检索结果-内蒙古大学图书馆

Video-to-Shot Tag Propagation by Graph sparse Group Lasso

IEEE TRANSACTIONS ON MULTIMEDIA 2013年第3期15卷 633-646页

作者： Zhu, Xiaofeng Huang, Zi Cui, Jiangtao Shen, Heng Tao Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld Australia Xidian Univ Sch Comp Sci Xian Peoples R China

Traditional approaches to video tagging are designed to propagate tags at the same level, such as assigning the tags of training videos (or shots) to the test videos (or shots), such as generating tags for the test video when the training videos are associated with the tags at the video-level or assigning tags to the test shot when given a collection of annotated shots. This paper focuses on automatical shot tagging given a collection of videos with the tags at the video-level. In other words, we aim to assign specific tags from the training videos to the test shot. The paper solves the V2S issue by assigning the test shot with the tags deriving from parts of the tags in a part of training videos. To achieve the goal, the paper first proposes a novel Graph sparse Group Lasso (shorted for GSGL) model to linearly reconstruct the visual feature of the test shot with the visual features of the training videos, i.e., finding the correlation between the test shot and the training videos. The paper then proposes a new tagging propagation rule to assign the video-level tags to the test shot by the learnt correlations. Moreover, to effectively build the reconstruction model, the proposed GSGL simultaneously takes several constraints into account, such as the inter-group sparsity, the intra-group sparsity, the temporal-spatial prior knowledge in the training videos and the local structure of the test shot. Extensive experiments on public video datasets are conducted, which clearly demonstrate the effectiveness of the proposed method for dealing with the video-to-shot tag propagation.

关键词： Manifold learning sparse coding sparse group lasso structure sparsity video annotation video tagging

来源：评论

学校读者我要写书评

暂无评论

sparse representation of local spatial-temporal features with dimensionality reduction for motion recognition

引用

NEUROCOMPUTING 2013年 115卷 150-160页

作者： Wang, Jin Sun, Xiangping Liu, Ping She, Mary F. H. Kong, Lingxue Deakin Univ Ctr Intelligent Syst Res Waurn Ponds Vic 3216 Australia Deakin Univ Inst Frontier Mat Waurn Ponds Vic 3216 Australia Univ S Carolina Dept Comp Sci & Engn Columbia SC 29208 USA

sparse representation and compressive sensing have attracted substantial interests in computer vision. In this paper, by introducing two new classification criteria, we extended the sparse representation classification method (SRC) for individual images to classify a video that contains a group of local spatial-temporal features. A dictionary is constructed by concatenating all class-specific dictionaries, each of which is learned from a motion class. A test video is assigned to a class label based on the minimum of reconstruction errors of individual local features or overall reconstruction error. Moreover, we compared the effectiveness of the traditional Principal Component Analysis (PCA) and two compressive sensing based dimensionality reduction methods, i.e., Random Matrix projection and Hash Matrix projection in the framework of sparse representation for motion recognition. Experimental results on four public datasets including hand gesture, human facial, human action and mouse behavior demonstrate that the proposed method achieves comparable or higher recognition accuracies compared to other state-of-the-art methods in the literatures. Although the traditional PCA requires more computation to get the transformation matrix, it performs better than the Random Matrix and Hash Matrix projections using gradient features. However, when raw features (i.e., pixel values) are used, the performance of the Random Matrix and Hash Matrix projections is significantly improved. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Motion analysis sparse coding Compressive sensing Interest points

来源：评论

学校读者我要写书评

暂无评论

Spatial pooling for greyscale images

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2013年第3期4卷 207-216页

作者： Thornton, John Srbic, Andrew Griffith Univ Inst Integrated & Intelligent Syst Nathan Qld 4111 Australia Griffith Univ Sch Informat & Commun Technol Nathan Qld 4111 Australia

It is a widely held view in contemporary computational neuroscience that the brain responds to sensory input by producing sparse distributed representations. In this paper we investigate a brain-inspired spatial pooling algorithm that produces sparse distributed representations of spatial images by modelling the formation of proximal dendrites associated with neocortical minicolumns. In this approach, distributed representations are formed out of a competitive process of inter-column inhibition and subsequent learning. Specifically, we evaluate the performance of a recently proposed binary spatial pooling algorithm on a well-known benchmark of greyscale natural images. In the process, we augment the algorithm to handle greyscale images, and to produce better quality encodings of binary images. We also show that the augmented algorithm produces superior population and lifetime kurtosis measures in comparison to a number of well-known coding schemes and explain how the augmented coding scheme can be used to produce high-fidelity reconstructions of greyscale input.

关键词： Hierarchical temporal memory sparse distributed representations Spatial clustering sparse coding Self-organisation

来源：评论

学校读者我要写书评

暂无评论

Unified Dictionary Learning and Region Tagging with Hierarchical sparse Representation

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2013年第8期117卷 934-946页

作者： Cao, Xiaochun Wei, Xingxing Han, Yahong Yang, Yi Sebe, Nicu Hauptmann, Alexander Tianjin Univ Sch Comp Sci & Technol Tianjin Peoples R China Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA Univ Trent Dept Informat Engn & Comp Sci I-38100 Trento Italy Tianjin Key Lab Cognit Comp & Applicat Tianjin 300072 Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China

Image patterns at different spatial levels are well organized, such as regions within one image and feature points within one region. These classes of spatial structures are hierarchical in nature. The appropriate integration and utilization of such relationship are important to improve the performance of region tagging. Inspired by the recent advances of sparse coding methods, we propose an approach, called Unified Dictionary Learning and Region Tagging with Hierarchical sparse Representation. This approach consists of two steps: region representation and region reconstruction. In the first step, rather than using the l(1)-norm as it is commonly done in sparse coding, we add a hierarchical structure to the process of sparse coding and form a framework of tree-guided dictionary learning. In this framework, the hierarchical structures among feature points, regions, and images are encoded by forming a tree-guided multi-task learning process. With the learned dictionary, we obtain a better representation of training and testing regions. In the second step, we propose to use a sub-hierarchical structure to guide the sparse reconstruction for testing regions, i.e., the structure between regions and images. Thanks to this hierarchy, the obtained reconstruction coefficients are more discriminate. Finally, tags are propagated to testing regions by the learned reconstruction coefficients. Extensive experiments on three public benchmark image data sets demonstrate that the proposed approach has better performance of region tagging than the current state of the art methods. (c) 2013 Elsevier Inc. All rights reserved.

关键词： sparse coding Region tagging sparse reconstruction Unified hierarchical structure Tree-guided dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Image Super-Resolution via Double Sparsity Regularized Manifold Learning

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2013年第12期23卷 2022-2033页

作者： Lu, Xiaoqiang Yuan, Yuan Yan, Pingkun Chinese Acad Sci Ctr Opt Imagery Anal & Learning Xian Inst Opt & Precis Mech State Key Lab Transient Opt & Photon Xian 710119 Peoples R China

Over the past few years, high resolutions have been desirable or essential, e. g., in online video systems, and therefore, much has been done to achieve an image of higher resolution from the corresponding low-resolution ones. This procedure of recovering/rebuilding is called single-image super-resolution (SR). Performance of image SR has been significantly improved via methods of sparse coding. That is to say, the image frame patch can be sparse linear combinations of basis elements. However, most of these existing methods fail to consider the local geometrical structure in the space of the training data. To take this crucial issue into account, this paper proposes a method named double sparsity regularized manifold learning (DSRML). DSRML can preserve the properties of the aforementioned local geometrical structure by employing manifold learning, e. g., locally linear embedding. Based on a large amount of experimental results, DSRML is demonstrated to be more robust and more effective than previous efforts in the task of single-image SR.

关键词： Double sparsity manifold learning single-image super-resolution (SR) sparse coding

来源：评论

学校读者我要写书评

暂无评论

Active-Set Newton Algorithm for Overcomplete Non-Negative Representations of Audio

引用

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2013年第11期21卷 2277-2289页

作者： Virtanen, Tuomas Gemmeke, Jort Florent Raj, Bhiksha Tampere Univ Technol Dept Signal Proc Tampere 33720 Finland Katholieke Univ Leuven Ctr Proc Speech & Images Dept Elect Engn B-3000 Louvain Belgium Carnegie Mellon Univ Sch Comp Sci Language Technol Inst Pittsburgh PA 15213 USA

This paper proposes a computationally efficient algorithm for estimating the non-negative weights of linear combinations of the atoms of large-scale audio dictionaries, so that the generalized Kullback-Leibler divergence between an audio observation and the model is minimized. This linear model has been found useful in many audio signal processing tasks, but the existing algorithms are computationally slow when a large number of atoms is used. The proposed algorithm is based on iteratively updating a set of active atoms, with the weights updated using the Newton method and the step size estimated such that the weights remain non-negative. Algorithm convergence evaluations on representing audio spectra that are mixtures of two speakers show that with all the tested dictionary sizes the proposed method reaches a much lower value of the divergence than can be obtained by conventional algorithms, and is up to 8 times faster. A source separation evaluation revealed that when using large dictionaries, the proposed method produces a better separation quality in less time.

关键词： Acoustic signal analysis audio source separation convex optimization Newton algorithm non-negative matrix factorization sparse coding sparse representation supervised source separation

来源：评论

学校读者我要写书评

暂无评论

Automatic Collecting Representative Logo Images from the Internet

引用

Tsinghua Science and Technology 2013年第6期18卷 606-617页

作者： Xiaobing Liu Bo Zhang State Key Laboratory for Intelligent Technology and System Tsinghua National Laboratory for Information Science and Technology(TNList)Department of Computer Science and TechnologyTsinghua University

With the explosive growth of commercial Iogos, high quality logo images are needed for training logo detection or recognition systems, especially for famous Iogos or new commercial brands. This paper focuses on automatic collecting representative logo images from the internet without any human labeling or seed images. We propose multiple dictionary invariant sparse coding to solve this problem. This work can automatically provide prototypes, representative images, or weak labeled training images for logo detection, logo recognition, trademark infringement detection, brand protection, and ad-targeting. The experiment results show that our method increases the mean average precision for 25 types of Iogos to 80.07% whereas the original search engine results only have 32% representative logo images. The top images collected by our method are accurate and reliable enough for practical applications in the future.

关键词： logo image sparse coding scale invariant shift invariant multiple dictionary

来源：评论

学校读者我要写书评

暂无评论

Learning dictionary on manifolds for image classification

引用

PATTERN RECOGNITION 2013年第7期46卷 1879-1890页

作者： Liu, Bao-Di Wang, Yu-Xiong Zhang, Yu-Jin Shen, Bin Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

At present, dictionary based models have been widely used in image classification. The image features are approximated as a linear combination of bases selected from the dictionary in a sparse space, resulting in compact patterns. The features applied to image classification usually reside on low dimensional manifolds embedded in a high dimensional ambient space;traditional sparse coding algorithm, however, does not consider this topological structure. It can be characterized naturally by linear coefficients that reconstruct each data point from its neighbors. One of the central issues here is how to determine the neighbors and learn the coefficients. In this paper, the geometrical structures are encoded in two situations. In simple cases when data points distribute on a single manifold, it is explicitly modeled by locally linear embedding algorithm combined with k-nearest neighbors. Nevertheless, in real-world scenarios, complex data points often lie on multiple manifolds. sparse representation algorithm combined with k-nearest neighbors is instead utilized to construct the topological structures, because it is capable of approximating the data point by selecting its homogenous neighbors adaptively to guarantee the smoothness of each manifold. After obtaining the local fitting relationship, these two topological structures are then embedded into sparse coding algorithm as regularization terms to formulate the corresponding objective functions of dictionary learning on single manifold (DLSM) and dictionary learning on multiple manifolds (DLMM), respectively. Upon this, a coordinate descent scheme is proposed to solve the unified optimization problems. Experimental results on several benchmark data sets, such as Caltech-256, Caltech-101, Scene 15, and UIUC-Sports, show that our proposed algorithms equal or outperform other state-of-the-art image classification algorithms. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： sparse coding Image classification Locally linear embedding Coordinate descent Manifold

来源：评论

学校读者我要写书评

暂无评论

Applying alternating direction method of multipliers for constrained dictionary learning

引用

NEUROCOMPUTING 2013年 106卷 126-136页

作者： Rakotomamonjy, A. Univ Rouen LITIS EA4108 F-76800 St Etienne France

This paper revisits the problem of dictionary learning on several points although we still consider an alternating optimization scheme. Our first contribution consists in providing a simple proof of convergence for this numerical scheme for a large class of constraints and regularizers on the dictionary atoms. We also investigate the use of a well-known optimization method named alternating direction method of multipliers for solving each of the alternate step of the dictionary learning problem. We show that such an algorithm yields to several benefits. Indeed, it can be more efficient than other competing algorithms such as Iterative Shrinkage Thresholding approach and besides, it allows one to easily deal with mixed constraints or regularizers over the dictionary atoms or approximation coefficients. For instance, we have induced joint sparsity, positivity and smoothness on the dictionary atoms by means of some total variation and sparsity-inducing regularizers. Our experimental results prove that using these mixed constraints helps in achieving better learned dictionary elements especially when learning from noisy signals. (c) 2012 Elsevier B.V. All rights reserved.

关键词： Dictionary learning sparse coding Alternate direction method of multipliers Mixed constraints

来源：评论

学校读者我要写书评

暂无评论

Online Non-Negative Convolutive Pattern Learning for Speech Signals

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2013年第1期61卷 44-56页

作者： Wang, Dong Vipperla, Ravichander Evans, Nicholas Zheng, Thomas Fang Tsinghua Univ Beijing 100084 Peoples R China EURECOM F-06560 Sophia Antipolis France

The unsupervised learning of spectro-temporal patterns within speech signals is of interest in a broad range of applications. Where patterns are non-negative and convolutive in nature, relevant learning algorithms include convolutive non-negative matrix factorization (CNMF) and its sparse alternative, convolutive non-negative sparse coding (CNSC). Both algorithms, however, place unrealistic demands on computing power and memory which prohibit their application in large scale tasks. This paper proposes a new online implementation of CNMF and CNSC which processes input data piece-by-piece and updates learned patterns gradually with accumulated statistics. The proposed approach facilitates pattern learning with huge volumes of training data that are beyond the capability of existing alternatives. We show that, with unlimited data and computing resources, the new online learning algorithm almost surely converges to a local minimum of the objective cost function. In more realistic situations, where the amount of data is large and computing power is limited, online learning tends to obtain lower empirical cost than conventional batch learning.

关键词： Non-negative matrix factorization convolutive NMF online pattern learning sparse coding speech processing speech recognition

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：