrowed down to zero step by step. As a result, the outputs of the topmost hidden layers of the stacked network contain very small pose variations, which can be used as the pose-robust features for face recognition. An additional attractiveness of the proposed method is that no pose estimation is needed for the test images. The proposed method is evaluated on two datasets with pose variations, i.e., MultiPIE and FERET datasets, and the experimental results demonstrate the superiority of our method to the existing works, especially to those 2D ones.

关键词： Face Three-dimensional displays Transforms Face recognition Solid modeling Decoding Training

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired visual attention model and saliency guided object segmentation 7

Bio-inspired visual attention model and saliency guided obje...

引用

7th International Conference on Genetic and Evolutionary computing, ICGEC 2013

作者： Duan, Lijuan Gu, Jili Yang, Zhen Miao, Jun Ma, Wei Wu, Chunpeng College of Computer Science and Technology Beijing University of Technology Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Fujitsu Research and Development Center Co. Ltd Beijing China

ISBN: (纸本)9783319017808

In this paper, we present a saliency guided image object segment method. We suppose that saliency maps can indicate informative regions, and filter out background in images. To produce perceptual satisfactory salient objects, we use our bio-inspired saliency measure which integrating three factors: dissimilarity, spatial distance and central bias to compute saliency map. Then the saliency map is used as the importance map in the salient object segment method. Experimental results demonstrate that our method outperforms previous saliency detection method, yielding higher precision (0.7669) and better recall rates (0.825), F-Measure (0.7545), when evaluated using one of the largest publicly available data sets. © Springer International Publishing Switzerland 2014.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial Expression Recognition

Learning Expressionlets on Spatio-Temporal Manifold for Dyna...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Mengyi Liu Shiguang Shan Ruiping Wang Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology

ISBN: (纸本)9781479951192

Facial expression is temporally dynamic event which can be decomposed into a set of muscle motions occurring in different facial regions over various time intervals. For dynamic expression recognition, two key issues, temporal alignment and semantics-aware dynamic representation, must be taken into account. In this paper, we attempt to solve both problems via manifold modeling of videos based on a novel mid-level representation, i.e. expressionlet. Specifically, our method contains three key components: 1) each expression video clip is modeled as a spatiotemporal manifold (STM) formed by dense low-level features;2) a Universal Manifold Model (UMM) is learned over all low-level features and represented as a set of local ST modes to statistically unify all the STMs. 3) the local modes on each STM can be instantiated by fitting to UMM, and the corresponding expressionlet is constructed by modeling the variations in each local ST mode. With above strategy, expression videos are naturally aligned both spatially and temporally. To enhance the discriminative power, the expressionlet-based STM representation is further processed with discriminant embedding. Our method is evaluated on four public expression databases, CK+, MMI, Oulu-CASIA, and AFEW. In all cases, our method reports results better than the known state-of-the-art.

关键词： Databases Manifolds Feature extraction Face recognition Covariance matrices Three-dimensional displays Training

来源：评论

学校读者我要写书评

暂无评论

Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification

Learning Euclidean-to-Riemannian Metric for Point-to-Set Cla...

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Zhiwu Huang Ruiping Wang Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology

ISBN: (纸本)9781479951192

In this paper, we focus on the problem of point-to-set classification, where single points are matched against sets of correlated points. Since the points commonly lie in Euclidean space while the sets are typically modeled as elements on Riemannian manifold, they can be treated as Euclidean points and Riemannian points respectively. To learn a metric between the heterogeneous points, we propose a novel Euclidean-to-Riemannian metric learning framework. Specifically, by exploiting typical Riemannian metrics, the Riemannian manifold is first embedded into a high dimensional Hilbert space to reduce the gaps between the heterogeneous spaces and meanwhile respect the Riemannian geometry of the manifold. The final distance metric is then learned by pursuing multiple transformations from the Hilbert space and the original Euclidean space (or its corresponding Hilbert space) to a common Euclidean sub-space, where classical Euclidean distances of transformed heterogeneous points can be measured. Extensive experiments clearly demonstrate the superiority of our proposed approach over the state-of-the-art methods.

关键词： Manifolds Hilbert space Kernel Extraterrestrial measurements Geometry

来源：评论

学校读者我要写书评

暂无评论

Learning to Rank for Blind Image Quality Assessment

引用

IEEE Transactions on Neural Networks and Learning Systems 2015年第10期26卷 2275-2290页

作者： Gao, Fei Tao, Dacheng Gao, Xinbo Li, Xuelong Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an710071 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology 235 Jones Street Sydney UltimoNSW2007 Australia State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an710071 China State Key Laboratory of Transient Optics and Photonics Xi'An Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi710119 China

Blind image quality assessment (BIQA) aims to predict perceptual image quality scores without access to reference images. State-of-the-art BIQA methods typically require subjects to score a large number of images to train a robust model. However, subjective quality scores are imprecise, biased, and inconsistent, and it is challenging to obtain a large-scale database, or to extend existing databases, because of the inconvenience of collecting images, training the subjects, conducting subjective experiments, and realigning human quality evaluations. To combat these limitations, this paper explores and exploits preference image pairs (PIPs) such as the quality of image Iais better than that of image Ibfor training a robust BIQA model. The preference label, representing the relative quality of two images, is generally precise and consistent, and is not sensitive to image content, distortion type, or subject identity;such PIPs can be generated at a very low cost. The proposed BIQA method is one of learning to rank. We first formulate the problem of learning the mapping from the image features to the preference label as one of classification. In particular, we investigate the utilization of a multiple kernel learning algorithm based on group lasso to provide a solution. A simple but effective strategy to estimate perceptual image quality scores is then presented. Experiments show that the proposed BIQA method is highly effective and achieves a performance comparable with that of state-of-the-art BIQA algorithms. Moreover, the proposed method can be easily extended to new distortion categories. © 2012 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Sign language recognition by 3D trajectory matching in frequency domain

引用

Ruan Jian Xue Bao/Journal of Software 2014年 25卷 36-43页

作者： Lin, Yu-Shun Chai, Xiu-Juan Xu, Zhi-Hao Yin, Fang Chen, Xi-Lin Key Laboratory of Intelligent Information Processing Institute of Computing Technology The Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

For hearing-impaired people, sign language is a common communication means just like spoken language to ordinary people. Because most of ordinary people cannot understand sign language, it's difficult for hearing-impaired community to participate in social activities. This paper proposes an effective method for sign language recognition with simple 3D trajectory information to break down the barriers between hearing-impaired and normal persons. First of all, the 3D trajectory captured from Kinect is preprocessed, and both the trajectories from the probe and galleries is normalized by the size of the signer. Then the trajectories are resampled evenly by a fast, easy, and usable interpolation algorithm. Before matching of two curves, the trajectory of the probe is aligned to the gallery trajectory and both aligned trajectories are transferred into frequency domain by DFT, and vectors linking the real part, imaginary part and amplitude are obtained. Finally, Euclidean distance between two trajectories in frequency domain is calculated to evaluate the dis-similarity of two trajectory vectors according to the minimized distance. The experimental results on a data set of 239 sign words show that the presented approach is effective to recognizing isolated words of Chinese sign language. ©2014 ISCAS.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A parallel scheme for three-dimensional reconstruction in large-field electron tomography

A parallel scheme for three-dimensional reconstruction in la...

引用

10th International Symposium on Bioinformatics Research and Applications, ISBRA 2014

作者： Zhang, Jingrong Wan, Xiaohua Zhang, Fa Ren, Fei Wang, Xuan Liu, Zhiyong Key Lab. of Intelligent Information Processing and Advanced Computing Research Lab Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Yanshan University Yanshan China

ISBN: (纸本)9783319081700

Large-field high-resolution electron tomography enables visualizing detailed mechanisms under global structure. As field enlarges, the processing time increases and the distortions in reconstruction become more critical. Adopting a nonlinear projection model instead of a linear one can compensate for curvilinear trajectories, nonlinear electron optics and sample warping. But the processing time for the reconstruction with nonlinear projection model is rather considerable. In this work, we propose a new parallel strategy for block iterative reconstruction algorithms. We also adopt a page-based data transfer in this strategy so as to dramatically reduce the processing time for data transfer and communication. We have tested this parallel strategy and it can yield speedups of approximate 40 times according to our experimental results. © 2014 Springer International Publishing Switzerland.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach of PTSVM and ELM inspired by samples' geometric distribution structure

A hybrid approach of PTSVM and ELM inspired by samples' geom...

引用

IEEE International Conference on Granular computing (GRC)

作者： Hong Hu Panyi Ouyang Liang Pang Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

In this paper, we try to hybrid projection twin support vector machine (PTSVM) and Extreme Learning Machine(ELM). The experiments shows that ELM generally out performs SVM/LS-SVM in various kinds of cases. PTELM tries to use ELM to overcome the shortness of PTSVM, which lacks of flexibility to change nonlinear kernel mapping for complex samples distribution regions. In order to overcome the shortness of ELMs, we try to maintain the geometric structure of the samples distribution in the initial setting of ELM parameters by starting with an auto-encoder ELM, a sufficient condition for such kind auto-encoder ELM to keep the equivalence of topological homology before and after nonlinear mapping is proved by us. For an auto-encoder, in order to do feature abstraction and find the exact manifold in which samples are located, the number of inner layers nodes should be small enough. For this purpose, we prove that the whole samples set can be at least replaced by a small subset which located on the boundary of distribution region. For more, the weights are modified by a ELM approach to make samples of a class move toward this classs hyperplane found by PTSVM. The experimental results on several UCI benchmark data sets show the feasibility and effectiveness of the proposed method.

关键词： Support vector machines Kernel Training Transforms Shape Vectors Manifolds

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：