检索结果-内蒙古大学图书馆

11th Asian Conference on Computer Vision, ACCV 2012

作者： Huang, Zhiwu Shan, Shiguang Zhang, Haihong Lao, Shihong Chen, Xilin Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China OMRON Social Solutions Co. Ltd. Kyoto Japan

ISBN: (纸本)9783642374432

Recently, more and more approaches are emerging to solve the cross-view matching problem where reference samples and query samples are from different views. In this paper, inspired by Graph Embedding, we propose a unified framework for these cross-view methods called Cross-view Graph Embedding. The proposed framework can not only reformulate most traditional cross-view methods (e.g., CCA, PLS and CDFE), but also extend the typical single-view algorithms (e.g., PCA, LDA and LPP) to cross-view editions. Furthermore, our general framework also facilitates the development of new cross-view methods. In this paper, we present a new algorithm named Cross-view Local Discriminant Analysis (CLODA) under the proposed framework. Different from previous cross-view methods only preserving inter-view discriminant information or the intra-view local structure, CLODA preserves the local structure and the discriminant information of both intra-view and inter-view. Extensive experiments are conducted to evaluate our algorithms on two cross-view face recognition problems: face recognition across poses and face recognition across resolutions. These real-world face recognition experiments demonstrate that our framework achieves impressive performance in the cross-view problems. © 2013 Springer-Verlag.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Benchmarking still-to-video face recognition via partial and local linear discriminant analysis on COX-S2V dataset

Benchmarking still-to-video face recognition via partial and...

引用

11th Asian Conference on Computer Vision, ACCV 2012

作者： Huang, Zhiwu Shan, Shiguang Zhang, Haihong Lao, Shihong Kuerban, Alifu Chen, Xilin Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China OMRON Social Solutions Co. Ltd. Kyoto Japan College of Information Science and Engineering Xinjiang University China

ISBN: (纸本)9783642374432

In this paper, we explore the real-world Still-to-Video (S2V) face recognition scenario, where only very few (single, in many cases) still images per person are enrolled into the gallery while it is usually possible to capture one or multiple video clips as probe. Typical application of S2V is mug-shot based watch list screening. Generally, in this scenario, the still image(s) were collected under controlled environment, thus of high quality and resolution, in frontal view, with normal lighting and neutral expression. On the contrary, the testing video frames are of low resolution and low quality, possibly with blur, and captured under poor lighting, in non-frontal view. We reveal that the S2V face recognition has been heavily overlooked in the past. Therefore, we provide a benchmarking in terms of both a large scale dataset and a new solution to the problem. Specifically, we collect (and release) a new dataset named COX-S2V, which contains 1,000 subjects, with each subject a high quality photo and four video clips captured simulating video surveillance scenario. Together with the database, a clear evaluation protocol is designed for benchmarking. In addition, in addressing this problem, we further propose a novel method named Partial and Local Linear Discriminant Analysis (PaLo-LDA). We then evaluated the method on COX-S2V and compared with several classic methods including LDA, LPP, ScSR. Evaluation results not only show the grand challenges of the COX-S2V, but also validate the effectiveness of the proposed PaLo-LDA method over the competitive methods. © 2013 Springer-Verlag.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

TEMPORALLY MULTIPLE DYNAMIC TEXTURES SYNTHESIS USING PIECEWISE LINEAR DYNAMIC SYSTEMS

TEMPORALLY MULTIPLE DYNAMIC TEXTURES SYNTHESIS USING PIECEWI...

引用

IEEE International Conference on Image processing

作者： Xing Yan Hong Chang Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China

ISBN: (纸本)9781479923427

Real-world nonlinear dynamic textures (DTs) usually consist of temporally multiple linear DTs which cannot be correctly modeled by previous works. In this paper, we propose piecewise linear dynamic systems (PLDS) to model temporally multiple DTs. PLDS simultaneously decides the temporal segmentation, models each DT segment with an LDS and the whole DT by switching between the LDS'. Experimental results verify that PLDS can capture the stochastic and dynamic nature of temporally multiple DTs and it synthesizes nonlinear DTs without decay or divergence. An EM-like algorithm iterating between sequence division and LDS' fitting is adopted to learn the model parameters.

关键词： Temporally Multiple Dynamic Textures Piecewise Linear Dynamic Systems Temporal Segmentation Local Digital Switch model parameters Programmable logic devices textures Stochastic dynamic decay Decay biodeterioration synthesis

来源：评论

学校读者我要写书评

暂无评论

Preface: WCSE 2013

Proceedings - 2013 4th World Congress on Software Engineerin...

引用

Proceedings - 2013 4th World Congress on Software Engineering, WCSE 2013 2013年 xi-xii页

作者： Xu, Li Da Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology China University of Mining and Technology China

来源：评论

学校读者我要写书评

暂无评论

SALIENT REGION DETECTION VIA TEXTURE-SUPPRESSED BACKGROUND CONTRAST

SALIENT REGION DETECTION VIA TEXTURE-SUPPRESSED BACKGROUND C...

引用

IEEE International Conference on Image processing

作者： Jiamei Shuai Laiyun Qing Jun Miao Zhiguo Ma Xilin Chen University of Chinese Academy of Sciences Beijing 100049 China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China

ISBN: (纸本)9781479923427

We propose a novel salient region detection algorithm by texture-suppressed background contrast. We employ a structure extraction algorithm to suppress the small scale textures which are supposed to be not sensitive for human vision system. Then the texture-suppressed image is segmented into homogeneous superpixels. Motivated by the observation that the spatial distribution of the background has a high probability on the boundaries of images, we estimate the background as superpixels near the image boundaries. The saliency of each superpixel is then defined as the summation of its k minimum color distances to the estimated background super-pixels. Finally a post-processing process involving spatial and color adjacency is employed to generate a per-pixel saliency map. Experimental results demonstrate that the proposed method outperforms the state-of-the-art approaches.

关键词： Salient region detection Background contrast Texture suppression Superpixels BACKGROUND images Summation computer vision Boundary value problems Grain boundaries boundary layer Color Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

pNovo+: De Novo Peptide Sequencing and Assembly Using Complementary HCD and ETD Tandem Mass Spectra

pNovo+: De Novo Peptide Sequencing and Assembly Using Comple...

引用

第八届中国蛋白质组学大会

作者： Hao Chi Haifeng Chen Kun He Long Wu Bing Yang Rui-Xiang Sun Jianyun Liu Wen-Feng Zeng Chun-Qing Song Si-Min He Meng-Qiu Dong Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China National Institute of Biological SciencesBeijingBeijing 102206China Laboratory of Intelligent Recognition and Image ProcessingBeijing Key Laboratory of Digital MediaBeihang UniversityBeijing100191China

来源：评论

学校读者我要写书评

暂无评论

Novel Retinex algorithm by interpolation and adaptive noise suppression

引用

Journal of Central South University 2012年第9期19卷 2541-2547页

作者：李武劲古博黄江涛王明辉 College of Computer Science Sichuan University College of Computer and Information Engineering Guangxi Teachers Education University Key Laboratory of Scientific Computing and Intelligent Information Processing of Guangxi Province (Guangxi University)

In order to improve image quality, a novel Retinex algorithm for image enhancement was presented. Different from conventional algorithms, it was based on certain defined points containing the illumination information in the intensity image to estimate the illumination. After locating the points, the whole illumination image was computed by an interpolation technique. When attempting to recover the reflectance image, an adaptive method which can be considered as an optimization problem was employed to suppress noise in dark environments and keep details in other areas. For color images, it was taken in the band of each channel separately. Experimental results demonstrate that the proposed algorithm is superior to the traditional Retinex algorithms in image entropy.

关键词： Retinex algorithm illumination estimation interpolation adaptive noise suppression

来源：评论

学校读者我要写书评

暂无评论

Evaluating structure of complex networks by navigation entropy

Evaluating structure of complex networks by navigation entro...

引用

2012 8th International Conference on Semantics, Knowledge and Grids, SKG 2012

作者： Sun, Xiaoping Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780769547947

Complex networks are extensively studied in various areas such as social networks, biological networks, Internet and WWW. Those networks have many characters such as small-diameter, higher cluster and power-law degree distribution. Small-world is evolved for efficient information transformation and navigation. Thus, navigation is an important functional character of networks. Previous researches mostly focus on understanding the navigability of small-world networks by analyzing the diameter and the routing efficiency. In this paper, we use the navigability to model the basic structural complexity of a network. That is, given a network topology, we need a model to evaluate how complex the topology is. Some network complexity models have been proposed but none of them consider the navigability factor of the network systems. We believe that using the navigability factor to evaluate the network structural complexity is a feasible and reasonable way. We use the adjacent matrix to build a navigation transition matrix and evaluate the randomness of random walks on the transition matrix by defining navigation entropy on it. We use the iteration of the random walk matrix to evaluate the navigability of a network and the complexity of network. That is, the higher the navigation entropy, the higher the randomness of a network. The lower the navigation entropy, the higher the structure of a network. We apply the navigation entropy model on a set of structural and random network topologies to show how the model can show the different complexity of networks. © 2012 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Faceted navigation on text

Faceted navigation on text

引用

2012 8th International Conference on Semantics, Knowledge and Grids, SKG 2012

作者： Xu, Bei Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China

ISBN: (纸本)9780769547947

This paper proposes a method which is not for summarization but for extracting multiple facets from a text according to the keyword sets representing readers' interests, so that readers can obtain the interested facets and carry out faceted navigation on text. A facet is a meaningful combination of the subsets of the text. Previous text process technologies are mostly based on text features such as word frequency, sentence location, syntax analysis and discourse analysis. These approaches neglect the cognition process of human reading. The proposed method considers human reading process. Experiments show that the facet extraction is effective and robust. © 2012 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Effective comic-like representations with embedded regions of interest

Effective comic-like representations with embedded regions o...

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

作者： Herranz, Luis Liu, Huiying Jiang, Shuqiang Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783642347771

Comic-like summaries exploit the narrative structure of comics to create intuitive and easily readable abstracts. However, real comics use complex composition techniques which are difficult to mimic in an unsupervised way as they involve high level semantic understanding. This paper explores the use of visual attention analysis and face detection to embed regions of interest in adjacent images, obtaining more compact yet informative representations. This paper also addresses the generation of the layout, which involves combinatorial optimization problems. In practice, using exhaustive search to solve the problem is not feasible due to the large number of images. A split and merge approach is proposed to effectively address the layout problem, thus the limitations of finding solutions in a wide range of row widths can be avoided. A user study conducted on several episodes of TV series confirmed the utility of the proposed approach. © 2012 Springer-Verlag.

关键词： Face recognition

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：