检索结果-内蒙古大学图书馆

The role of superior image composition in children's analogical reasoning

SOFTWARE-PRACTICE & EXPERIENCE 2020年第11期50卷 2082-2094页

作者： Yu, Xiao Han, Congcong Guo, Junqi Chen, Yinghe Beijing Normal Univ Fac Psychol Sch Dev Psychol Beijing 100875 Peoples R China Shandong Normal Univ Sch Psychol Jinan Shandong Peoples R China Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China

Analogical reasoning, as a higher cognitive ability, can help children make inferences about a novel situation. It is vital to help children's analogical reasoning development. However, the traditional intervention methods are simple and the effects cannot maintain. Aiming at this problem, the present study was the first to use computer technology especially image composition technique to promote children's analogical reasoning from an interdisciplinary perspective. Specifically, one minimum region entropy based composition model was proposed. On the one hand, sparse coding model and spatial pyramid matching model were used for searching semantically matching images. On the other hand, minimum region entropy model could contribute to composite the candidate region into an ideal position. Furthermore, we set up a database using massive images and adequate experiments based on it to verify the model's effectiveness and robustness. What's more important, we applied the improved image composition to analogical reasoning task. The results showed that the performance of intervention group was obviously better than control group during intervention stages and posttest stage. In general, the present study not only demonstrated the advantages of the improved image composition but also revealed composition's remarkable contribution for getting analogical relationship by children.

关键词： analogical reasoning children image composition minimum region entropy sparse coding spatial pyramid matching watershed segmentation

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image classification using a spectral-spatial sparse coding model

Hyperspectral image classification using a spectral-spatial ...

引用

Conference on Image and Signal Processing for Remote Sensing XIX

作者： Oguslu, Ender Zhou, Guoqing Li, Jiang Guilin Univ Technol Guangxi Key Lab Spatial Informat & Geomat Guilin 541004 Peoples R China Old Dominion Univ Dept Elect & Comp Engn Norfolk VA 23529 USA Air Force NCO Voacat Coll Izmir Turkey

ISBN: (纸本)9780819497611

We present a sparse coding based spectral-spatial classification model for hyperspectral image (HSI) datasets. The proposed method consists of an efficient sparse coding method in which the l(1)/l(q) regularized multi-class logistic regression technique was utilized to achieve a compact representation of hyperspectral image pixels for land cover classification. We applied the proposed algorithm to a HSI dataset collected at the Kennedy Space Center and compared our algorithm to a recently proposed method, Gaussian process maximum likelihood (GP-ML) classifier. Experimental results show that the proposed method can achieve significantly better performances than the GP-ML classifier when training data is limited with a compact pixel representation, leading to more efficient HSI classification systems.

关键词： Remote sensing sparse coding feature selection

来源：评论

学校读者我要写书评

暂无评论

Analysis of WD Face Dictionary for sparse coding Based Face Recognition

Analysis of WD Face Dictionary for Sparse Coding Based Face ...

引用

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

作者： Thavalengal, Shejin Sao, Anil Kumar School of Computing and Electrical Engineering Indian Institute of Technology Mandi India

ISBN: (纸本)9783642411816;9783642411809

This paper deals with the analysis of WD Face dictionary for sparse coding based face recognition. WD (weighted decomposition) Face dictionary emphasizes subject specific unique information of a person. This dictionary has an advantage to adapt to the nature of training images. In the resultant dictionary rows are uncorrelated, which is an essential criterion for dictionary to ensure sparse representation of coefficient vector. The range of sparsity determined by calculating the lower and upper bounds of sparse recovery of coefficient vector for WD Face dictionary exhibits its capability to sparsely represent a test image as a linear combination of training images, even when available training images are small in number. Experimental results solidify our proposal that sparse coding based face recognition with WD Face dictionary is preferable to the existing face recognition techniques.

关键词： sparse coding dictionary face recognition.

来源：评论

学校读者我要写书评

暂无评论

A DIAGONALIZED NEWTON ALGORITHM FOR NON-NEGATIVE sparse coding

A DIAGONALIZED NEWTON ALGORITHM FOR NON-NEGATIVE SPARSE CODI...

引用

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

作者： Van Hamme, Hugo Katholieke Univ Leuven ESAT Dept Elect Engn Louvain Belgium

ISBN: (纸本)9781479903566

Signal models where non-negative vector data are represented by a sparse linear combination of non-negative basis vectors have attracted much attention in problems including image classification, document topic modeling, sound source segregation and robust speech recognition. In this paper, an iterative algorithm based on Newton updates to minimize the Kullback-Leibler divergence between data and model is proposed. It finds the sparse activation weights of the basis vectors more efficiently than the expectation-maximization (EM) algorithm. To avoid the computational burden of a matrix inversion, a diagonal approximation is made and therefore the algorithm is called diagonal Newton Algorithm (DNA). It is several times faster than EM, especially for undercomplete problems. But DNA also performs surprisingly well on overcomplete problems.

关键词： sparse coding non-negative matrix factorization source separation Newton method Kullback Leibler divergence vocabulary acquisition

来源：评论

学校读者我要写书评

暂无评论

Decoupling sparse coding of SIFT descriptors for large-scale visual recognition

Decoupling sparse coding of SIFT descriptors for large-scale...

引用

Conference on Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XI

作者： Ji, Zhengping Theiler, James Chartrand, Rick Kenyon, Garrett Brumby, Steven P. Los Alamos Natl Lab Div Theoret T5 Los Alamos NM 87545 USA

ISBN: (纸本)9780819495419

In recent years, sparse coding has drawn considerable research attention in developing feature representations for visual recognition problems. In this paper, we devise sparse coding algorithms to learn a dictionary of basis functions from Scale-Invariant Feature Transform (SIFT) descriptors extracted from images. The learned dictionary is used to code SIFT-based inputs for the feature representation that is further pooled via spatial pyramid matching kernels and fed into a Support Vector Machine (SVM) for object classification on the large-scale ImageNet dataset. We investigate the advantage of SIFT-based sparse coding approach by combining different dictionary learning and sparse representation algorithms. Our results also include favorable performance on different subsets of the ImageNet database.

关键词： Visual recognition sparse coding SIFT ImageNet

来源：评论

学校读者我要写书评

暂无评论

Multi-pose Face Recognition Based on Block Adaptation 1

引用

11th International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management (DHM) Held as Part of the 22nd International Conference on Human-Computer Interaction (HCII)

作者： Shi, Jianguo Zhao, Yuanyuan Anhui Polytech Univ Sch Comp & Informat Beijing Cent Rd 8 Wuhu 241000 Peoples R China

ISBN: (数字)9783030499075

ISBN: (纸本)9783030499068;9783030499075

Considering that the SRC algorithm cannot solve the error offset problem between the testing and training samples, we propose one method as the affine transformation and partition by integrating into the linear reconstruction model, which were named as block adaptive multi-pose face recognition algorithm (BA-SRC). In this method, we first model the pose change using the affine transformation model for the face after the human face was blocked. Then we estimate the initial value of the affine transformation parameter by minimizing the image block reconstruction error, and then compensate the local area error caused by pose change, so as to improve the performance of face recognition. The experiments show that the algorithm proposed in this paper is very robust to pose change, and has a good recognition result.

关键词： Block adaptive Affine transformation sparse coding Multi-pose Face recognition

来源：评论

学校读者我要写书评

暂无评论

Document Specific sparse coding for Word Retrieval

Document Specific Sparse Coding for Word Retrieval

引用

12th International Conference on Document Analysis and Recognition (ICDAR)

作者： Shekhar, Ravi Jawahar, C. V. Int Inst Informat Technol Hyderabad Ctr Visual Informat Technol Hyderabad Andhra Pradesh India

ISBN: (纸本)9780769549993

Bag of words (BoW) based retrieval is an efficient method to compare the visual similarity between two images. Recognition free methods based on BoW have shown to outperform OCR based methods. We further improve the performance by defining a document specific sparse coding scheme for representing visual words (interest points) in document images. Our method is motivated by the successful use of sparsity in signal representation by exploiting the neighbourhood properties. In addition to providing insights into the design of the coding scheme, we also verify the method on two data sets and compare with the recent methods. We have also developed text query based search solution, and we report performance comparable to image based search.

关键词： Document Image Retrieval sparse coding Bag of Words

来源：评论

学校读者我要写书评

暂无评论

TEMPORALLY ADAPTIVE-DYNAMIC sparse NETWORK FOR MODELING DISEASE PROGRESSION 17

TEMPORALLY ADAPTIVE-DYNAMIC SPARSE NETWORK FOR MODELING DISE...

引用

IEEE 17th International Symposium on Biomedical Imaging (ISBI)

作者： Zhang, Jie Wang, Yalin Arizona State Univ Sch Comp Informat & Decis Syst Engn Tempe AZ 85281 USA

ISBN: (纸本)9781538693308

Alzheimer's disease (AD) is a neurodegenerative disorder with progressive impairment of memory and cognitive functions. sparse coding (SC) has been demonstrated to be an efficient and effective method for AD diagnosis and prognosis. However, previous SC methods usually focus on the baseline data while ignoring the consistent longitudinal features with strong sparsity pattern along the disease progression. Additionally, SC methods extract sparse features from image patches separately rather than learn with the dictionary atoms across the entire subject. To address these two concerns and comprehensively capture temporal-subject sparse features towards earlier and better discriminability of AD, we propose a novel supervised SC network termed Temporally Adaptive-Dynamic sparse Network (TADsNet) to uncover the sequential correlation and native subject-level codes from the longitudinal brain images. Our work adaptively updates the sparse codes to impose the temporal regularized correlation and dynamically mine the dictionary atoms to make use of entire subject-level features. Experimental results on ADNI-I cohort validate the superiority of our approach.

关键词： RNN sparse coding Longitudinal

来源：评论

学校读者我要写书评

暂无评论

A physics-constrained dictionary learning approach for compression of vibration signals

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2021年 153卷 107434-107434页

作者： Lu, Yanglong Wang, Yan Georgia Inst Technol Woodruff Sch Mech Engn Atlanta GA 30332 USA

Monitoring the health condition of rotating machinery in manufacturing systems usually requires vibration signals to be continuously collected, transmitted, and stored. The available bandwidth in communication channels for transmission of a large amount of data is limited in an industry setting. Therefore, reducing the amount of data in communication and storage without sacrificing the amount of information collection is necessary. Here, a new technique called physics-constrained dictionary learning is proposed to reduce the volume of data in storage and communication using compressed sensing. In compressed sensing, the original signals can be reconstructed with a much smaller amount of data determined by a measurement matrix, if the representation of signals in the reciprocal space is sparse. The proposed physics-constrained dictionary learning approach optimizes the measurement and basis matrices simultaneously to improve the accuracy of reconstruction, where physical constraints of time stamps of sampling and sampling intervals are considered. New training algorithms are developed. The proposed scheme is applied to compress the vibration signals of roller bearings. It is shown that the reconstruction performance of the proposed scheme is significantly improved from traditional dictionary learning. (c) 2020 Elsevier Ltd. All rights reserved.

关键词： Compressed sensing Dictionary learning sparse coding Data compression Rotating machinery

来源：评论

学校读者我要写书评

暂无评论

Learning Features for Activity Recognition with Shift-Invariant sparse coding

Learning Features for Activity Recognition with Shift-Invari...

引用

23rd International Conference on Artificial Neural Networks (ICANN)

作者： Vollmer, Christian Gross, Horst-Michael Eggert, Julian P. Ilmenau Univ Technol Neuroinformat & Cognit Robot Lab D-98684 Ilmenau Germany Honda Res Inst Europe GmbH D-63073 Offenbach Germany

ISBN: (纸本)9783642407277;9783642407284

In activity recognition, traditionally, features are chosen heuristically, based on explicit domain knowledge. Typical features are statistical measures, like mean, standard deviation, etc., which are tailored to the application at hand and might not fit in other cases. However, Feature Learning techniques have recently gained attention for building approaches that generalize over different application domains. More conventional approaches, like Principal Component Analysis, and newer ones, like Deep Belief Networks, have been studied so far and yielded significantly better results than traditional techniques. In this paper we study the potential of Shift-invariant sparse coding (SISC) as an additional Feature Learning technique for activity recognition. We evaluate the performance on several publicly available activity recognition data sets and show that classification based on features learned by SISC outperforms other previously presented Feature Learning techniques.

关键词： feature learning activity recognition 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：