检索结果-内蒙古大学图书馆

structured sparse coding With the Group Log-regularizer for Key Frame Extraction

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1818-1830页

作者： Zhenni Li Yujie Li Benying Tan Shuxue Ding Shengli Xie the School of Automation Guangdong University of TechnologyGuangzhou 510006 the Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology(GDUT)Guangzhou 510006China the School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China the National Institute of Advanced Industrial Science and Technology TsukubaIbaraki 305-8560Japan IEEE the Key Laboratory of Intelligent Information Processing and System Integration of Io T(GDUT) Ministry of Education Guangdong Key Laboratory of IoT Information Technology(GDUT) Guangzhou 510006China

Key frame extraction based on sparse coding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a *** this paper,we propose a novel model of structured sparse-codingbased key frame extraction,wherein a nonconvex group log-regularizer is used with strong sparsity and a low reconstruction *** automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by *** rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structured sparse coefficient *** solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the l1 norm,which can be directly obtained through the proximal ***,an efficient structured sparse coding algorithm with the group log-regularizer for key frame extraction is developed,which can automatically extract a few frames directly from the video to represent the entire video with a low reconstruction *** results demonstrate that the proposed algorithm can extract more accurate key frames from most Sum Me videos compared to the stateof-the-art ***,the proposed algorithm can obtain a higher compression with a nearly 18% increase compared to sparse modeling representation selection(SMRS)and an 8% increase compared to SC-det on the VSUMM dataset.

关键词： Difference of convex algorithm(DCA) group logregularizer key frame extraction structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

structured sparse coding-Based Hyperspectral Imagery Denoising With Intracluster Filtering

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2017年第12期55卷 6860-6876页

作者： Wei, Wei Zhang, Lei Tian, Chunna Plaza, Antonio Zhang, Yanning Northwestern Polytech Univ Sch Comp Sci & Engn Shaanxi Prov Key Lab Speech & Image Informat Proc Xian 710072 Shaanxi Peoples R China Xidian Univ Sch Elect Engn Xian 710071 Shaanxi Peoples R China Univ Extremadura Escuela Politecn Dept Technol Comp & Commun Hyperspectral Comp Lab Caceres 10071 Spain

sparse coding can exploit the intrinsic sparsity of hyperspectral images (HSIs) by representing it as a group of sparse codes. This strategy has been shown to be effective for HSI denoising. However, how to effectively exploit the structural information within the sparse codes (structured sparsity) has not been widely studied. In this paper, we propose a new method for HSI denoising, which uses structured sparse coding and intracluster filtering. First, due to the high spectral correlation, the HSI is represented as a group of sparse codes by projecting each spectral signature onto a given dictionary. Then, we cast the structured sparse coding into a covariance matrix estimation problem. A latent variable-based Bayesian framework is adopted to learn the covariance matrix, the sparse codes, and the noise level simultaneously from noisy observations. Although the considered strategy is able to perform denoising through accurately reconstructing spectral signatures, an inconsistent recovery of sparse codes may corrupt the spectral similarity in each spatial homogeneous cluster within the scene. To address this issue, an intracluster filtering scheme is further employed to restore the spectral similarity in each spatial cluster, which results in better denoising results. Our experimental results, conducted using both simulated and real HSIs, demonstrate that the proposed method outperforms several state-of-the-art denoising methods.

关键词： Covariance matrix estimation hyperspectral images (HSIs) denoising intracluster filtering structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

Robust Exemplar Extraction Using structured sparse coding

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2015年第8期26卷 1816-1821页

作者： Liu, Huaping Liu, Yunhui Sun, Fuchun Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Tsinghua Natl Lab Informat Sci & Technol State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China

Robust exemplar extraction from the noisy sample set is one of the most important problems in pattern recognition. In this brief, we propose a novel approach for exemplar extraction through structured sparse learning. The new model accounts for not only the reconstruction capability and the sparsity, but also the diversity and robustness. To solve the optimization problem, we adopt the alternating directional method of multiplier technology to design an iterative algorithm. Finally, the effectiveness of the approach is demonstrated by experiments of various examples including traffic sign sequences.

关键词： Alternating directional method of multiplier (ADMM) robust exemplar extraction structured sparse coding traffic sign recognition

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL IMAGERY DENOISING USING COVARIANCE MATRIX ESTIMATION BASED structured sparse coding AND INTRA-CLUSTER FILTERING 36

HYPERSPECTRAL IMAGERY DENOISING USING COVARIANCE MATRIX ESTI...

引用

36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Zhang, Lei Wei, Wei Zhang, Yanning Wang, Cong Northwestern Polytech Univ Sch Comp Sci & Engn Xian 710072 Peoples R China

ISBN: (纸本)9781509033324

sparse coding provides an excellent image prior for hyper-spectral images (HSIs) denoising. However, on one hand, it is challenging to capture the structure within each sparse code for improving the reconstruction accuracy, on the other hand, the inconsistent recovery of the sparse codes corrupts the spectrum similarity in each homogeneous cluster of the HSI. To address these problems, we first propose a novel covariance matrix estimation based structured sparse coding method, where the sparse code matrix is modeled by a matrix normal distribution with a full covariance matrix. By estimating the covariance matrix with a latent variable based Bayesian framework, the data-dependent and noise-robust structure for each sparse code is learned from the noisy observation, with which the sparse codes are reconstructed accurately. Then, an intra-cluster filtering is employed to restore the spectrum similarity in each cluster. Experimental results demonstrate that the proposed method outperforms several state-of-the-art methods in HSIs denoising.

关键词： Covariance matrix estimation structured sparse coding Intra-cluster filtering

来源：评论

学校读者我要写书评

暂无评论

Wikifying Novel Words to Mixtures of Wikipedia Senses by structured sparse coding 2

Wikifying Novel Words to Mixtures of Wikipedia Senses by Str...

引用

2nd International Conference on Pattern Recognition Applications and Methods (ICPRAM)

作者： Pinter, Balazs Voeroes, Gyula Szabo, Zoltan Lorincz, Andras Eotvos Lorand Univ Fac Informat H-1117 Budapest Hungary UCL Gatsby Computat Neurosci Unit London WC1N 3AR England

ISBN: (纸本)9783319126104;9783319126098

We extend the scope of Wikification to novel words by relaxing two premises of Wikification: (i) we wikify without using the surface form of the word (ii) to a mixture ofWikipedia senses instead of a single sense. We identify two types of "novel" words: words where the connection between their surface form and their meaning is broken (e. g., a misspelled word), and words where there is no meaning to connect to-the meaning itself is also novel. We propose a method capable of wikifying both types of novel words while also dealing with the inherently large-scale disambiguation problem. We show that the method can disambiguate between up to 1,000 Wikipedia senses, and it can explain words with novel meaning as a mixture of other, possibly related senses. This mixture representation compares favorably to the widely used bag of words representation.

关键词： Interpreting novel words Wikification Link disambiguation Natural language processing structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

Discriminative structured dictionary learning with hierarchical group sparsity

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2015年 136卷 59-68页

作者： Xu, Yong Sun, Yuping Quan, Yuhui Zheng, Bo S China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China

Learning adaptive dictionaries for sparse coding has been the focus of latest research as it provides a promising way to maximize the efficiency of sparse representation. In particular, learning discriminative dictionaries rather than reconstructive ones has demonstrated significantly improved performance in pattern recognition. In this paper, a powerful method is proposed for discriminative dictionary learning. During the dictionary learning process, we enhance the discriminability of sparse codes by promoting hierarchical group sparsity and reducing linear prediction error on sparse codes. With the employment of joint within-class collaborative hierarchical sparsity, our method is able to learn adaptive dictionaries from labeled data for classification, which encourage coefficients to be sparse at both group level and singleton level and thus enforce the separability of sparse codes. Benefiting from joint dictionary and classifier learning, the discriminability of sparse codes is further strengthened. An efficient alternating iterative scheme is presented to solve the proposed model. We applied our method to face recognition, object recognition and scene classification. Experimental results have demonstrated the excellent performance of our method in comparison with existing discriminative dictionary learning approaches. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Discriminative dictionary learning structured sparse coding Group sparsity Image classification

来源：评论

学校读者我要写书评

暂无评论

Robotic Room-Level Localization Using Multiple Sets of Sonar Measurements

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2017年第1期66卷 2-13页

作者： Liu, Huaping Sun, Fuchun Fang, Bin Zhang, Xinyu Tsinghua Univ State Key Lab Intelligent Technol & Syst Dept Comp Sci & Technol Beijing 100084 Peoples R China Tsinghua Univ Tsinghua Natl Lab Informat Sci & Technol Dept Comp Sci & Technol Beijing 100084 Peoples R China

In this paper, we aim to achieve robust and cost-effective room-level localization for the indoor mobile robot. It is unrealistic to obtain precise localization information from the sonar sensors because of the sparseness and uncertainty. Our attempts show that the room-level localization can be achieved using sonar sensors by accumulating the sonar data to overcome the limitations of sensor performance. To this end, we formulate the room-level localization as a joint sparse coding problem, which encourages the coding vectors to share the common room sparsity, but different locations. We systematically evaluate the performance of the different coding strategies on the collected sonar measurement data set.

关键词： Indoor mobile robot multiple measurements room-level localization sonar measurements structured sparse coding

来源：评论

学校读者我要写书评

暂无评论

Small target detection in infrared video sequence using robust dictionary learning

引用

INFRARED PHYSICS & TECHNOLOGY 2015年 68卷 1-9页

作者： Yang, Chunwei Liu, Huaping Liao, Shouyi Wang, Shicheng High Tech Inst Xian Xian 710025 Shaanxi Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China TNLIST State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China

Small target detection in infrared video sequence is a challenging problem. In this paper, a collaborative structured sparse coding (SSC) model which incorporates the L-1,L-2 and L-2,L-1 regularization terms is proposed. The Alternating Direction Method of Multiplier (ADMM) is developed to solve this model. Further, online dictionary learning is embedded into the model and temporal information is incorporated to eliminate the clutters and noises. Extensive synthetic and real data experiments show that our method obtains better detection performance than baseline methods and state-of-art infrared-patch-image (IPI) model. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Small target detection structured sparse coding Robust dictionary learning Alternating direction method of multiplier

来源：评论

学校读者我要写书评

暂无评论

AN AUGMENTED LAGRANGIAN METHOD FOR PIANO TRANSCRIPTION USING EQUAL LOUDNESS THRESHOLDING AND LSTM-BASED DEcoding

AN AUGMENTED LAGRANGIAN METHOD FOR PIANO TRANSCRIPTION USING...

引用

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)

作者： Ewert, Sebastian Sandler, Mark B. Queen Mary Univ London Sch Elect Engn & Comp Sci Machine Listening Lab MLLAB London England Queen Mary Univ London Sch Elect Engn & Comp Sci Ctr Digital Mus C4DM London England

ISBN: (纸本)9781538616321

A central goal in automatic music transcription is to detect individual note events in music recordings. An important variant is instrument-dependent music transcription where methods can use calibration data for the instruments in use. However, despite the additional information, results rarely exceed an f-measure of 80%. As a potential explanation, the transcription problem can be shown to be badly conditioned and thus relies on appropriate regularization. A recently proposed method employs a mixture of simple, convex regularizers (to stabilize the parameter estimation process) and more complex terms (to encourage more meaningful structure). In this paper, we present two extensions to this method. First, we integrate a computational loudness model to better differentiate real from spurious note detections. Second, we employ (Bidirectional) Long Short Term Memory networks to re-weight the likelihood of detected note constellations. Despite their simplicity, our two extensions lead to a drop of about 35% in note error rate compared to the state-of-the-art.

关键词： Proximal Methods Alternating Directions Method of Multipliers structured sparse coding Instrument-dependent Transcription

来源：评论

学校读者我要写书评

暂无评论

Determining Unintelligible Words from their Textual Contexts

引用

Procedia - Social and Behavioral Sciences 2013年 73卷 101-108页

作者： Balázs Pintér Gyula Vörös Zsolt Palotai Zoltán Szabó András Lőrincz Eötvös Loránd University Budapest H-1117 Hungary

We propose a method to determine unintelligible words based on the textual context of the word determined. As there can be many different possibilities for the word, a robust, large-scale method is needed. The large scale makes the problem sensitive to spurious similarities of contexts: when the contexts of two, different words are similar. To reduce this effect, we induce structured sparsity on the words by formulating the task as a group Lasso problem. We compare this formulation to a k-nearest neighbor and a support vector machine based approach, and find that group Lasso outperforms both by a large margin. We achieve up to 75% of accuracy when determining the word from among 1000 words both on the Brown corpus and on the British National Corpus. Unintelligible words are often the result of errors in Optical Character Recognition (OCR) algorithms. As the proposed method utilizes information independent from information used in OCR, we expect that a combined approach could be very successful, as OCR and the proposed method complement each other.

关键词： Natural language processing structured sparse coding Word recognition Distributional hypothesis

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：