检索结果-内蒙古大学图书馆

8th IFIP International Conference on intelligent information processing, IIP 2014

作者： Li, Xiangyang Jiang, Shuqiang Song, Xinhang Herranz, Luis Shi, Zhiping Capital Normal University College of Information Engineering Beijing China Key Lab of Intelligent Information Processing Institute of Computing Tech Beijing China

ISBN: (纸本)9783662449790

Extracting good representations from images is essential for many computer vision tasks. While progress in deep learning shows the importance of learning hierarchical features, it is also important to learn features through multiple paths. This paper presents Multipath Convolutional-Recursive Neural Networks(M-CRNNs), a novel scheme which aims to learn image features from multiple paths using models based on combination of convolutional and recursive neural networks (CNNs and RNNs). CNNs learn low-level features, and RNNs, whose inputs are the outputs of the CNNs, learn the efficient high-level features. The final features of an image are the combination of the features from all the paths. The result shows that the features learned from M-CRNNs are a highly discriminative image representation that increases the precision in object recognition. © IFIP International Federation for information processing 2014.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Extreme Learning Machine for Unsupervised Representation Learning

Hierarchical Extreme Learning Machine for Unsupervised Repre...

引用

International Joint Conference on Neural Networks

作者： Wentao Zhu Jun Miao Laiyun Qing Guang-Bin Huang Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100049 China School of Electrical & Electronic Engineering Nanyang Technological University Nanyang Avenue Singapore 639798

ISBN: (纸本)9781479919611

Learning representations from massive unlab.led data is a hot topic for high-level tasks in many applications. The recent great improvements on benchmark data sets, which are achieved by increasingly complex unsupervised learning methods and deep learning models with lots of parameters, usually require many tedious tricks and much expertise to tune. However, filters learned by these complex architectures are quite similar to standard hand-crafted features visually, and training the deep models costs quite long time to fine-tune their weights. In this paper, Extreme Learning Machine-Autoencoder (ELM-AE) is employed as the learning unit to learn local receptive fields at each layer, and the lower layer responses are transferred to the last layer (trans-layer) to form a more complete representation to retain more information. In addition, some beneficial methods in deep learning architectures such as local contrast normalization and whitening are added to the proposed hierarchical Extreme Learning Machine networks to further boost the performance. The obtained trans-layer representations are followed by block histograms with binary hashing to learn translation and rotation invariant representations, which are utilized to do high-level tasks such as recognition and detection. Compared to traditional deep learning methods, the proposed trans-layer representation method with ELM-AE based learning of local receptive filters has much faster learning speed and is validated in several typical experiments, such as digit recognition on MNIST and MNIST variations, object recognition on Caltech 101. State-of-the-art performances are achieved on both Caltech 101 15 samples per class task and 4 of 6 MNIST variations data sets, and highly impressive results are obtained on MNIST data set and other tasks.

关键词： Hierarchical Extreme Learning Machine Unsupervised Representation Learning deep learning models Learning machines Dataset representation method Recognition (Psychology) Receptive field Learning representations Religious Missions Hierarchical

来源：评论

学校读者我要写书评

暂无评论

Artifact reduction of compressed video via three-dimensional adaptive estimation of transform coefficients

Artifact reduction of compressed video via three-dimensional...

引用

作者： Zhang, Xinfeng Xiong, Ruiqin Ma, Siwei Gao, Wen Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Institute of Digital Media Peking University Beijing100871 China

ISBN: (纸本)9781479957514

Block transform compressed videos usually suffer from annoying artifacts at low bit rates, caused by the coarse quantization of transform coefficients. The inter prediction utilized in video coding also induces block boundary artifacts when the neighboring blocks using different motion vectors from previous decoded frames. In this paper, a three-dimensional adaptive estimation method for video transform coefficients is proposed to reduce the artifact in compressed video. In the proposed method, transform coefficients of each block are estimated by adaptively fusing three prediction sources based on their reliabilities. One prediction source is the transform coefficients directly acquired from the decoded video, whose reliability is determined by the distribution of the quantization noise. The other prediction source is derived by a temporal autoregressive model of transform-blocks along motion trajectory among neighboring reference frames. Its reliability is estimated from prediction variance of local blocks. The last prediction source is derived from the nonlocal transform-blocks, whose reliability is estimated based on the distribution of the nonlocal coefficients and their similarity with the estimated block. Experimental results for compressed video sequences by HEVC show that, the proposed method can reduce the compression artifacts and improve both the objective and subjective quality. © 2014 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A multi-channel SSVEP-based brain-computer interface using a canonical correlation analysis in the frequency domain

Advances in Intelligent Systems and Computing

引用

Advances in intelligent Systems and computing 2014年 215卷 603-616页

作者： Chen, Guang Song, Dandan Liao, Lejian Beijing Eng. Research Center of High Volume Language Inf. Processing and Cloud Computing App. Beijing Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Beijing China

Brain-computer interface (BCI) is a new way for man-machine interaction with wide applications, in which steady-state visual evoked potentials (SSVEP) is a promising option. However, many characteristics of SSVEP show great user variation. So parameter optimization and channel selection for each subject were applied to improve the performance of BCI. These optimizations limit the practical applicability of the SSVEP-based BCI. The use of a canonical correlation analysis (CCA) method for multi-channel SSVEP in the time domain detection showed highly increased detection accuracy, but it is sensitive to the noise when the stimulate frequency is low. In this paper, a method of CCA in the frequency domain is presented for classifying multi-channel SSVEPs. First overlapping average is conducted on the original training signals. Then fast Fourier transform (FFT) is used to transform the signals from time domain to frequency domain to produce the reference data. Finally, according to the correlation coefficients of the new data and the references in the frequency domain, the SSVEP is classified. The experimental results show the enhanced accuracy of our method when applied to low stimulate frequencies. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Quotient space granularity selection based Affinity Propagation clustering algorithm

引用

Journal of Computational information Systems 2014年第6期10卷 2425-2433页

作者： Ding, Shifei Li, Hui School of Computer Science and Technology China University of Mining and Technology Xuzhou 221116 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Jiangsu Normal University Xuzhou 221116 China

The aim of this paper is to develop an improved AP clustering algorithm based on the quotient space granularity selection. Firstly, we give the characteristics of the quotient space granularity and Affinity Propagation (AP) clustering. Secondly, we analyze the interlinking of clustering and the quotient space granularity. And then we introduce the quotient space concept to the AP clustering analysis, which can find an optimal granularity from all possible granularities. Simulation results show that our proposed method here, quotient space granularity selection based AP clustering algorithm, is effective and feasible and has a better performance. Copyright © 2014 Binary information Press.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Augment dependency-to-string translation with fixed and floating structures 25

Augment dependency-to-string translation with fixed and floa...

引用

25th International Conference on Computational Linguistics, COLING 2014

作者： Xie, Jun Xu, Jinan Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer and Information Technology Beijing Jiaotong University China School of Computing Dublin City University Ireland

ISBN: (纸本)9781941643266

In this paper, we propose an augmented dependency-to-string model to combine the merits of both the head-dependents relations at handling long distance reordering and the fixed and floating structures at handling local reordering. For this purpose, we first compactly represent both the head-dependent relation and the fixed and floating structures into translation rules;second, in decoding we build "on-the-fly" new translation rules from the compact translation rules that can incorporate non-syntactic phrases into translations, thus alleviate the non-syntactic phrase coverage problem of dependency-to-string translation (Xie et al., 2011). Large-scale experiments on Chinese-to-English translation show that our augmented dependency-to-string model gains significant improvement of averaged +0.85 BLEU scores on three test sets over the dependencyto- string model.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Visual saliency based bag of phrases for image retrival 13

Visual saliency based bag of phrases for image retrival

引用

13th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry, VRCAI 2014

作者： Duan, Lijuan Ma, Wei Miao, Jun Zhang, Xuan College of Computer Science Beijing University of Technology China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing100190 China

ISBN: (纸本)9781450332545

This paper presents a saliency based bag-of-phrases (Saliency-BoP for short) method for image retrieval. It combines saliency detection with visual phrase construction to extract bag-of-phrase features. To achieve this, the method first detects salient regions in images. Then, it constructs visual phrases using the word pairs which are from the same salient regions. Finally, it extracts the bag of visual phrases from the first K salient regions to describe images. Experimental results on Corel 1K and Microsoft Research Cambridge image database demonstrated that the Saliency-BoP method outperforms related methods such as Bag-of-Words (BoW) or Saliency-BoW. Copyright © ACM.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Signal processing for the 5G Revolution

引用

IEEE SIGNAL processing MAGAZINE 2014年第6期31卷 12-13页

作者： Heath, Robert W., Jr. Leus, Geert Quek, Tony Q. S. Talwar, Shilpa Zhou, Peiying Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Department of Computer Systems University of São Paulo - USP São Carlos Brazil IRISA Research Institute University of South Brittany - IRISA/UBS Vannes France

The articles in this special section provide an overview of recent advances in signal processing for communication with an emphasis on signal processing techniques that will be relevant for 5G cellular systems. It covers a wide range of topics including modulation, beamforming, cross-layer optimization based on different performance metrics, location-aware communication, cloud computing, and cloud radio access networks. The articles provide a diverse perspective on the potential challenges in 5G cellular systems.

关键词： Special issues and sections 5G mobile communication Next generation networking Wireless communication Cellular networks Wireless cellular networks

来源：评论

学校读者我要写书评

暂无评论

Transformation and decomposition for efficiently implementing and improving dependency-to-string model in moses 8

Transformation and decomposition for efficiently implementin...

引用

8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2014

作者： Li, Liangyou Xie, Jun Way, Andy Liu, Qun CNGL Centre for Global Intelligent Content School of Computing Dublin City University Dublin 9 Ireland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781937284961

Dependency structure provides grammatical relations between words, which have shown to be effective in Statistical Machine Translation (SMT). In this paper, we present an open source module in Moses which implements a dependency-to-string model. We propose a method to transform the input dependency tree into a corresponding constituent tree for reusing the tree-based decoder in Moses. In our experiments, this method achieves comparable results with the standard model. Furthermore, we enrich this model via the decomposition of dependency structure, including extracting rules from the substructures of the dependency tree during training and creating a pseudo-forest instead of the tree per se as the input during decoding. Large-scale experiments on Chinese–English and German–English tasks show that the decomposition approach improves the baseline dependency-to-string model significantly. Our system achieves comparable results with the state-of-the-art hierarchical phrase-based model (HPB). Finally, when resorting to phrasal rules, the dependency-to-string model performs significantly better than Moses HPB. © 2014 Association for Computational Linguistics

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

The DCU-ICTCAS MT system at WMT 2014 on German-english translation task 9

The DCU-ICTCAS MT system at WMT 2014 on German-english trans...

引用

9th Workshop on Statistical Machine Translation, WMT 2014 at the 52nd Conference of the Associationfor Computational Linguistics, ACL 2014

作者： Li, Liangyou Wu, Xiaofeng Cortes Váillo, Santiago Xie, Jun Way, Andy Liu, Qun CNGL Centre for Global Intelligent Content School of Computing Dublin City University Dublin 9 Ireland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781941643174

This paper describes the DCU submission to WMT 2014 on German-English translation task. Our system uses phrasebased translation model with several popular techniques, including Lexicalized Reordering Model, Operation Sequence Model and Language Model interpolation. Our final submission is the result of system combination on several systems which have different pre-processing and alignments. © Proceedings of the Annual Meeting of the Association for Computational Linguistics 2014.

关键词： Translation (languages)

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：