检索结果-内蒙古大学图书馆

No reference video quality assessment based on 3D convolutional neural network

Ruan Jian Xue Bao/Journal of Software 2016年 27卷 103-112页

作者： Wang, Chun-Feng Su, Li Zhang, Wei-Gang Huang, Qing-Ming Key Laboratory on Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology The Chinese Academy of Sciences Beijing100190 China Weihai264209 China

No reference video quality assessment (NR-VQA) measures distorted videos quantitatively without the reference of original high quality videos. Conventional NR-VQA methods are generally designed for specific types of distortions, or not consistent with human's perception. This paper innovatively introduces 3D deep convolutional neural network (3D-CNN) into VQA and proposes a 3D-CNN based NR-VQA method, which is universal for non-specific types of distortions. First, the proposed method utilizes 3D patches to learn spatio-temporal features that represent video content effectively. Second, the original 3D-CNN model is modified which is used to classify videos to make it adapt to VQA task. Experiments demonstrate that the proposed method is highly consistent with human's perception across numerous distortions and metrics. Compared with other state-of-the-art no-reference VQA methods, the proposed method runs much faster while keeping the similar performance. As a no-reference VQA method, it is even comparable with many of the state-of-the-art full-reference VQA methods, which provides the proposed method with better application prospects. © Copyright 2016, institute of Software, the Chinese Academy of Sciences. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

SEMANTICS CONSTRAINED DICTIONARY LEARNING FOR SIGNER-INDEPENDENT SIGN LANGUAGE RECOGNITION

SEMANTICS CONSTRAINED DICTIONARY LEARNING FOR SIGNER-INDEPEN...

引用

IEEE International Conference on Image processing

作者： Fang Yin Xiujuan Chai Yu Zhou Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Institute of Information Engineering Chinese Academy of Sciences

ISBN: (纸本)9781479983407

In this paper, a sparse coding based framework is proposed for sign language recognition (SLR), especially for the signer-independent case. To deal with the inter-signer variation, a dictionary capturing the common features among different signers is learnt by considering the semantic constraint. Thus for a given sign from an unknown signer, the sparse representation, which maintains more information of this specific sign class while neglecting the identity information as much as possible, can be generated. In our implementation, each sign is partitioned into a fixed number of fragments and the features fusing hand shape and moving trajectory are extracted from the fragments. The dictionary learnt from the training fragments can be taken as the basic subunits of signs and each fragment of sign video can be coded by these basis vectors. Finally, the recognition result is achieved through SVM with the concatenated sparse coding features of the fragments. The experiments and comparisons show that our method is more effective for the signer-independent recognition problem than other baseline methods. At the same time, it also performs well for the signer-dependent case.

关键词： Sparse coding Dictionary learning Sign language recognition Signer-independent Semantic constraint

来源：评论

学校读者我要写书评

暂无评论

Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with Image Sets

Discriminant Analysis on Riemannian Manifold of Gaussian Dis...

引用

IEEE Conference on Computer Vision and Pattern Recognition

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

ISBN: (纸本)9781467369657

This paper presents a method named Discriminant Analysis on Riemannian manifold of Gaussian distributions (DARG) to solve the problem of face recognition with image sets. Our goal is to capture the underlying data distribution in each set and thus facilitate more robust classification. To this end, we represent image set as Gaussian Mixture Model (GMM) comprising a number of Gaussian components with prior probabilities and seek to discriminate Gaussian components from different classes. In the light of information geometry, the Gaussians lie on a specific Riemannian manifold. To encode such Riemannian geometry properly, we investigate several distances between Gaussians and further derive a series of provably positive definite probabilistic kernels. Through these kernels, a weighted Kernel Discriminant Analysis is finally devised which treats the Gaussians in GMMs as samples and their prior probabilities as sample weights. The proposed method is evaluated by face identification and verification tasks on four most challenging and largest databases, YouTube Celebrities, COX, YouTube Face DB and Point-and-Shoot Challenge, to demonstrate its superiority over the state-of-the-art.

关键词： Kernel Manifolds Gaussian distribution Face recognition Covariance matrices Data models Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Social sensing enhanced time estimation for bus service

Social sensing enhanced time estimation for bus service

引用

作者： Liu, Jin Li, Juan Cui, Xiaohui Niu, Xiaoguang Sun, Xiaoping Zhou, Jing State Key Lab. of Software Engineering Computer School Wuhan University Wuhan China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China International School of Software Wuhan University Wuhan China Computer School Wuhan University Wuhan China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science Communication University of China China

The precise prediction of bus routes or the arrival time of buses for a traveler can enhance the quality of bus service. However, many social factors influence people's preferences for taking buses. These social factors may include heavy traffic cost, traffic congestion, poor air quality and so forth. Existing prediction techniques rarely consider social sensing when predicting the bus arrival time. Accordingly, this paper proposes a social sensing enhanced service for predicting bus routes, which integrates sensing ability and social networks to understand and measure the influence between social events and vehicle velocity. We focus on the analysis of two different attributions: PT service quality attributions PEAs and road condition attributions PRCAs. Both of them synthesize the social sensing in their evaluation of bus routes. PEA represents individual preferences and PRCA represents physical factors that significantly influence vehicle velocity. Bus relevant social events were further categorized into PEA events or PRCA events. PEAs of buses were scored according to the tendency of bus conditions reflected in social events. Furthermore, an artificial neural network prediction model is established to estimate the bus travel time. © 2015 John Wiley & Sons, Ltd.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Adaptive sparse recovery based on difference algorithm

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2015年第6期27卷 1047-1052页

作者： Zhang, Fengzhen Zhao, Ruizhen Cen, Yigang Hu, Shaohai Zhang, Yongdong Institute of Information Science Beijing Jiaotong University Beijing100044 China Key Laboratory of Advanced Information Science and Network Technology of Beijing Beijing100044 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

To improve the disadvantages that iterative reconstruction algorithms of compressed sensing need priori knowledge of the sparsity of original signal or iterative threshold, an adaptive sparse recovery based on difference algorithm is proposed. When the sparsity of original signal is unknown, the proposed algorithm takes advantage of unbalance of correlation coefficient between the measurement matrix and residual. With those properties, the proposed algorithm can select the support set of the original signal, and approach the sparsity of the original signal. Simulation results show that the proposed algorithm obtains better recovery results under the same conditions. Especially in the lower sampling rate, the advantage is more obvious. ©, 2015, institute of computing technology. All right reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Object detection capability evaluation for SAR image

Object detection capability evaluation for SAR image

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Zheyuan Wang Yuanxiang Li Fangjie Yu Wenxian Yu Zhuhui Jiang Yongke Ding Shanghai Key Lab. of Intelligent Sensing & Recognition Shanghai Jiao Tong University Shanghai China Laboratory for Regional Oceanography and Numerical Modeling Qingdao National Laboratory for Marine Science and Technology Qingdao China College of Information Science and Engineering Ocean University of China Qingdao China Beijing Institute of Applied Meteorology Beijing China

The existing SAR image quality assessment method could not be effectively used for assessing the performance of object detection. Thus, it is difficult to select SAR images and corresponding detection algorithms for SAR object detection. By analyzing the relationship between object detection results and basic image quality indicators, this paper studies the image quality assessment for image object detection. Based on the concept of “application suitability”, basic quality indicators including radiometric resolution, spatial resolution, PSLR and ISLR are integrated into a single indicator called Detection Index, which is able to comprehensively evaluate the degree to which SAR image is suitable for object detection tasks. Experimental results on aircraft detection with single scene show the effectiveness of the proposed model for SAR image capability evaluation in object detection applications.

关键词： Synthetic aperture radar Object detection Spatial resolution Image quality Indexes Detection algorithms Aircraft

来源：评论

学校读者我要写书评

暂无评论

Noisy image super-resolution reconstruction based on sparse representation

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2015年第4期52卷 943-951页

作者： Dou, Nuo Zhao, Ruizhen Cen, Yigang Hu, Shaohai Zhang, Yongdong Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing Jiaotong University Beijing100044 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Denoising and super-resolution reconstruction are performed separately in traditional methods for noisy image super-resolution reconstruction, while in the noisy image super-resolution reconstruction method based on sparse representation and dictionary learning the two processes are compounded together. Since an image patch can be well represented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary, two dictionaries are trained respectively from noisy low-and clean high-resolution image patches by enforcing the similarity of two sparse representations with respect to their own dictionary. Given a noisy low-resolution image, sparse representations of low-resolution patches via trained low-dictionary are computed, then the high-resolution image can be reconstructed from high-resolution patches with the help of the related low-resolution sparse representations and trained high-dictionary, after global optimization a clean high-resolution is obtained to accomplish the goal of image super-resolution and denosing simultaneously. The experiments show that zooming low-resolution image to a middle-resolution using locally adaptive zooming algorithm for extracting features can get a better reconstructed image than bicubic interpolation algorithm. By setting the parameter λ, we can obtain the best performance both in super-resolution and denoising with absolute advantages in image quality and visual effect, which demonstrates the validity and robustness of our algorithm. ©, 2015, Science Press. All right reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Sentiment extraction by leveraging aspect-opinion association structure 15

Sentiment extraction by leveraging aspect-opinion associatio...

引用

24th ACM International Conference on information and Knowledge Management, CIKM 2015

作者： Zhao, Li Huang, Minlie Sun, Jiashen Luo, Hengliang Yang, Xiankai Zhu, Xiaoyan State Key Lab. of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University Beijing100084 China Samsung R and D Institute China Beijing China

ISBN: (纸本)9781450337946

Sentiment extraction aims to extract and group aspect and opinion words from online reviews. Previous works usually extract aspect and opinion words by leveraging association between a single pair of aspect and opinion word[5] [14] [9] [4][11], but the structure of aspect and opinion word clusters has not been fully exploited. In this paper, we investigate the aspect-opinion association structure, and propose a "first clustering, then extracting" unsupervised model to leverage properties of the structure for sentiment extraction. For the clustering purpose, we formalise a novel concept syntactic distribution consistency as soft constraint in the framework of posterior regularization;for the extraction purpose, we extract aspect and opinion words based on cluster-cluster association. In comparison to traditional word-word association, we show that cluster-cluster association is a much stronger signal to distinguish aspect (opinion) words from non-aspect (non-opinion) words. Extensive experiments demonstrate the effectiveness of the proposed approach and the advantages against state-of-the-art baselines. © 2015 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

The B4-Modalized Propositional Logic

The B4-Modalized Propositional Logic

引用

2015 International Conference on Mechanical,Electronic and information technology Engineering

作者： Cao Cungen Sui Yuefei Deng Shaobo Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Science University of Chinese Academy of Sciences

A modalized propositional Belnap-Dunn logic will be proposed in this paper which there are four modalities [t],[T],[⊥],[f]to represent the four values t,T,⊥,f, respectively, and a Gentzentyped deduction system will ... 详细信息

关键词： The Belnap-Dunn logic,modality,the soundness,the completeness

来源：评论

学校读者我要写书评

暂无评论

AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation

AgeNet: Deeply Learned Regressor and Classifier for Robust A...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Xin Liu Shaoxin Li Meina Kan Jie Zhang Shuzhe Wu Wenxian Liu Hu Han Shiguang Shan Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing China Tencent BestImage Team Shanghai China

Apparent age estimation from face image has attracted more and more attentions as it is favorable in some real-world applications. In this work, we propose an end-to-end learning approach for robust apparent age estimation, named by us AgeNet. Specifically, we address the apparent age estimation problem by fusing two kinds of models, i.e., real-value based regression models and Gaussian lab.l distribution based classification models. For both kind of models, large-scale deep convolutional neural network is adopted to learn informative age representations. Another key feature of the proposed AgeNet is that, to avoid the problem of over-fitting on small apparent age training set, we exploit a general-to-specific transfer learning scheme. Technically, the AgeNet is first pre-trained on a large-scale web-collected face dataset with identity lab.l, and then it is fine-tuned on a large-scale real age dataset with noisy age lab.l. Finally, it is fine-tuned on a small training set with apparent age lab.l. The experimental results on the ChaLearn 2015 Apparent Age Competition demonstrate that our AgeNet achieves the state-of-the-art performance in apparent age estimation.

关键词： Estimation Encoding Robustness Neural networks Face Aging Standards

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：