检索结果-内蒙古大学图书馆

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Du, Yong Fu, Yun Wang, Liang Center for Research on Intelligent Perception and Computing CRIPAC China Center for Excellence in Brain Science and Intelligence Technology CEBSIT China Nat'l Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China College of Engineering College of Computer and Information Science Northeastern University United States

ISBN: (纸本)9781479961009

Temporal dynamics of postures over time is crucial for sequence-based action recognition. Human actions can be represented by the corresponding motions of articulated skeleton. Most of the existing approaches for skeleton based action recognition model the spatial-temporal evolution of actions based on hand-crafted features. As a kind of hierarchically adaptive filter banks, Convolutional Neural Network (CNN) performs well in representation learning. In this paper, we propose an end-to-end hierarchical architecture for skeleton based action recognition with CNN. Firstly, we represent a skeleton sequence as a matrix by concatenating the joint coordinates in each instant and arranging those vector representations in a chronological order. Then the matrix is quantified into an image and normalized to handle the variable-length problem. The final image is fed into a CNN model for feature extraction and recognition. For the specific structure of such images, the simple max-pooling plays an important role on spatial feature selection as well as temporal frequency adjustment, which can obtain more discriminative joint information for different actions and meanwhile address the variable-frequency problem. Experimental results demonstrate that our method achieves the state-of-art performance with high computational efficiency, especially surpassing the existing result by more than 15 percentage on the challenging ChaLearn gesture recognition dataset. © 2015 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Theory of ϕ-Jensen variance and its applications in higher education

引用

Journal of Inequalities and Applications 2015年第1期2015卷 1-40页

作者： Wen, JiaJin Huang, Yi Cheng, Sui Sun Institute of Mathematical Inequalities and Applications College of Mathematics and Computer Science Chengdu University Chengdu 610106 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Higher Education Institutions of Sichuan Province College of Mathematics and Computer Science Chengdu University Chengdu 610106 China Department of Mathematics Tsing Hua University Hsinchu 30043 Taiwan

This paper introduces the theory of ϕ-Jensen variance. Our main motivation is to extend the connotation of the analysis of variance and facilitate its applications in probability, statistics and higher education. To this end, we first introduce the relevant concepts and properties of the interval function. Next, we study several characteristics of the log-concave function and prove an interesting quasi-log concavity conjecture. Next, we introduce the theory of ϕ-Jensen variance and study the monotonicity of the interval function JVar_ϕ φ(X_[a,b]) by means of the log concavity. Finally, we demonstrate the applications of our results in higher education, show that the hierarchical teaching model is ‘normally’ better than the traditional teaching model under the appropriate hypotheses, and study the monotonicity of the interval function Var A (X_[a,b]). © 2015, Wen et al.

关键词： hierarchical teaching model interval function k-normal distribution truncated random variable ϕ-Jensen variance

来源：评论

学校读者我要写书评

暂无评论

SHREC'15 track: 3D object retrieval with multimodal views 8

SHREC'15 track: 3D object retrieval with multimodal views

引用

8th Eurographics Workshop on 3D Object Retrieval, 3DOR 2015

作者： Gao, Yue Liu, Anan Nie, Weizhi Su, Yuting Dai, Qionghai Chen, Fuhai Chen, Yingying Cheng, Yanhua Dong, Shuilong Duan, Xingyue Fu, Jianlong Gao, Zan Guo, Haiyun Guo, Xin Huang, Kaiqi Ji, Rongrong Jiang, Yingfeng Li, Haisheng Lu, Hanqing Song, Jianming Sun, Jing Tan, Tieniu Wang, Jinqiao Yin, Huanpu Zhang, Chaoli Zhang, Guotai Zhang, Yan Zhao, Chaoyang Zhao, Xin Zhu, Guibo School of Medicine University of North Carolina Chapel Hill United States School of Electronic Information Engineering Tianjin University China Department of Automation Tsinghua University China School of Information Science and Engineering Xiamen University China Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China College of Computing and Digital Media DePaul University United States School of Computing Tianjin University of Technology China School of Computer Science and Information Engineering Beijing Technology and Business University China

ISBN: (纸本)9783905674781

This paper reports the results of the SHREC'15 track: 3D Object Retrieval with Multimodal Views, which goal is to evaluate the performance of retrieval algorithms when multimodal views are employed for 3D object representation. In this task, a collection of 505 objects is generated and both the color images and the depth images are provided for each object. 311 objects are selected as the queries and average retrieval performance is measured. The track attracted six participants and the submission of 26 runs, to two tasks. The evaluation results show a promising scenario about multimodal view-based 3D retrieval methods, and reveal interesting insights in dealing with multimodal data. © The Eurographics Association 2015.

关键词： information retrieval

来源：评论

学校读者我要写书评

暂无评论

An effective watermarking method against valumetric distortions

An effective watermarking method against valumetric distorti...

引用

作者： Wang, Zairan Dong, Jing Wang, Wei Tan, Tieniu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation China College of Engineering and Information Technology University of Chinese Academy of Sciences China

ISBN: (纸本)9781479957514

Most of the quantization based watermarking algorithms are very sensitive to valumetric distortions, while these distortions are regarded as common processing in audio/video analysis. In recent years, watermarking methods which can resist this kind of distortions have attracted a lot of interests. But still many proposed methods can only deal with one certain kind of valumetric distortion as amplitude scaling, and fail in other kinds of valumetric distortions like constant change attack or gamma correction. In this paper, we propose a very simple method to tackle all the three kinds of valumetric distortions. A constant change invariant domain is first constructed by spread transform, in which the watermark is embedded using a certain amplitude scaling invariant based watermarking scheme. Several typical watermarking methods and attacks have been implemented in our experiments to demonstrate the effectiveness of the proposed method. © 2014 IEEE.

关键词： amplitude scaling QIM valumetric distortions watermarking

来源：评论

学校读者我要写书评

暂无评论

Improved robust watermarking based on rational dither modulation

Communications in Computer and Information Science

引用

Communications in Computer and information Science 2014年 437卷 305-314页

作者： Wang, Zairan Dong, Jing Wang, Wei Tan, Tieniu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China College of Engineering and Information Technology University of Chinese Academy of Sciences China

ISBN: (纸本)9783662454978

Rational dither modulation (RDM) watermarking was presented to resist amplitude scaling attack. This property is achieved by quantizing the ratio of consecutive samples instead of samples themselves. In this paper, we improve the performance of basic RDM watermarking to resist more types of watermarking attacks. We improve the robustness of our modified RDM watermarking by the following three aspects: 1) The quantization step size is increased by modifying two coefficients instead of only one coefficient in the basic RDM method, 2) Several modification rules are defined to reduce embedding distortion, and 3) The coefficients with larger magnitudes in the lowest sub-band in DWT domain are selected to embed watermark. A variety of attacks are implemented to evaluate the performance of our method. Experimental results demonstrate that our method outperforms the basic RDM method and two state-of-the-art watermarking methods over a wide range of attacks and it also has good imperceptibility. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Modulation

来源：评论

学校读者我要写书评

暂无评论

Erratum to: A Robust Tracking System for Low Frame Rate Video

引用

International Journal of Computer Vision 2015年第3期115卷 305-305页

作者： Xiaoqin Zhang Weiming Hu Nianhua Xie Hujun Bao Stephen Maybank Institute of Intelligent System and Decision Wenzhou University Zhejiang China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Computer Science Zhejiang University Zhejiang China Department of Computer Science and Information Systems Birkbeck College London UK

来源：评论

学校读者我要写书评

暂无评论

Adaptive iteration filter for suppression of impulse noise in color images

Adaptive iteration filter for suppression of impulse noise i...

引用

2012 International Conference on Mechatronic Systems and Automation Systems, MSAS 2012

作者： Wang, Gaihua Li, Dehua Zhao, Tongzhou Institute for pattern recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China The College of Physics and Information Science of Xinjiang Normal University Urumqi 830053 China Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan 430073 China

ISBN: (纸本)9783037854921

New impulse detection and filtering algorithm is proposed in color images. Based on fast peer group filter, the proposed filtering algorithm uses different iteration times to complete filter according to different impulse noise density. The extensive experimental results show that the proposed scheme provides better performance than many of the existing vector filters. Meanwhile, the proposed approach is simple and practical for real-time application. © (2012) Trans Tech Publications, Switzerland.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Iterative data adaptive anisotropic image filtering

Iterative data adaptive anisotropic image filtering

引用

2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012

作者： Yang, Chang-Cai Zheng, Xin-Yi Tian, Jin-Wen Shang, Ke Tian, Xin Hao, Wei Institute for Pattern Recognition and Artificial Intelligence Science and Technology on Multi-Spectral Information Processing Laboratory Huazhong University of Science and Technology Wuhan 430074 China Electrical Engineering and Renewable Energy School China Three Gorges University Yichang 443002 China Institute of Intelligent Vision and Image Information College of Computer and Information Technology China Three Gorges University Yichang 443002 China

ISBN: (纸本)9781467314855

This paper presents a novel data-adaptive anisotropic filtering technique built on top of an iterative scheme. This new technique can preserve the original significant structures while suppressing noises to the largest extent. To achieve this goal, dominant orientation information of all gradients is used to control the local kernel adaptively. This results in elongated and elliptical contours spread along the directions of the local edge structure. With these locally adapted kernels, the smoothing is mostly effective along the edges, rather than across them. Therefore details in the original input can be preserved. The performance of the proposed data-adaptive anisotropic filter together with its iterative scheme are compared with the conventional Gaussian filter, anisotropic diffusion filter, the structure-adaptive anisotropic filter, and the iterative kernel regression scheme. The experimental results on both simulated Gaussian and Poission noisy images indicate that the proposed method performs the best, and the iterative scheme can significantly improve the performance of the noise suppressing while delivering high computation efficiency. © 2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Approximate computation of Madaline sensitivity based on discrete stochastic technique

引用

Science China(information Sciences) 2010年第12期53卷 2399-2414页

作者： ZHONG ShuiMing , ZENG XiaoQin, LIU HuiYi & XU Yan institute of pattern recognition and intelligent System, college of Computer and information Engineering, Hohai University, Nanjing 210098, China 1. Institute of Pattern Recognition and Intelligent System College of Computer and Information Engineering Hohai University Nanjing 210098 China

The computation of the sensitivity of a Madaline’s output to its parameter perturbation is system- atically discussed. Firstly, according to the discrete feature of Adalines, a method based on discrete stochastic technique is proposed, which derives some analytical formulas for the computation of Adalines’ sensitivity. The method can theoretically solve some problems that are unsolvable by the existing methods based on continu- ous stochastic techniques, release some unpractical constraints, and make it available to theoretically analyze the approximation error of Adalines’ sensitivity. Secondly, on the basis of the sensitivity of Adalines and the structural characteristics of Madalines, a new selection strategy depending on a type of dedication degree for computing Madalines’ sensitivity is proposed, which is superior to current popular way of simply averaging in both precision and complexity. The proposed formulas and algorithm have the advantages of simplicity, low computational complexity, small approximation error, and high generality, as have been verified by a great amount of experimental simulations.

关键词： Adaline Madaline feedforward networks sensitivity parameter perturbation stochastic discrete technique

来源：评论

学校读者我要写书评

暂无评论

Learning human actions with an adaptive codebook

Learning human actions with an adaptive codebook

引用

2010 16th International Conference on Virtual Systems and Multimedia, VSMM 2010

作者： Kong, Yu Zhang, Xiaoqin Hu, Weiming Jia, Yunde Beijing Laboratory of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Beijing 100081 China College of Mathematics and Information Science Wenzhou University Zhejiang China National Laboratory of Pattern Recognition Institute of Automation China

ISBN: (纸本)9781424490264

Learning a compact and yet discriminative codebook for classifying human actions is a challenging problem. One difficulty lies in that the learning procedure is split into two independent phases (dimension reduction and clustering) and thus results in the loss of discriminative information which clustering requires. Besides, traditional used principal component analysis is not optimized for class separability and may not help to improve data separation. In this paper, we propose a novel optimization framework which unifies dimension reduction and clustering. In contrast to previous methods, our method enables to dynamically select indispensable and crucial dimensions for building a discriminative codebook. We add metric learning before clustering to provide the clustering method with an optimized distance metric. Experimental results show that our approach constructs a highly discriminative codebook and achieves comparable results to other state-of-the-art approaches. ©2010 IEEE.

关键词： Principal component analysis

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：