检索结果-内蒙古大学图书馆

IEEE International Conference on Computer Vision (ICCV)

作者： Chi, Yu-Tseh Ali, Mohsen Rushdi, Muhammad Ho, Jeffrey Univ Florida Dept Comp & Informat Sci & Engn Gainesville FL 32611 USA Cairo Univ Dept Biomed & Syst Engn Giza Egypt

ISBN: (纸本)9781479928392

This paper proposes a novel approach for sparse coding that further improves upon the sparse representation-based classification (SRC) framework. The proposed framework, Affine-Constrained Group sparse coding (ACGSC), extends the current SRC framework to classification problems with multiple input samples. Geometrically, the affine-constrained group sparse coding essentially searches for the vector in the convex hull spanned by the input vectors that can best be sparse coded using the given dictionary. The resulting objective function is still convex and can be efficiently optimized using iterative block-coordinate descent scheme that is guaranteed to converge. Furthermore, we provide a form of sparse recovery result that guarantees, at least theoretically, that the classification performance of the constrained group sparse coding should be at least as good as the group sparse coding. We have evaluated the proposed approach using three different recognition experiments that involve illumination variation of faces and textures, and face recognition under occlusions. Preliminary experiments have demonstrated the effectiveness of the proposed approach, and in particular, the results from the recognition/occlusion experiment are surprisingly accurate and robust.

关键词： sparse coding affine classification group

来源：评论

学校读者我要写书评

暂无评论

Human Motion Retrieval Based on sparse coding and Touchless Interactions

Human Motion Retrieval Based on Sparse Coding and Touchless ...

引用

13th International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics)

作者： Zhou, Liuyang Leung, Howard City Univ Hong Kong Dept Comp Sci Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781479925766

To search for a particular motion from a large database, a user-friendly and efficient retrieval mechanism is essential. In this paper, we propose a human motion retrieval system based on sparse coding and touchless interactions. Compared with existing methods that involve vector quantization, sparse coding leads to a more compact and discriminative representation. Motion comparison based on sparse representation greatly improves the effectiveness of motion retrieval in terms of accuracy and speed. With the recent advancement in human motion tracking hardware such as Kinect, our retrieval system allows the user to specify the query motion by performing it directly. Besides, the user interacts with the retrieval system interactively using gestures so no controller is required thus delivering a natural user interface.

关键词： Character animation motion retrieval sparse representation sparse coding Microsoft kinect

来源：评论

学校读者我要写书评

暂无评论

Target Tracking Using Two-stage sparse coding

Target Tracking Using Two-stage Sparse Coding

引用

International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)

作者： Liu, Yang Ji, Xiaofei Li, Yibo Yi, Guohan Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing Jiangsu Peoples R China Shenyang Aerosp Univ Coll Automat Shenyang Peoples R China

ISBN: (纸本)9781479925650

Target tracking is an important issue in computer vision for its widely applications in video surveillance, human-computer interaction, robotic navigation, image compression and so on. There exist challenging problems such as occlusion, pose change, illumination change etc. in real videos. The two-stage sparse coding method for target tracking is proposed in this paper. The proposed method is based on Bayesian network and sparse coding with dynamic dictionary. In order to overcome the visual drift, the two-stage method is applied with target and dictionary updating to realize tracking accurately and quickly. Some public and popular challenging sequences are used to demonstrate the effectiveness of the proposed method. The experiment results show that the proposed method has better performance compared with other state-of-the-art methods.

关键词： sparse coding object tracking Bayesian tracking framework

来源：评论

学校读者我要写书评

暂无评论

Predicting future cognitive decline with hyperbolic stochastic coding

引用

MEDICAL IMAGE ANALYSIS 2021年 70卷 102009-102009页

作者： Zhang, Jie Dong, Qunxi Shi, Jie Li, Qingyang Stonnington, Cynthia M. Gutman, Boris A. Chen, Kewei Reiman, Eric M. Caselli, Richard J. Thompson, Paul M. Ye, Jieping Wang, Yalin Arizona State Univ Sch Comp Informat & Decis Syst Engn POB 878809 Tempe AZ 85287 USA Mayo Clin Arizona Dept Psychiat & Psychol Scottsdale AZ USA IIT Armour Coll Engn Chicago IL 60616 USA Banner Alzheimers Inst Phoenix AZ USA Mayo Clin Arizona Dept Neurol Scottsdale AZ USA Univ Southern Calif Imaging Genet Ctr Inst Neuroimaging & Informat Los Angeles CA USA Univ Michigan Dept Computat Med & Bioinformat Ann Arbor MI 48109 USA Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

Hyperbolic geometry has been successfully applied in modeling brain cortical and subcortical surfaces with general topological structures. However, such approaches, similar to other surface-based brain morphology analysis methods, usually generate high dimensional features. It limits their statistical power in cognitive decline prediction research, especially in datasets with limited subject numbers. To address the above limitation, we propose a novel framework termed as hyperbolic stochastic coding (HSC). We first compute diffeomorphic maps between general topological surfaces by mapping them to a canonical hyperbolic parameter space with consistent boundary conditions and extracts critical shape features. Secondly, in the hyperbolic parameter space, we introduce a farthest point sampling with breadth-first search method to obtain ring-shaped patches. Thirdly, stochastic coordinate coding and max-pooling algorithms are adopted for feature dimension reduction. We further validate the proposed system by comparing its classification accuracy with some other methods on two brain imaging datasets for Alzheimer's disease (AD) progression studies. Our preliminary experimental results show that our algorithm achieves superior results on various classification tasks. Our work may enrich surface-based brain imaging research tools and potentially result in a diagnostic and prognostic indicator to be useful in individualized treatment strategies. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Alzheimer's disease (AD) Hyperbolic space Ring-shaped patches sparse coding Classification

来源：评论

学校读者我要写书评

暂无评论

Multi-source material image optimized selection based multi-option composition

引用

IMAGE AND VISION COMPUTING 2021年 107卷 104123-104123页

作者： Wu, Hao An, Ding Zhu, Xiaoyu Zhang, Zhiyi Fan, Guodong Hua, Zhen Beijing Normal Univ Sch Artificial Intelligence Beijing Peoples R China Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai Peoples R China

Image composition aims to composite a material region into a target image. Using this technique, more images could be interactive, as there are millions of images created daily in modern life. However, it is difficult for the majority of traditional composition methods to retrieve relatively realistic semantically valid material images. Also, even if the minority of traditional composition methods yield superior results, it remains difficult to retrieve adequate material images due to the limitation of existing semantically valid images. Artificial traces also significantly reduce the visual esthetic of composited results. Based on these problems, we propose a multi-source material image optimized selection based multi-option composition method. Firstly, a robust sparse coding based retrieval model is used to retrieve material images effectively. On this basis, the attention mechanism based circular SA-GAN model could generate many semantically valid material images that guarantee the adequacy of material images. Secondly, the pixel-level optimization based multi-scale composition model minimizes artificial traces and reduces computational burden. Finally, an experimental database using many images was built. Based on this model, adequate comparative experiments using multiple evaluation criteria fully show the proposed method's effectiveness and robustness. ? 2021 Elsevier B.V. All rights reserved.

关键词： Image composition Material image sparse coding Circular SA-GAN Multi-scale composition

来源：评论

学校读者我要写书评

暂无评论

sparse MP4

Sparse MP4

引用

IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI)

作者： Wang, Daniel A. Strauss, Charles M. S. Springer, Jacob M. Thresher, Austin Pritchard, Howard Kenyon, Garrett T. Los Alamos Natl Lab Ultrascale Res Ctr Los Alamos NM 87545 USA New Mexico Consortium Los Alamos NM USA Swarthmore Coll Swarthmore PA 19081 USA Los Alamos Natl Lab Adv Res Cyber Syst Los Alamos NM USA Los Alamos Natl Lab Computat Comp & Stat Sci Los Alamos NM USA

ISBN: (数字)9781728157450

ISBN: (纸本)9781728157450

MP4 is currently the gold standard for video compression. Here we demonstrate that MP4 can be augmented by using a spatiotemporal sparse code optimized for the reconstruction of video portraits to up-sample data streams in which 75% of the pixels have been removed. Lossless MP4 can then be used to transmit the decimated video stream, yielding additional compression via a hybrid algorithm we refer to as sparse MP4. We report that when compared with standard MP4 tuned for a similar overall compression ratio, sparse MP4 achieves significantly higher PSNR and similar SSIM scores.

关键词： Video Compression sparse coding Bottleneck Autoencoders MP4

来源：评论

学校读者我要写书评

暂无评论

Compressive Non-Intrusive Load Monitoring 20

Compressive Non-Intrusive Load Monitoring

引用

7th Systems for Energy Efficient Buildings, Cities, and Transportation

作者： Singh, Shikha Majumdar, Angshul Makonin, Stephen Indraprastha Inst Informat Technol Delhi India Simon Fraser Univ Vancouver BC Canada

ISBN: (纸本)9781450380614

In non-intrusive load monitoring (NILM), an increase in sampling frequency translates to capturing unique signal features during transient states, which, in turn, can improve disaggregation accuracy. Smart meters are capable of sampling at a high frequency (typically 20kHz). However, transmitting signals continuously would choke the network bandwidth. Given the deployment of millions of smart meters which communicate over a wireless wide-area network (WAN), utilities can only collect power signals at very low frequencies. We propose a compressive sampling (CS) approach. After measuring the high-frequency power signal from a smart meter will be encoded (by a random matrix) to very few samples making the signal suitable for WAN transmission without choking network bandwidth. CS guarantees the recovery of the high-frequency signal from the few transmitted samples under certain conditions. This work shows how to simultaneously recover the signal and disaggregate it;hence, the name Compressive NILM.

关键词： non-intrusive load monitoring NILM energy disaggregation compressed sensing compressive sampling sparse coding

来源：评论

学校读者我要写书评

暂无评论

Neuronal Firing Rate As Code Length: a Hypothesis

引用

Computational Brain and Behavior 2020年第1期3卷 34-53页

作者： Qian, Ning Zhang, Jun Department of Neuroscience Zuckerman Institute and Department of Physiology & Cellular Biophysics Columbia University New York 10027 NY United States Department of Psychology and Department of Mathematics University of Michigan Ann Arbor 48109 MI United States

Many theories assume that a sensory neuron’s higher firing rate indicates a greater probability of its preferred stimulus. However, this contradicts (1) the adaptation phenomena where prolonged exposure to, and thus increased probability of, a stimulus reduces the firing rates of cells tuned to the stimulus;and (2) the observation that unexpected (low probability) stimuli capture attention and increase neuronal firing. Other theories posit that the brain builds predictive/efficient codes for reconstructing sensory inputs. However, they cannot explain that the brain preserves some information while discarding other. We propose that in sensory areas, projection neurons’ firing rates are proportional to optimal code length (i.e., negative log estimated probability), and their spike patterns are the code, for useful features in inputs. This hypothesis explains adaptation-induced changes of V1 orientation tuning curves and bottom-up attention. We discuss how the modern minimum-description-length (MDL) principle may help understand neural codes. Because regularity extraction is relative to a model class (defined by cells) via its optimal universal code (OUC), MDL matches the brain’s purposeful, hierarchical processing without input reconstruction. Such processing enables input compression/understanding even when model classes do not contain true models. Top-down attention modifies lower-level OUCs via feedback connections to enhance transmission of behaviorally relevant information. Although OUCs concern lossless data compression, we suggest possible extensions to lossy, prefix-free neural codes for prompt, online processing of most important aspects of stimuli while minimizing behaviorally relevant distortion. Finally, we discuss how neural networks might learn MDL’s normalized maximum likelihood (NML) distributions from input data. © 2019, Society for Mathematical Psychology.

关键词： Bayesian universal code Decoding Encoding Image statistics Rate-distortion Shannon information sparse coding

来源：评论

学校读者我要写书评

暂无评论

Model Order Reduction Using Overcomplete Damped Sinusoid Dictionary and sparse coding

Model Order Reduction Using Overcomplete Damped Sinusoid Dic...

引用

IEEE 56th International Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Fakhr, Mohamed Waleed Hanafy, Yasser Univ Bahrain Dept Elect & Elect Engn Isa Town Manama Bahrain

ISBN: (纸本)9781479900664

Model order reduction (MOR) is an approximation approach where a high order complex system is modeled by a low order parametric system. Power system transients, RLC interconnects in deep submicron technology, and large scale dynamical systems are just a few examples of MOR practical applications. In this paper, the focus is on approximating the impulse response of high order RLC-like systems. In the proposed approach an overcomplete dictionary of damped sinusoids is constructed and the sparse coding paradigm is used to find the sparsest solution to the given impulse response. Two modifications of the basic dictionary with added random atoms are used. A particle swarm optimization with constraints algorithm is employed to refine the sparse coding model, and finally, the best model is chosen adaptively. A system of order 24 is simulated and reduced models of orders 4, 6 and 8 are tested for different dictionary sizes.

关键词： Model Order Reduction Damped Sinusoid Dictionary sparse coding Compressed Sensing

来源：评论

学校读者我要写书评

暂无评论

Automatic lumen border detection in IVUS images using dictionary learning and kernel sparse representation

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2021年第0期66卷 102489-102489页

作者： Tong, Jijun Li, Kai Lin, Wenting Xia, Shudong Anwar, Ali Jiang, Lurong Zhejiang Sci Tech Univ Sch Informat Sci & Technol Hangzhou Peoples R China Zhejiang Univ Affiliated Hosp 4 Sch Med Cardiol Dept Yiwu Peoples R China

Intravascular ultrasound (IVUS) images display the cross-sectional information of the lumen, from which the diameter and length of the lumen are accurately measured to calculate the volume. More importantly, they provide the tissue information of the plaque, thus assisting the diagnosis of coronary heart disease and effective interventional therapy. In this study, a fully automatic method is presented for the detection of the lumen contours in IVUS images of the coronary artery. First, texture feature vectors are extracted from the original images with a patch size of 3 x 3. The sparse coding and kernel dictionary learning are used to employ the features to construct two dictionaries for positive and negative tissues, respectively. Then a series of preprocessing helps to reduce the impact of artifacts, calculation cost and get approximate Region of interest (ROI). A kernel-cluster algorithm based on linear discrimination method is developed to classify the pixels in the ROI. In the end, morphological operations are used to improve the detection quality. Publicly available evaluation indicators are applied to the proposed algorithm with 326 test images of different structures. Mean value of the total results (JACC: 0.87, HD: 0.35, PAD: 0.09) outperforms the other automatic methods of the participants in the challenge. Besides, compared with the recent methods used on the same dataset, the proposed method shows good performance and high accuracy. Furthermore, kernel method and preprocessing steps are effective in acquiring better detection results by reducing the influences of artifacts.

关键词： Intravascular ultrasound Lumen contours Dictionary learning Kernel method 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：