检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,060 篇 期刊文献
1,025 篇 会议
16 篇 学位论文

馆藏范围

2,101 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,919 篇 工学
- 1,155 篇 计算机科学与技术...
- 920 篇 电气工程
- 219 篇 软件工程
- 212 篇 信息与通信工程
- 157 篇 控制科学与工程
- 131 篇 机械工程
- 86 篇 仪器科学与技术
- 85 篇 生物医学工程（可授...
- 83 篇 电子科学与技术（可...
- 71 篇 测绘科学与技术
- 22 篇 材料科学与工程（可...
- 18 篇 环境科学与工程（可...
- 13 篇 光学工程
- 10 篇 网络空间安全
- 9 篇 土木工程
- 7 篇 航空宇航科学与技...
451 篇 理学
- 216 篇 物理学
- 92 篇 生物学
- 52 篇 数学
- 48 篇 地球物理学
- 35 篇 系统科学
- 11 篇 化学
- 7 篇 统计学（可授理学、...
- 6 篇 地理学
412 篇 医学
- 289 篇 临床医学
- 123 篇 基础医学(可授医学...
- 57 篇 特种医学
86 篇 管理学
- 83 篇 管理科学与工程(可...
28 篇 农学
- 7 篇 农业资源与环境
12 篇 教育学
- 10 篇 心理学(可授教育学...
9 篇 文学
5 篇 军事学
3 篇 法学
2 篇 哲学
2 篇 经济学
1 篇 艺术学

主题

2,101 篇 sparse coding
381 篇 dictionary learn...
85 篇 sparse represent...
83 篇 image classifica...
70 篇 feature extracti...
66 篇 dictionaries as ...
54 篇 classification
48 篇 images
47 篇 machine learning
43 篇 super-resolution
43 篇 image denoising
38 篇 face recognition
38 篇 encoding
37 篇 dictionaries
36 篇 deep learning
36 篇 denoising
34 篇 compressed sensi...
34 篇 image representa...
31 篇 transfer learnin...
31 篇 image coding

机构

17 篇 nanjing univ sci...
12 篇 northwestern pol...
10 篇 zhejiang univ co...
10 篇 univ georgia dep...
10 篇 harbin inst tech...
9 篇 los alamos natl ...
9 篇 natl univ singap...
9 篇 univ georgia bio...
8 篇 chinese acad sci...
8 篇 zhejiang univ co...
8 篇 chinese acad sci...
8 篇 univ michigan de...
7 篇 sichuan univ col...
7 篇 univ chinese aca...
7 篇 georgia inst tec...
7 篇 shanghai jiao to...
6 篇 univ chinese aca...
6 篇 suzhou vocat uni...
6 篇 astar inst infoc...
6 篇 univ minnesota d...

作者

15 篇 li xiang
14 篇 liu tianming
11 篇 qian yuntao
11 篇 elad michael
10 篇 lv jinglei
10 篇 yang jianchao
10 篇 kenyon garrett t...
10 篇 guo lei
9 篇 zhang lei
9 篇 han junwei
9 篇 zhou jun
8 篇 quan yuhui
8 篇 ding shuxue
8 篇 yang yi-hsuan
8 篇 ye jieping
8 篇 zhang jie
8 篇 li xuelong
8 篇 barth erhardt
8 篇 sapiro guillermo
8 篇 zhu xiaofeng

语言

2,051 篇 英文
38 篇 其他
8 篇 中文
2 篇 土耳其文
1 篇 法文
1 篇 俄文

检索条件"主题词=sparse coding"

共 2101 条记录，以下是2081-2090 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach 13

What Are the Invariant Occlusive Components of Image Patches...

引用

Annual Conference on Neural Information Processing Systems

作者： Zhenwen Dai Georgios Exarchakis Joerg Luecke University of Sheffield UK and FIAS Goethe-University Frankfurt Germany Redwood Center for Theoretical Neuroscience The University of California Berkeley US Cluster of Excellence Hearing4all University of Oldenburg Germany and BCCN Berlin Technical University Berlin Germany

ISBN: (纸本)9781632660244

We study optimal image encoding based on a generative approach with non-linear feature combinations and explicit position encoding. By far most approaches to unsupervised learning of visual features, such as sparse coding or ICA, account for translations by representing the same features at different positions. Some earlier models used a separate encoding of features and their positions to facilitate invariant data encoding and recognition. All probabilistic generative models with explicit position encoding have so far assumed a linear superposition of components to encode image patches. Here, we for the first time apply a model with non-linear feature superposition and explicit position encoding for patches. By avoiding linear superpositions, the studied model represents a closer match to component occlusions which are ubiquitous in natural images. In order to account for occlusions, the non-linear model encodes patches qualitatively very different from linear models by using component representations separated into mask and feature parameters. We first investigated encodings learned by the model using artificial data with mutually occluding components. We find that the model extracts the components, and that it can correctly identify the occlusive components with the hidden variables of the model. On natural image patches, the model learns component masks and features for typical image components. By using reverse correlation, we estimate the receptive fields associated with the model's hidden units. We find many Gabor-like or globular receptive fields as well as fields sensitive to more complex structures. Our results show that probabilistic models that capture occlusions and invariances can be trained efficiently on image patches, and that the resulting encoding represents an alternative model for the neural encoding of images in the primary visual cortex.

关键词： image patch images coding image coding Receptive field Probability Image Masks Occlusion sparse coding Unsupervised learning alternative model Striate Cortex

来源：评论

学校读者我要写书评

暂无评论

LEVERAGING 2D AND 3D CUES FOR FINE-GRAINED OBJECT CLASSIFICATION

LEVERAGING 2D AND 3D CUES FOR FINE-GRAINED OBJECT CLASSIFICA...

引用

IEEE International Conference on Image Processing

作者： Xiaolong Wang Robert (Bo) Li Jon Currey Samsung Research America

ISBN: (纸本)9781467399623

Objects in fine-grained categories always share a high degree of shape similarity, making both "localizing discriminative parts" and "learning appearance descriptors" extremely difficult. We propose a framework to leverage 2D+3D cues to handle above two challenges. Towards the goal of image alignment to localize discriminative parts, traditional methods rely on either manual part annotation or image segmentation. Instead, our framework leverages each image's 3D camera pose estimation to align images;Towards the goal of "learning appearance descriptors" confined with small training data and memory/computation cost, we propose an unsupervised Convolutional sparse coding (CSC) + manifold learning that significantly reduces model complexity, but still successfully produces highly diverse feature filters like deep neural network. Our experimental results attest the advocated framework's accuracy is comparable to a deep network, demonstrating its great potential on mobile devices.

关键词： Fine-grained object classification 2D+3D cues Convolutional sparse coding image registration Frameworks Leverage Mobile devices Taxonomy image segmentation Three Dimensions train data sparse coding

来源：评论

学校读者我要写书评

暂无评论

EXPLOITING LOW-DIMENSIONAL STRUCTURES TO ENHANCE DNN BASED ACOUSTIC MODELING IN SPEECH RECOGNITION

EXPLOITING LOW-DIMENSIONAL STRUCTURES TO ENHANCE DNN BASED A...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Pranay Dighe Gil Luyett Afsaneh Asaei Hervé Bourlard Idiap Research Institute Martigny Switzerland University of Fribourg Switzerland

ISBN: (纸本)9781479999897

We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding. sparse representation of the test posteriors using this dictionary enables projection to the space of training data. Relying on the fact that the intrinsic dimensions of the posterior subspaces are indeed very small and the matrix of all posteriors belonging to a class has a very low rank, we demonstrate how low-dimensional structures enable further enhancement of the posteriors and rectify the spurious errors due to mismatch conditions. The enhanced acoustic modeling method leads to improvements in continuous speech recognition task using hybrid DNN-HMM (hidden Markov model) framework in both clean and noisy conditions, where upto 15.4% relative reduction in word error rate (WER) is achieved.

关键词： sparse coding Dictionary learning Deep neural network Union of Low Dimensional Subspaces Acoustic modeling sparse coding Speech recognition acoustic modeling Dictionaries as Topic Modeling

来源：评论

学校读者我要写书评

暂无评论

Low-rank and sparse soft targets to learn better DNN acoustic models

Low-rank and sparse soft targets to learn better DNN acousti...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Pranay Dighe Afsaneh Asaei Herve Bourlard Idiap Research Institute Martigny Switzerland

ISBN: (纸本)9781509041183

Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition systems correspond to context-dependent tied states or senones. The present work addresses some limitations of GMM-HMM senone alignments for DNN training. We hypothesize that the senone probabilities obtained from a DNN trained with binary labels can provide more accurate targets to learn better acoustic models. However, DNN outputs bear inaccuracies which are exhibited as high dimensional unstructured noise, whereas the informative components are structured and low-dimensional. We exploit principal component analysis (PCA) and sparse coding to characterize the senone subspaces. Enhanced probabilities obtained from low-rank and sparse reconstructions are used as soft-targets for DNN acoustic modeling, that also enables training with untranscribed data. Experiments conducted on AMI corpus shows 4.6% relative reduction in word error rate.

关键词： Soft targets Principle component analysis sparse coding Automatic speech recognition Untranscribed data sparse coding Speech recognition principal components analysis Hidden Markov models Acoustic models Targets speech recognition system Gm(m) Error analysis

来源：评论

学校读者我要写书评

暂无评论

Clustering of Words using Dictionary-Learnt Word Representations

Clustering of Words using Dictionary-Learnt Word Representat...

引用

International Conference on Advances in Computing, Communications and Informatics

作者： Remya R. K. Menon Gargi, S. Samili, S. Department of Computer Science and Applications Amrita School of Engineering Amrita Vishwa Vidyapeetham Amrita University

ISBN: (纸本)9781509020300

Language is the way of communication through words. This will help to get a better insight of the world. Natural Language Processing (NLP) mainly concentrate on expanding systems that allow computers to communicate with people using everyday language. One of the challenges inherent in NLP is teaching computers to recognize the way humans learn and use language. Word representations give rise to capture syntactic and semantic properties of words. So the main purpose of this work is to find out the set of words which have similar semantics by matching the context in which the words occur. In this work we explore a new method for learning word representations using sparse coding, a technique usually done on signals and images. We present an efficient sparse coding algorithm, Orthogonal Matching Pursuit to generate the sparse code. Based on the input given, sparse codes are generated for the input. The input term vectors are classified based on the sparse code by grouping the terms which have same sparse code into one class. K-Means algorithm is also used to classify the input terms vectors which have semantic similarities. Finally, this paper makes a comparison that gives the best representation from the sparse code and K-Means. The result shows an improved set of similar words using sparse code when compared to K-Means. This is because SVD is used as a part of dictionary learning which captures the latent relationship that exists between the words.

关键词： NLP sparse coding Dictionary Learning K-Means OMP K-SVD Terms PMI

来源：评论

学校读者我要写书评

暂无评论

Learning Multiple Pooling Combination for Image Classification

Learning Multiple Pooling Combination for Image Classificati...

引用

International Joint Conference on Neural Networks

作者： Junlin Hu Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University

ISBN: (纸本)9781467314886

Recently sparse coding with spatial pyramid matching method has shown its excellent performance in image classification. Inspired by this technique, we present an image classification approach by learning the optimal Multiple Pooling Combination strategy based on Non-Negative sparse coding (MPC-NNSC) in this paper. First, non-negative sparse coding with three different pooling methods as well as spatial pyramid matching method are utilized to encode local descriptors for image representation, respectively. Then a promising weight learning approach is employed to find a set of optimal weights for best fusing all these pooling methods in different scales. Lastly, support vector machine classifier with linear and histogram intersection kernel is employed for the final classification task. Experiments on two popular benchmark datasets are presented and they demonstrate the better performance of the proposed scheme compared to the state-of-the-art methods.

关键词： Image classification pooling sparse coding image representation Nonnegative Pyramid

来源：评论

学校读者我要写书评

暂无评论

SPARSITY LEVEL IN A NON-NEGATIVE MATRIX FACTORIZATION BASED SPEECH STRATEGY IN COCHLEAR IMPLANTS

SPARSITY LEVEL IN A NON-NEGATIVE MATRIX FACTORIZATION BASED ...

引用

European Signal Processing Conference

作者： Hongmei Hu Nasser Mohammadiha Jalil Taghia Arne Leijon Mark E. Lutman Shouyan Wang Institute of Sound and Vibration Research University of Southampton School of Electrical Engineering Royal Institute of Technology

ISBN: (纸本)9781467310680

Non-negative matrix factorization (NMF) has increasingly been used as a tool in signal processing in the last years, but it has not been used in the cochlear implants (CIs). To improve the performance of CIs in noisy environments, a novel sparse strategy is proposed by applying NMF on envelopes of 22 channels. In the new algorithm, the noisy speech is first transferred to the time-frequency domain via a 22-channel filter bank and the envelope in each frequency channel is extracted;secondly, NMF is applied to the envelope matrix (envelopegram);finally, the sparsity condition is applied to the coefficient matrix to get more sparse representation. Speech reception threshold (SRT) subjective experiment was performed in combination with five objective measurements in order to choose the proper parameters for the sparse NMF model.

关键词： Non-negative matrix factorization Cochlear implants sparse coding Objective measurements Speech perception threshold matrix decomposition envelopes frequency channel NMF protocol Coefficient Matrix Speech speech reception threshold (SRT) indium Implants and Prostheses factorization Frequency-domain analysis ENVELOPE signal processing

来源：评论

学校读者我要写书评

暂无评论

Tumor classification via a simultaneous structure sparse representation model

Tumor classification via a simultaneous structure sparse rep...

引用

International Conference on BioMedical Engineering and Informatics (BMEI)

作者： Yafeng Li Department of Computer Science Baoji University of Arts and Science Baoji China

ISBN: (纸本)9781479927623

Cancer diagnosis is an important clinical application of gene expression microarray technology. This paper proposes a new model for tumor classification. The key idea is to implement the similar joint decomposition approach in the context of sparse coding with subsequences of gene expression data (SGED). Based on this idea, we formulate a simultaneous structure sparse model for tumor classification. Finally, experimental results in five tumor gene expression datasets show that the proposed method outperforms sparse representation method.

关键词： Component sparse representation Tumor classification Gene expression data Structure sparse who tumor classification sparse representation sparse coding neoplasm diagnosis

来源：评论

学校读者我要写书评

暂无评论

Prediction of O-linked Glycosylation Sites in Protein Sequence by PCA-LDA

Prediction of O-linked Glycosylation Sites in Protein Sequen...

引用

2009 Ninth International Conference on Hybrid Intelligent Systems(第九届混合智能系统国际会议 HIS 2009)

作者： Xue-mei Yang College of Mathematics and Information Science Xianyang Normal Univ. Xianyang 712000China

O-glycosylation is one of the main types of the mammalian protein glycosylation, it occurs on the particular site of serine and threonine. In this paper, a new method of PCA-LDA is used for the prediction of O-glycosylation site under all kinds of window size (5,7,9,11,21,31,41,51). The new method of PCA-LDA is the combination of PCA and LDA, we also call it hybrid discriminant analysis(HDA). The test protein sequence which is encoded by the sparse coding is projected to the one-dimensional subspace and then by calculating the Mahanalobis distance between the projection and each class center, the test protein sequence is assigned into the “nearest” class, so it can be known that whether a particular site of serine and threonine is glycosylated. The result of experiments shows that the proposed method of HDA is more effective and accurate. The prediction accuracy is about 75％-92.5％.

关键词： prediction glycosylation protein sparse coding HDA classification

来源：评论

学校读者我要写书评

暂无评论

A DISCRIMINATIVE APPROACH TO POLYPHONIC PIANO NOTE TRANSCRIPTION USING SUPERVISED NON-NEGATIVE MATRIX FACTORIZATION

A DISCRIMINATIVE APPROACH TO POLYPHONIC PIANO NOTE TRANSCRIP...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Felix Weninger Christian Kirst Bjorn Schuller Hans-Joachim Bungartz Machine Intelligence & Signal Processing Group MMK Department of Informatics Technische Universit?t München

ISBN: (纸本)9781479903573

We introduce a novel method for the transcription of polyphonic piano music by discriminative training of support vector machines (SVMs). As features, we use pitch activations computed by supervised non-negative matrix factorization from low-level spectral features. Different approaches to low-level feature extraction, NMF dictionary learning and activation feature extraction are analyzed in a large-scale evaluation on eight hours of piano music including synthesized and real recordings. We conclude that the proposed method delivers state-of-the-art results and clearly outperforms SVMs using simple spectral features.

关键词： Transcription sparse coding non-negative matrix factorization music information retrieval Music information retrieval Genetic Transcription sparse coding matrix decomposition Transcription spectral feature factorization PIANO matrix Support Vector Network Feature extraction

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共211页 << < 202 203 204 205 206 207 208 209 210 211 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：