检索结果-内蒙古大学图书馆

IEEE International Conference on Computer Vision (ICCV)

作者： Harandi, Mehrtash Sanderson, Conrad Shen, Chunhua Lovell, Brian C. NICTA Sydney NSW Australia Australian Natl Univ Coll Engn & Comp Sci Canberra ACT 0200 Australia Queensland Univ Technol Brisbane Qld 4001 Australia Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia Univ Queensland Brisbane Qld 4072 Australia

ISBN: (纸本)9781479928392

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables us to devise a closed-form solution for updating a Grassmann dictionary, atom by atom. Furthermore, to handle non-linearity in data, we propose a kernelised version of the dictionary learning algorithm. Experiments on several classification tasks (face recognition, action recognition, dynamic texture classification) show that the proposed approach achieves considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelised Affine Hull Method and graphembedding Grassmann discriminant analysis.

关键词： Grassmann manifolds action recognition dictionary learning dynamic texture classification image-set sparse coding sparse coding Dictionaries as Topic images computer vision Manifolds Symmetric matrix

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC IMAGE ANNOTATION VIA LOCAL sparse coding

AUTOMATIC IMAGE ANNOTATION VIA LOCAL SPARSE CODING

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhang, Wenbo Tian, Dongping Hu, Hong Zhao, Xiaofei Shi, Zhongzhi Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China

ISBN: (纸本)9781479903566

sparse coding is an active research topic in machine learning and signal processing community. In this paper, we propose a novel local sparse model for multi-label image annotation. Existing feature descriptors and extraction algorithms pay less attention to semantic information and extracted feature dimension usually is high, which leads to heavy computation. Noise and redundant information often reduce the performance of sparse model. To address these issues, we combine label and visual information for feature selection while most previous work only utilizes labels and ignores visual information itself. First of all, we make use of label sets to seek images neighbor relations and generate the Gaussian kernel matrix over these neighbor images, then use LLP(Local Learning Projection) algorithm to get minimal local estimation error. After that, for each query image, we find its K nearest neighbors in the transformed space and use these neighbors to reconstruct it via sparse coding. Moreover, during coding, we penalize the corresponding reconstruction coefficients to implicitly reflect the neighbor relations. Finally, propagating tags from training data to test data. Image annotation experiments on the Corel5k dataset show the performance of our approach is comparable to several state-of-the-art algorithms.

关键词： image annotation feature selection KN-N local sparse coding

来源：评论

学校读者我要写书评

暂无评论

Single Textual Image Super-Resolution Using Multiple Learned Dictionaries Based sparse coding

Single Textual Image Super-Resolution Using Multiple Learned...

引用

17th International Conference on Image Analysis and Processing (ICIAP)

作者： Walha, Rim Drira, Fadoua Lebourgeois, Franck Garcia, Christophe Alimi, Adel M. Univ Sfax ENIS REGIM BP 1173 Sfax 3038 Tunisia Univ Lyon INSA Lyon CNRS LIRIS UMR5205 F-69621 Lyon France

ISBN: (纸本)9783642411847;9783642411830

In this paper, we propose a new approach based on sparse coding for single textual image Super-Resolution (SR). The proposed approach is able to build more representative dictionaries learned from a large training Low-Resolution/High-Resolution (LR/HR) patch pair database. In fact, an intelligent clustering is employed to partition such database into several clusters from which multiple coupled LR/HR dictionaries are constructed. Based on the assumption that patches of the same cluster live in the same subspace, we exploit for each local LR patch its similarity to clusters in order to adaptively select the appropriate learned dictionary over that such patch can be well sparsely represented. The obtained sparse representation is hence applied to generate a local HR patch from the corresponding HR dictionary. Experiments on textual images show that the proposed approach outperforms its counterparts in visual fidelity as well as in numerical measures.

关键词： Super-resolution sparse coding multiple learned dictionaries textual image

来源：评论

学校读者我要写书评

暂无评论

Multi-Attributed Dictionary Learning for sparse coding

Multi-Attributed Dictionary Learning for Sparse Coding

引用

IEEE International Conference on Computer Vision (ICCV)

作者： Chiang, Chen-Kuo Su, Te-Feng Yen, Chih Lai, Shang-Hong Natl Tsing Hua Univ Hsinchu 300 Taiwan

ISBN: (纸本)9781479928392

We present a multi-attributed dictionary learning algorithm for sparse coding. Considering training samples with multiple attributes, a new distance matrix is proposed by jointly incorporating data and attribute similarities. Then, an objective function is presented to learn category-dependent dictionaries that are compact (closeness of dictionary atoms based on data distance and attribute similarity), reconstructive (low reconstruction error with correct dictionary) and label-consistent (encouraging the labels of dictionary atoms to be similar). We have demonstrated our algorithm on action classification and face recognition tasks on several publicly available datasets. Experimental results with improved performance over previous dictionary learning methods are shown to validate the effectiveness of the proposed algorithm.

关键词： Dictionary learning multiple attributes sparse coding sparse coding Dictionaries as Topic reconstruction error distance matrix Facial Recognition

来源：评论

学校读者我要写书评

暂无评论

A Fast Proximal Method for Convolutional sparse coding

A Fast Proximal Method for Convolutional Sparse Coding

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chalasani, Rakesh Principe, Jose C. Ramakrishnan, Naveen Univ Florida Dept Elect & Comp Engn Gainesville FL 32611 USA Robert Bosch LLC Res & Technol Ctr North Amer Pittsburgh PA USA

ISBN: (纸本)9781467361293;9781467361286

sparse coding, an unsupervised feature learning technique, is often used as a basic building block to construct deep networks. Convolutional sparse coding is proposed in the literature to overcome the scalability issues of sparse coding techniques to large images. In this paper we propose an efficient algorithm, based on the fast iterative shrinkage thresholding algorithm (FISTA), for learning sparse convolutional features. Through numerical experiments, we show that the proposed convolutional extension of FISTA can not only lead to faster convergence compared to existing methods but can also easily generalize to other cost functions.

关键词： Convolution sparse coding Feature Extraction Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

Shearlet Network-based sparse coding Augmented by Facial Texture Features for Face Recognition

Shearlet Network-based Sparse Coding Augmented by Facial Tex...

引用

17th International Conference on Image Analysis and Processing (ICIAP)

作者： Borgi, Mohamed Anouar Labate, Demetrio El'Arbi, Maher Ben Amar, Chokri Univ Sfax ENIS REGIM REs Grp Intelligent Machines BP 1173 Sfax 3038 Tunisia Univ Houston Dept Math Houston TX 77204 USA

ISBN: (纸本)9783642411847;9783642411830

One open challenge in face recognition (FR) is the single training sample per subject. This paper addresses this problem through a novel approach that combine Shearlet Networks (SN) and PCA called (SNPCA). Shearlet Network takes advantage of the sparse representation (SR) properties of shearlets in biometric applications, Especially, for face coding and recognition. The main contributions of this paper are (1) the combination of the multi-scale representation which capture geometric information to derive a very efficient representation of facial templates, and the use of a PCA-based approach and (2) the design of a fusion step by a refined model of belief function based on the Dempster-Shafer rule in the context of confusion matrices. This last step is helpful to improve the processing of facial texture features. We compared our algorithm (SNPCA) against SN, a wavelet network (WN) implementation and other standard algorithms. Our tests, run on several face databases including FRGC, Extended Yale B database and others, shows that this approach yields a very competitive performance compared to wavelet networks (WN), standard shearlet and PCA-based methods.

关键词： Shearlet Shearlets Network sparse coding Face Recognition

来源：评论

学校读者我要写书评

暂无评论

Pose-invariant Face Synthesis and Recognition via sparse coding and Symmetrical Information

引用

2nd International Conference on Industrial Design and Mechanics Power (ICIDMP 2013)

作者： Shuai, Zhang Rui, Wang Hai Li, He Xiao Kunming Univ Sci & Technol Sch Informat Engn & Automat Kunming Peoples R China

ISBN: (纸本)9783037858967

Pose variation which brings illumination change, occlusion and non-linear scale variation, dramatically drops the performance of face recognition systems. In this paper, we propose a novel pose invariant face recognition method, in which we build a joint sparse coding scheme to predict face images from a certain pose to another. By introducing autoregressive regularization and symmetric information, our algorithm could achieve high robustness to local misalignment and large pose differences. Besides, we propose a new coarse pose estimation algorithm by collaborative representation classifier, which is very fast and enough accurate for our synthesis algorithm. The experiment results on multi-pose subsets of CMU-PIE and FERET database show the efficiency of the proposed method on multi-pose face recognition.

关键词： Multi-pose Face Recognition Face Synthesis sparse coding

来源：评论

学校读者我要写书评

暂无评论

High Payload Audio Watermarking Using sparse coding with Robustness to MP3 Compression

High Payload Audio Watermarking Using Sparse Coding with Rob...

引用

1st International Conference on Advances in Security of Information and Communication Networks (SecNet 2013)

作者： Fakhr, Mohamed Waleed Univ Bahrain Elect & Elect Dept Manama Bahrain

ISBN: (纸本)9783642405969

A high payload audio watermarking technique is proposed based on the compressed sensing and sparse coding framework, with robustness to MP3 128kbps and 64kbps compression attacks. The binary watermark is a sparse vector with one non-zero element that takes a positive or negative sign based on the bit value to be encoded. A Gaussian random dictionary maps the sparse watermark to a random watermark embedding vector that is selected adaptively for each audio frame to maximize robustness to the MP3 attack. At the decoder, the Basis Pursuit Denoising algorithm (BPDN) is used to extract the embedded watermark sign. High payloads of (689, 1378 and 2756) bps are achieved with %BER of (0.3%, 0.5% and 1%) and (0.1%, 0.3% and 0.5%) for 64kbps and 128kbps MP3 compression attacks respectively. The signal to embedding noise ratio is kept in the range of 27-30 dB in all cases.

关键词： sparse coding Compressed Sensing Audio Watermarking MP3 Audio Robust Watermarking Basis Pursuit Denoising (BPDN)

来源：评论

学校读者我要写书评

暂无评论

Highly overcomplete sparse coding

Highly overcomplete sparse coding

引用

Conference on Human Vision and Electronic Imaging XVIII

作者： Olshausen, Bruno A. Univ Calif Berkeley Redwood Ctr Theoret Neurosci Helen Wills Neurosci Inst Berkeley CA 94720 USA

ISBN: (纸本)9780819494245

This paper explores sparse coding of natural images in the highly over complete *** show that as the over completeness ratio approaches 10x, new types of dictionary elements emerge beyond the classical Gabor function shape obtained from complete or only modestly overcomplete sparse coding. These more diverse dictionaries allow images to be approximated with lower L1 norm (for a fixed SNR), and the coefficients exhibit steeper decay. We also evaluate the learned dictionaries in a denoising task, showing that higher degrees of overcompleteness yield modest gains in peformance.

关键词： sparse coding natural images overcomplete dictionaries denoising

来源：评论

学校读者我要写书评

暂无评论

Field of experts optimization-based noisy image retrieval

引用

SOFTWARE-PRACTICE & EXPERIENCE 2020年第11期50卷 2110-2118页

作者： Guo, Junqi Shen, Guicheng Su, Yichen Zhao, Jin Wu, Hao Zhu, Zhilin Beijing Normal Univ Sch Artificial Intelligence Beijing Peoples R China Minist Educ Engn Res Ctr Intelligent Technol & Educ Applicat Beijing Peoples R China Beijing Wuzi Univ Sch Informat Beijing Peoples R China Beijing Normal Univ Sch Math Sci Beijing Peoples R China Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai Shandong Peoples R China

The value of image retrieval has become more and more prominent in the era of big data. However, large numbers of images are missed from current method since the image retrieval precision largely depends on the high quality of images. By common methodology, when the quality of images decreases a little, the accuracy of retrieval would decrease significantly. In particular, it is difficult to retrieve noisy images effectively by conventional approach. Yet large number of the noisy images could not be ignored at the age of data explosion. Aiming at the problem above, we proposed noisy image retrieval model based on field of experts (FoE) optimization. High-quality learning images could be selected by sparse coding, which is based on similarity calculation model, and the multioption filter combination model enhances the power of FoE model. We set up a database containing a large numbers of noisy images. Over this database, adequate groups of experiments are conducted. The verification of the method concluded its effectiveness and superiority.

关键词： FoE multioption filters noisy image retrieval sparse coding

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：