检索结果-内蒙古大学图书馆

11th ACM International Conference on Web Search and Data Mining

作者： Qian, Yuqiu Tan, Conghui Mamoulis, Nikos Cheung, David W. Univ Hong Kong Hong Kong Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Univ Ioannina Ioannina Greece

ISBN: (纸本)9781450355810

Nonnegative matrix factorization (NMF) has been successfully applied in different fields, such as text mining, image processing, and video analysis. NMF is the problem of determining two non-negative low rank matrices U and V, for a given input matrix M, such that M approximate to UVT. There is an increasing interest in parallel and distributed NMF algorithms, due to the high cost of centralized NMF on large matrices. In this paper, we propose a distributed sketched alternating nonnegative least squares (DSANLS) framework for NMF, which utilizes a matrix sketching technique to reduce the size of nonnegative least squares subproblems in each iteration for U and V. We design and analyze two different random matrix generation techniques and two subproblem solvers. Our theoretical analysis shows that DSANLS converges to the stationary point of the original NMF problem and it greatly reduces the computational cost in each subproblem as well as the communication cost within the cluster. DSANLS is implemented using MPI for communication, and tested on both dense and sparse real datasets. The results demonstrate the efficiency and scalability of our framework, compared to the state-of-art distributed NMF MPI implementation.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DnM3Net: Multi-Scale & Multi-Level Shuffle-CNN Via Multi-Level Attention for image Denoising

DnM3Net: Multi-Scale & Multi-Level Shuffle-CNN Via Multi-Lev...

引用

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yue Cao Jinhe He Yu Zhang Gang Lu Shigang Liu Xiaojun Wu School of Computer Science Shaanxi Normal University Xian Shaanxi Normal University Xi'an China

ISBN: (纸本)9781728152103

Recently, based on novel convolutional neural net-work architectures proposed, tremendous advances have been achieved in image denoising task. An effective and efficient multi-level network architecture for image denoising refers to restore the latent clean image from a coarser scale to finer scales and pass features through multiple levels of the model. Unfortunately, the bottleneck of applying multi-level network architecture lies in the multi-scale information from input images is not effectively captured and the fine-to-coarse feature fusion strategy to be ignored in image denoising task. To solve these problems, we propose a multi-scale & multi-level shuffle-CNN Via multi-level attention (DnM3Net), which plugs the multi-scale feature extraction, fine-to-coarse feature fusion strategy and multi-level attention module into the new network architecture in image denoising task. The advantage of this approach are two-fold: (1) It solve the multi-scale information extraction issue of multi-level network architecture, making it more effective and efficient for the image denoising task. (2) It is impressive performance because the better trade-off between denoising and detail preservation. The proposed novel network architecture is validated by applying on synthetic gaussian noise gray and RGB images. Experimental results show that the DnM3Net effectively improve the quantitative metrics and visual quality compared to the state-of-the-art denoising methods.

关键词： convolutional neural nets feature extraction Gaussian noise image colour analysis image denoising image sampling image denoising image samples image colour analysis NETWORK STRUCTURE Gaussian noise Feature extraction multi-scale hierarchical models Noise reduction

来源：评论

学校读者我要写书评

暂无评论

Siamese Network for Visual Tracking via Focal Loss

Siamese Network for Visual Tracking via Focal Loss

引用

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Shan Jiang Cheng Han Xiaoqiang Di Hua Li School of Computer Science and Technology ChangChun Unviersity of Science and Technology Changchun China

ISBN: (纸本)9781728152103

Visual tracking is a fundamental problem in computer vision. Lots efforts have been made in the past decades and researchers have obtained some achievements, but there are still problems exist. To get a more powerful feature representation, deep learning based methods appear layer upon layer, and most of them achieve good performance at the price of losing speed. In this paper, we propose a SiamFL network for visual tracking, which introduce the focal loss with the Siamese network. With the focal loss, the network is capable of filtering out the easy examples, leaving the hard samples to train a discriminative network. Moreover, the SiamFL network also can alleviate the class imbalance problem by properly sampling the positive and negative samples at a certain ratio. Experimental results demonstrate the SimaFL has quick convergence and also have a better performance over the baseline tracker.

关键词： computer vision image representation learning (artificial intelligence) visual tracking image representation images computer vision siamese Balance impairment Network

来源：评论

学校读者我要写书评

暂无评论

Multiple License Plate Location Algorithm in Complex Scene

Multiple License Plate Location Algorithm in Complex Scene

引用

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： YuMei Zhou MeiNi Lv ZiQing Ling DongLing Li School of Electrical and Eletronic Engineering TianHe College of GuangDong Polytechnic Normal University GuangZhou China School of Eletronic and Information Engineering WuZhou University WuZhou China

ISBN: (纸本)9781728152103

Aiming at the problem that the existing license plate location methods can't work well in locating the license plate in certain natural scenes such as low luminance, low resolution and inclination scene of vehicle, a license plate location method based on cascade classifier and convolution neural network is proposed. Firstly, the cascade classifier is used for license plate coarse location, and the convolution neural network is used for license plate precise location. Experiments show that, compared with cascade classifier, the method in this paper has higher accuracy and recall rate for target license plate location, and the method in this paper has strong adaptability to different environments.

关键词： character recognition convolutional neural nets edge detection feature extraction image colour analysis object detection traffic engineering computing License plates image colour analysis Character recognition Object detection Edge detection Feature extraction engineering computing cascades Retrieval recall

来源：评论

学校读者我要写书评

暂无评论

Enhanced Knowledge Distillation for Face Recognition

Enhanced Knowledge Distillation for Face Recognition

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Hao Ni Jie Shen Chong Yuan Yingcai Honors College University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Face recognition have been widely used in different industries due to the advancement of deep convolutional neural networks. Although deep learning has greatly promoted the development of face recognition technology, its computing-intensive and memory-intensive features make it difficult to deploy the model on some embedded devices or mobile computing platforms. Many solutions which include Knowledge Distillation have been proposed to increase the calculation speed of model and reduce the storage space required for calculations, in this paper, we propose a novel Two Stage Knowledge Distillation which enhances the performance of knowledge distillation in face recognition and low resolution face recognition. After experimenting on the several major face datasets, our method turns out to have better results compared to the traditional optimization methods.

关键词： Face recognition Knowledge engineering Face Adaptation models image resolution Neural networks Computational modeling

来源：评论

学校读者我要写书评

暂无评论

An Integrative Approach to Robust Hand Detection Using CPM-YOLOv3 and RGBD Camera in Real Time

An Integrative Approach to Robust Hand Detection Using CPM-Y...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Muhammad Raza Vachiraporn Ketsoi Haopeng Chen School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Innovative methods to interact with electronic devices are attracting researchers attentions, and many applications of Human Computer Interaction have been developed in recent years. Hand detection under different illuminations and backgrounds is crucial for tasks such as, actions recognition, gestures recognition and hand-based interaction with wearable devices. Many existing methods are able to detect the human hand precisely, but the task still remains challenging due to environment complexity, different invariants, processing time, and accuracy. It is required for an application to recognize the human hand precisely for proper interaction with the wearable devices. This paper proposed a robust and a compact method for hand detection by employing you only look once (YOLO) and convolutional pos machines (CPM). This paper consists of two parts, network training and testing. In the first part, Oxford hand dataset is used to train a neural network. This dataset has various hand images under different invariants, and backgrounds. Afterwards, images are captured using a digital camera in real-time and then human hands are detected using a trained neural network. In addition, detected hands, positions and orientations are calculated accordance with defined active zone parameters and a depth sensor. Our trained neural network is dubbed as HHDNet, an abbreviation for human hand detection network. The HHDNet is tested under different environment conditions, and experimental results showed that the accuracy and the frame rate of the proposed model are superior than others state of the art methods.

关键词： image color analysis Neural networks Feature extraction Cameras Robot sensing systems Estimation Skin

来源：评论

学校读者我要写书评

暂无评论

The Challenge of a Strong Speed-Up of a Bio-Medical Big Data Application

The Challenge of a Strong Speed-Up of a Bio-Medical Big Data...

引用

IEEE International Conference on Big Data (Big Data)

作者： Strutz, Marco Lindequist, Bjoern Hessling, Hermann Streit, Achim Univ Appl Sci HTW Berlin Wilhelminenhofstr 75A D-12459 Berlin Germany KIT SCC Hermann von Helmholtz Pl 1 D-76344 Eggenstein Leopoldshafen Germany

ISBN: (纸本)9781538650356

Digital data of patients can aid a pathologist along the diagnostic process In Medical devices generate data sets that are processed by specialized computing applications, which often run on a single computer. The resolution power of the devices is increasing steadily and, consequently, the volumes of the data sets are also growing and can no longer be analyzed in a reasonable amount of time. Big Data tools like Apache Spark [2] provide methods for analyzing data, however, they are not directly applicable and need considerable implementation efforts, in general. Usually, well established analysis tools for medical data are designed to run on single workstations. These tools are not designed to meet current and future challenges. Migrating processing tools from single nodes to distributed environments is nontrivial. Moreover, partitioning data sets for a parallel processing is a further challenge [3]. In this work, we continue our efforts for improving the speedup of a bio-medical big data application further by partitioning the images of a Whole Slide image (WSI) [4] into sub tiles and by analyzing these sub tiles on a cluster of computer nodes. The idea is to benefit from the divide and conquer strategy. However, it is shown that the score parameter is determined incorrectly, when the software package is applied to each sub tile and the score parameters of all sub tiles are combined in an apparently natural manner. The cause of this anomaly is determined and a solution suggested. The original software is based on implicit assumptions. For example, the size of the tiles is assumed to be 1024 x 1024 px(2). The anomaly shows up when this constraint is reduced.

关键词： Runtime Tumors Tools Big Data Medical diagnostic imaging parallel processing

来源：评论

学校读者我要写书评

暂无评论

An identification framework for print-scan books in a large database

引用

INFORMATION SCIENCES 2017年 396卷 33-54页

作者： Lee, Sang-Hoon Kim, Jongyoo Lee, Sanghoon Yonsei Univ Dept Elect & Elect Engn Seoul 120749 South Korea

In this paper, we propose an identification framework to determine copyright infringement in the form of illegally distributed print-scan books in a large database. The framework contains following main stages: image pre-processing, feature vector extraction, clustering, and indexing, and hierarchical search. The image pre-processing stage provides methods for alleviating the distortions induced by a scanner or digital camera. From the preprocessed image, we propose to generate feature vectors that are robust against distortion. To enhance the clustering performance in a large database, we use a clustering method based on the parallel-distributed computing of Hadobp MapReduce. In addition, to store the clustered feature vectors efficiently and minimize the searching time, we investigate an inverted index for fedture vectors. Finally, we implement a two-step hierarchical search to achieve fast and accurate on-line identification. In a simulation, the proposed identification framework shows accurate and robust in the presence of print-scan distortions. The processing time analysis in a parallel computing environment gives extensibility of the proposed framework to massive data. In the matching performance analysis, we empirically and theoretically find that in terms of query time, the optimal number of clusters scales with O(root N) for N print-scan books. (C) 2017 Elsevier Inc. All rights reserved.

关键词： image identification image databases parallel databases MapReduce Inverted index Hierarchical search

来源：评论

学校读者我要写书评

暂无评论

Stacked Sparse Auto-Encoder for Deep Clustering

Stacked Sparse Auto-Encoder for Deep Clustering

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Jinyu Cai Shiping Wang Wenzhong Guo College of Mathematics and Computer Science Fuzhou university Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Deep clustering attempts to capture the feature representation that benefits the clustering issue for inputs. Although the existing deep clustering methods have achieved encouraging performance in many research fields, there still presents some shortcomings, such as the lack of consideration of local structure preservation and sparse characteristics of input data. To this end, we propose the deep-stacked sparse embedded clustering method in this paper, which considers both the preservation of local structure and sparse property of inputs. The proposed network is trained to capture the feature representation for input data by the guidance of clustering loss and reconstruction loss, where the reconstruction loss prevents the corruption of feature space and guarantees the local structure preservation. Besides, some sparse parameters are added to the encoder to avoid learning of meaningless features. Through simultaneously minimizing the reconstruction loss and cluster loss, the proposed network can jointly learn the clustering oriented feature and optimize the assignment of cluster labels. Then we conduct amounts of comparative experiments, which consist of six clustering methods and four publicly available data sets. Eventually, the clustering accuracy, adjusted rand index and normalized mutual information are utilized as three evaluation metrics to provide a comparison. Comprehensive experiments validate the effectiveness of introducing sparse property and preserving local structure in our method.

关键词： Clustering methods Clustering algorithms Decoding Neural networks Computer science image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Challenges of Ship Focusing with Long Coherence processing Interval

Challenges of Ship Focusing with Long Coherence Processing I...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： WenKang Liu MengDao Xing Guang-Cai Sun Xidian University Xi’an P. R. China

Ship oscillatory motions with long coherence processing interval (CPI) are complex and hard to accurately estimate. The traditional ship imaging methods usually avoid long-CPI focusing by dealing with a short observation time interval, which may make it hard to obtain a high-resolution and high-SNR image. In this paper, the mechanisms and challenges of long CPI imaging of oscillatory targets are investigated. The properties of wavenumber domain support (WDS) and point spreading function (PSF) of oscillatory targets are analyzed. It's found that the WDS spreads as a three-dimensional (3D) thin and curved sweep surface, with time-variant energy density, non-parallel boundaries and a complex structure. The PSF of an oscillatory target has a 3D resolution, but also multiple side-lobes with high level. We inspect the relationships between the properties of the WDS and the non-ideal PSF. Moreover, it's found that scatters distributed on a 3D oscillatory target cannot be focused uniformly on a predefined imaging plane (IP). The projection relationship of the target focusing positions on the slant-range plane (SRP) and the IP are also derived. The simulation results can well validate the proposed method.

关键词： Marine vehicles Three-dimensional displays IP networks Radar imaging Focusing

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：