检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Li, Xuelong Lu, Quanmao Dong, Yongsheng Tao, Dacheng Fellow IEEE IEEE State Key Laboratory of Transient Optics and Photonics Xi’an Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi’an710119 China State Key Laboratory of Transient Optics and Photonics Xi’an Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi’an710119 China University of Chinese Academy of Sciences Beijing100049 China Center for Optical Imagery Analysis and Learning State Key Laboratory of Transient Optics and Photonics Xian Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xian710119 China Information Engineering College Henan University of Science and Technology Luoyang471023 China UBTech Sydney Artificial Intelligence Institute School of Information Technologies in Faculty of Engineering and Information Technologies University of Sydney J12/318 Cleveland St DarlingtonNSW2008 Australia

Cluster analysis plays a very important role in data analysis. In these years, cluster ensemble, as a cluster analysis tool, has drawn much attention for its robustness, stability and accuracy. Many efforts have been done to combine different initial clustering results into a single clustering solution with better performance. However, they neglect the structure information of the raw data in performing the cluster ensemble. In this paper, we propose a Structural Cluster Ensemble (SCE) algorithm for data partitioning formulated as a set-covering problem. In particular, we construct a Laplacian regularized objective function to capture the structure information among clusters. Moreover, considering the importance of the discriminative information underlying in the initial clustering results, we add a discriminative constraint into our proposed objective function. Finally, we verify the performance of the SCE algorithm on both synthetic and real data sets. The experimental results show the effectiveness of our proposed SCE algorithm. Copyright © 2019, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Manifold Adaptive Kernelized Low-Rank Representation for Semisupervised Image Classification”

引用

Complexity 2018年第1期2018卷

作者： Yong Peng Wanzeng Kong Feiwei Qin Feiping Nie School of Computer Science Hangzhou Dianzi University Hangzhou 310018 *** Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing 210023 *** Center for OPTical IMagery Analysis and Learning (OPTIMAL) Northwestern Polytechnical University Xi’an 710072 ***

来源：评论

学校读者我要写书评

暂无评论

Avoiding optimal mean robust PCA/2DPCA with non-greedy 1-norm maximization 25

Avoiding optimal mean robust PCA/2DPCA with non-greedy 1-nor...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Luo, Minnan Nie, Feiping Chang, Xiaojun Yang, Yi Hauptmann, Alexander Zheng, Qinghua Shaanxi Province Key Lab of Satellite-Terrestrial Network Department of Computer Science Xi'An Jiaotong University China School of Computer Science Center for Optical Imagery Analysis and Learning Northwestern Polytechnical University China Centre for Quantum Computation and Intelligent Systems University of Technology Sydney Australia School of Computer Science Carnegie Mellon University PA United States

Robust principal component analysis (PCA) is one of the most important dimension reduction techniques to handle high-dimensional data with outliers. However, the existing robust PCA presupposes that the mean of the data is zero and incorrectly utilizes the Euclidean distance based optimal mean for robust PCA with 1-norm. Some studies consider this issue and integrate the estimation of the optimal mean into the dimension reduction objective, which leads to expensive computation. In this paper, we equivalently reformulate the maximization of variances for robust PCA, such that the optimal projection directions are learned by maximizing the sum of the projected difference between each pair of instances, rather than the difference between each instance and the mean of the data. Based on this reformulation, we propose a novel robust PCA to automatically avoid the calculation of the optimal mean based on 1-norm distance. This strategy also makes the assumption of centered data unnecessary. Additionally, we intuitively extend the proposed robust PCA to its 2D version for image recognition. Efficient non-greedy algorithms are exploited to solve the proposed robust PCA and 2D robust PCA with fast convergence and low computational complexity. Some experimental results on benchmark data sets demonstrate the effectiveness and superiority of the proposed approaches on image reconstruction and recognition.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Object discovery via cohesion measurement

arXiv

引用

arXiv 2017年

作者： Guo, Guanjun Wang, Hanzi Zhao, Wan-Lei Yan, Yan Li, Xuelong Fujian Key Laboratory of Sensing and Computing for Smart City School of Information Science and Engineering Xiamen University Xiamen Fujian361005 China Center for Optical Imagery Analysis and Learning State Key Laboratory of Transient Optics and Photonics Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi710119 China

Color and intensity are two important components in an image. Usually, groups of image pixels, which are similar in color or intensity, are an informative representation for an object. They are therefore particularly suitable for computer vision tasks, such as saliency detection and object proposal generation. However, image pixels, which share a similar real-world color, may be quite different since colors are often distorted by intensity. In this paper, we reinvestigate the affinity matrices originally used in image segmentation methods based on spectral clustering. A new affinity matrix, which is robust to color distortions, is formulated for object discovery. Moreover, a Cohesion Measurement (CM) for object regions is also derived based on the formulated affinity matrix. Based on the new Cohesion Measurement, a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix. Then we apply the proposed method to both saliency detection and object proposal generation. Experimental results on several evaluation benchmarks demonstrate that the proposed CM based method has achieved promising performance for these two tasks. Copyright © 2017, The Authors. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

On the effectiveness of least squares generative adversarial networks

arXiv

引用

arXiv 2017年

作者： Mao, Xudong Li, Qing Xie, Haoran Lau, Raymond Y.K. Wang, Zhen Smolley, Stephen Paul Department of Computer Science City University of Hong Kong Hong Kong Department of Mathematics and Information Technology Education University of Hong Kong Hong Kong Department of Information Systems City University of Hong Kong Hong Kong Center for Optical Imagery Analysis and Learning School of Mechanical Engineering Northwestern Polytechnical University Xian710072 China CodeHatch Corp. EdmontonAB Canada

Unsupervised learning with generative adversarial networks (GANs) has proven to be hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss for both the discriminator and the generator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson χ2divergence. We also show that the derived objective function that yields minimizing the Pearson χ2divergence performs better than the classical one of using least squares for classification. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stably during the learning process. For evaluating the image quality, we conduct both qualitative and quantitative experiments, and the experimental results show that LSGANs can generate higher quality images than regular GANs. Furthermore, we evaluate the stability of LSGANs in two groups. One is to compare between LSGANs and regular GANs without gradient penalty. We conduct three experiments, including Gaussian mixture distribution, difficult architectures, and a newly proposed method - datasets with small variability, to illustrate the stability of LSGANs. The other one is to compare between LSGANs with gradient penalty (LSGANs-GP) and WGANs with gradient penalty (WGANs-GP). The experimental results show that LSGANs-GP succeed in training for all the difficult architectures used in WGANs-GP, including 101-layer ResNet. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Temporal Multimodal learning in Audiovisual Speech Recognition

Temporal Multimodal Learning in Audiovisual Speech Recogniti...

引用

IEEE Conference on computer Vision and Pattern Recognition

作者： Di Hu Xuelong Li Xiaoqiang Lu School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL) Northwestern Polytechnical University Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences

ISBN: (纸本)9781467388528

In view of the advantages of deep networks in producing useful representation, the generated features of different modality data (such as image, audio) can be jointly learned using Multimodal Restricted Boltzmann Machines (MRB-M). Recently, audiovisual speech recognition based the M-RBM has attracted much attention, and the MRBM shows its effectiveness in learning the joint representation across audiovisual modalities. However, the built networks have weakness in modeling the multimodal sequence which is the natural property of speech signal. In this paper, we will introduce a novel temporal multimodal deep learning architecture, named as Recurrent Temporal Multimodal RB-M (RTMRBM), that models multimodal sequences by transforming the sequence of connected MRBMs into a probabilistic series model. Compared with existing multimodal networks, it's simple and efficient in learning temporal joint representation. We evaluate our model on audiovisual speech datasets, two public (AVLetters and AVLetters2) and one self-build. The experimental results demonstrate that our approach can obviously improve the accuracy of recognition compared with standard MRBM and the temporal model based on conditional RBM. In addition, RTMRBM still outperforms non-temporal multimodal deep networks in the presence of the weakness of long-term dependencies.

关键词： Audiovisuals Speech recognition Hypodynamia serial mode Voice Signal

来源：评论

学校读者我要写书评

暂无评论

DESI Strong Lens Foundry I: HST Observations and Modeling with GIGA-Lens

arXiv

引用

arXiv 2025年

作者： Huang, X. Baltasar, S. Ratier-Werbin, N. Storfer, C. Sheu, W. Agarwal, S. Tamargo-Arizmendi, M. Schlegel, D.J. Aguilar, J. Ahlen, S. Aldering, G. Banka, S. BenZvi, S. Bianchi, D. Bolton, A. Brooks, D. Cikota, A. Claybaugh, T. de la Macorra, A. Dey, A. Doel, P. Edelstein, J. Filipp, A. Forero-Romero, J.E. Gaztañaga, E. Gontcho, S.A. Gontcho Gu, A. Gutierrez, G. Honscheid, K. Jullo, E. Juneau, S. Kehoe, R. Kirkby, D. Kisner, T. Kremin, A. Kwon, K.J. Lambert, A. Landriau, M. Lang, D. Le Guillou, L. Liu, J. Meisner, A. Miquel, R. Moustakas, J. Myers, A.D. Perlmutter, S. Pérez-Ràfols, I. Prada, F. Rossi, G. Rubin, D. Sanchez, E. Schubnell, M. Shu, Y. Silver, E. Sprayberry, D. Suzuki, N. Tarlé, G. Weaver, B.A. Zou, H. Department of Physics & Astronomy University of San Francisco San FranciscoCA94117 United States Physics Division Lawrence Berkeley National Laboratory 1 Cyclotron Road BerkeleyCA94720 United States Department of Physics Complutense University of Madrid Madrid28040 Spain Department of Mathematics Complutense University of Madrid Madrid28040 Spain Institute for Astronomy University of Hawai’i HonoluluHI96822-1897 United States Department of Physics & Astronomy University of California Los Angeles Los AngelesCA90095 United States University of Chicago Department of Astronomy ChicagoIL60615 United States Department of Physics & Astronomy University of Pittsburgh PittsburghPA15260 United States Physics Dept. Boston University 590 Commonwealth Avenue BostonMA02215 United States Department of Electrical Engineering & Computer Sciences University of California Berkeley BerkeleyCA94720 United States Department of Physics & Astronomy University of Rochester 206 Bausch and Lomb Hall P.O. Box 270171 RochesterNY14627-0171 United States Dipartimento di Fisica "Aldo Pontremoli" Università degli Studi di Milano Via Celoria 16 MilanoI-20133 Italy NSF’s National Optical-Infrared Astronomy Research Laboratory TucsonAZ85719 United States Department of Physics & Astronomy University College London Gower Street LondonWC1E 6BT United Kingdom Gemini Observatory NSF’s NOIRLab Casilla 603 La Serena Chile Instituto de Física Universidad Nacional Autónoma de México Circuito de la Investigación Científica Ciudad Universitaria Cd. de MéxicoC. P. 04510 Mexico Space Sciences Laboratory University of California Berkeley 7 Gauss Way BerkeleyCA94720 United States Université de Montréal Physics Department 1375 Av. Thérèse-Lavoie-Roux MontréalQCH2V 0B3 Canada Ciela – Montreal Institute for Astrophysical Data Analysis and Machine Learning 1375 Av. Thérèse-Lavoie-Roux MontréalQCH2V 0B3 Canada Technical University Munich TUM School of Natural Sciences

We present the Dark Energy Spectroscopic Instrument (DESI) Strong Lens Foundry. We discovered ∼ 3500 new strong gravitational lens candidates in the DESI Legacy Imaging Surveys using residual neural networks (ResNet). We observed a subset (51) of our candidates using the Hubble Space Telescope (HST). All of them were confirmed to be strong lenses. We also briefly describe spectroscopic follow-up observations by DESI and Keck NIRES programs. From this very rich dataset, a number of studies will be carried out, including evaluating the quality of the ResNet search candidates and lens modeling. In this paper, we present our initial effort in these directions. In particular, as a demonstration, we present the lens model for DESI-165.4754-06.0423, with imaging data from HST, and lens and source redshifts from DESI and Keck NIRES, respectively. In this effort, we have applied a fully forward-modeling Bayesian approach (GIGA-Lens), using multiple GPUs, for the first time in both regards, to a strong lens with HST data, or any high resolution imaging. © 2025, CC BY.

关键词： Dark energy

来源：评论

学校读者我要写书评

暂无评论

Spatiochromatic Context Modeling for Color Saliency analysis

引用

IEEE Transactions on Neural Networks and learning Systems 2016年第6期27卷 1177-1189页

作者： Zhang, Jun Wang, Meng Zhang, Shengping Li, Xuelong Wu, Xindong School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of Computer Science and Technology Harbin Institute of Technology Weihai264209 China State Key Laboratory of Transient Optics and Photonics Center for Optical Imagery Analysis and Learning Xi'An Institute of Optics and Precision Mechanics Xi'an710119 China Department of Computer Science University of Vermont BurlingtonVT05405 United States

Visual saliency is one of the most noteworthy perceptual abilities of human vision. Recent progress in cognitive psychology suggests that: 1) visual saliency analysis is mainly completed by the bottom-up mechanism consisting of feedforward low-level processing in primary visual cortex (area V1) and 2) color interacts with spatial cues and is influenced by the neighborhood context, and thus it plays an important role in a visual saliency analysis. From a computational perspective, the most existing saliency modeling approaches exploit multiple independent visual cues, irrespective of their interactions (or are not computed explicitly), and ignore contextual influences induced by neighboring colors. In addition, the use of color is often underestimated in the visual saliency analysis. In this paper, we propose a simple yet effective color saliency model that considers color as the only visual cue and mimics the color processing in V1. Our approach uses region-/boundary-defined color features with spatiochromatic filtering by considering local color-orientation interactions, therefore captures homogeneous color elements, subtle textures within the object and the overall salient object from the color image. To account for color contextual influences, we present a divisive normalization method for chromatic stimuli through the pooling of contrary/complementary color units. We further define a color perceptual metric over the entire scene to produce saliency maps for color regions and color boundaries individually. These maps are finally globally integrated into a one single saliency map. The final saliency map is produced by Gaussian blurring for robustness. We evaluate the proposed method on both synthetic stimuli and several benchmark saliency data sets from the visual saliency analysis to salient object detection. The experimental results demonstrate that the use of color as a unique visual cue achieves competitive results on par with or better than 12 state-of-the-ar

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Statistical physics of human cooperation

arXiv

引用

arXiv 2017年

作者： Perc, Matjaž Jordan, Jillian J. Rand, David G. Wang, Zhen Boccaletti, Stefano Szolnoki, Attila Faculty of Natural Sciences and Mathematics University of Maribor Koroška cesta 160 MariborSI-2000 Slovenia CAMTP – Center for Applied Mathematics and Theoretical Physics University of Maribor Mladinska 3 MariborSI-2000 Slovenia Department of Psychology Yale University New HavenCT06511 United States Department of Economics Yale University New HavenCT06511 United States School of Management Yale University New HavenCT06511 United States Center for Optical Imagery Analysis and Learning Northwestern Polytechnical University Xi’an710072 China CNR Institute of Complex Systems Via Madonna del Piano 10 Sesto Fiorentino Florence50019 Italy Italian Embassy in Israel 25 Hamered st. Tel Aviv68125 Israel Institute of Technical Physics and Materials Science Centre for Energy Research Hungarian Academy of Sciences P.O. Box 49 BudapestH-1525 Hungary

Extensive cooperation among unrelated individuals is unique to humans, who often sacrifice personal benefits for the common good and work together to achieve what they are unable to execute alone. The evolutionary success of our species is indeed due, to a large degree, to our unparalleled other-regarding abilities. Yet, a comprehensive understanding of human cooperation remains a formidable challenge. Recent research in social science indicates that it is important to focus on the collective behavior that emerges as the result of the interactions among individuals, groups, and even societies. Non-equilibrium statistical physics, in particular Monte Carlo methods and the theory of collective behavior of interacting particles near phase transition points, has proven to be very valuable for understanding counterintuitive evolutionary outcomes. By studying models of human cooperation as classical spin models, a physicist can draw on familiar settings from statistical physics. However, unlike pairwise interactions among particles that typically govern solid-state physics systems, interactions among humans often involve group interactions, and they also involve a larger number of possible states even for the most simplified description of reality. The complexity of solutions therefore often surpasses that observed in physical systems. Here we review experimental and theoretical research that advances our understanding of human cooperation, focusing on spatial pattern formation, on the spatiotemporal dynamics of observed solutions, and on self-organization that may either promote or hinder socially favorable states. Copyright © 2017, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Hierarchical CNN for traffic sign recognition

Hierarchical CNN for traffic sign recognition

引用

IEEE Symposium on Intelligent Vehicle

作者： Xuehong Mao Samer Hijazi Raúl Casas Piyush Kaul Rishi Kumar Chris Rowen Faculty of Electrical and Computer Engineering United States Naval Academy Annapolis MD USA School of Electronic Engineering Xidian University Xi’an China School of Computer and Information Science Hubei Engineering University Xiaogan China Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street Ultimo NSW Australia Center for Optical Imagery Analysis and Learning (OPTIMAL) State Key Laboratory of Transient Optics and Photonics Xi’an Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi’an Shaanxi China

ISBN: (纸本)9781509018222

The Convolutional Neural Network (CNN) is a breakthrough technique in object classification and pattern recognition. It has enabled computers to achieve performance superior to humans in specialized image recognition tasks. Prior art CNNs learn object features by stacking multiple convolutional/non-linear layers in sequence on top of a classifier. In this work, we propose a Hierarchical CNN (HCNN) which is inspired by a coarse-to-fine human learning methodology. For a given dataset, we introduce a CNN-oriented clustering algorithm to separate classes into K subsets, which are referred to as families. Then, the HCNN algorithm trains K+1 classification CNNs: one CNN for family classification and K dedicated CNNs corresponding to each family for member classification. We evaluate this HCNN approach on the German Traffic Sign Recognition Benchmark (GTSRB), and achieve 99.67% correct detection rate (CDR), which is superior to the best reported results (99.46%) achieved by a single network.

关键词： Clustering algorithms Training Classification algorithms Measurement Partitioning algorithms Standards Neural networks

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：