检索结果-内蒙古大学图书馆

12th International Conference on computational intelligence and Communication Networks, CICN 2020

作者： Abraham, Deepa Manuel, Manju Rajiv Gandhi Institute of Technology Department of Electronics and Communication Engineering Kottayam India

ISBN: (纸本)9781728193939

Ramanujan Sums have recently aroused interest in signal processing community owing to its special properties. These sums have been used in many signal processing applications such as periodicity detection of sequences and bio molecules, filter bank design, formulation of new signal transforms, etc. In this paper, it is proposed to use Ramanujan Sums based filter banks for image transmultiplexing. Transmultiplexer filter coefficients derived by this method are integer valued and the designed filter bank obeys perfect reconstruction condition. © 2020 ieee.

关键词： Filter banks

来源：评论

学校读者我要写书评

暂无评论

signal and image processing and computational intelligence

Signal and Image Processing and Computational Intelligence

引用

ieee International Conference on Industrial Technology (ICIT)

Start of the above-titled section of the conference proceedings record.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image Captioning using Deep Learning: Text Augmentation by Paraphrasing via Backtranslation

Image Captioning using Deep Learning: Text Augmentation by P...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Ingrid Ravn Turkerud Ole Jakob Mengshoel Department of Computer Science NTNU TrondheimNorway

ISBN: (纸本)9781728190495

image captioning, an exciting but challenging area of research at the intersection of natural language processing and computer vision, has recently seen dramatic progress. Much of the progress has been due to advances in machine learning and the availability of suitable data sets consisting of images, each with multiple captions. However, there has been little research on the impact of varying the number of captions on the quality of image captioning results. In particular, does it improve image captioning performance if we increase the number of captions in a dataset by augmenting the existing captions with paraphrases created using backtranslation? In this paper, we address this question and make the following three main contributions. First, we present a novel method of adding captions to a dataset by means of paraphrasing via backtranslation. Backtranslation amounts, in our case, to translating an English caption to a French counterpart which is then translated back to English. Typically, this results in the backtranslated English caption being different from the original English caption. Such backtranslated English captions can thus be used to augment the original dataset. Second, using our method, we generate paraphrases for the seminal MS COCO image captioning dataset. Our paraphrase dataset consists of around 490 000 paraphrased captions that are different from the original captions in MS COCO. Third, in image captioning experiments with deep learning models, we use datasets augmented with backtranslated paraphrases. We study the extent to which augmenting image captioning training datasets with paraphrases improves image captioning models' performance, and report promising results. Code and data are publicly available.

关键词： Deep learning Training Computer vision Codes Stochastic processes Simulated annealing Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Inpainting Electrical Logging images Based on Deep CNN with Attention Mechanisms

Inpainting Electrical Logging Images Based on Deep CNN with ...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Du, Chunyu Xing, Qiang Zhang, Jinyan Wang, Jun Liu, Baodi Wang, Yanjiang China Univ Petr East China Coll Control Sci & Engn Qingdao 266580 Peoples R China Well Logging Co Sinopec Shengli Petr Engn Co LTD Dongying 257000 Peoples R China

ISBN: (纸本)9781728125473

Microresistivity imaging logging is a crucial technique for evaluating the glutenite, carbonate and other complex reservoirs in oil exploration field. Because the size of the electrode pads in the electric imaging logging instrument can not match the borehole size well, it is hard to get full borehole covering images, which leads to many blank strips in the logging images. Thus it is necessary to fill the blank strips to ensure the accuracy of the subsequent processing and interpretation. The existing filling methods work well only in simple formation structures, but for images whose structure is very complex, for example, glutenite formation, the filled regions appear blurred and indistinct. To remedy the drawbacks, in this paper, we propose a machine learning method to inpaint the blank strips in electrical logging images based on deep convolutional neural network with the attention mechanisms embedded, which can capture a large number of low-level image statistical prior information. The attention mechanisms here refer to both the channel attention and the spatial attention. The channel attention focuses on the information to be attended in the intermediate feature maps while the spatial attention serves determining where to attend. Extensive experiments validate and confirm the effectiveness of the proposed filling method, which produce more compelling results than the existing filling approaches.

关键词： deep convolutional neural network attention mechanism image inpainting Microresistivity imaging logging

来源：评论

学校读者我要写书评

暂无评论

A 170μW image signal Processor Enabling Hierarchical image Recognition for intelligence at the Edge

A 170μW Image Signal Processor Enabling Hierarchical Image ...

引用

2020 ieee symposium on VLSI Circuits, VLSI Circuits 2020

作者： An, Hyochan Venkatesan, Siddharth Schiferl, Sam Wesley, Tim Zhang, Qirui Wang, Jingcheng Choo, Kyojin Liu, Shiyu Liu, Bowen Li, Ziyun Zhong, Hengfei Gong, Luyao Blaauw, David Dreslinski, Ronald Sylvester, Dennis Kim, Hun Seok University of Michigan Ann Arbor United States

ISBN: (数字)9781728199429

ISBN: (纸本)9781728199429

We propose an ultra-low power (ULP) image signal Processor (ISP) that performs on-the-fly in-processing frame (de)compression and hierarchical event recognition to exploit the temporal and spatial sparsity in an image sequence to achieve a 16× imaging system energy gain. The ISP is fabricated in 40nm CMOS and consumes only 170 μW at 5 fps for neural network-based intruder detection and 192× compressed image recording. © 2020 ieee.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible images

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2022年 71卷

作者： Wang, Zhishe Chen, Yanlin Shao, Wenyu Li, Hui Zhang, Lei Taiyuan Univ Sci & Technol Sch Appl Sci Taiyuan 030024 Peoples R China Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Jiangsu Peoples R China Nanyang Normal Univ Sch Mechatron Engn Nanyang 473061 Peoples R China

The existing deep learning fusion methods mainly concentrate on convolutional neural networks (CNNs), and few attempts are made with transformer. Meanwhile, the convolutional operation is a content-independent interaction between the image and the convolution kernel, which may lose some important contexts and further limit fusion performance. Toward this end, we present a simple and strong fusion baseline for infrared and visible images, namely, residual Swin Transformer fusion network, termed SwinFuse. Our SwinFuse includes three parts: the global feature extraction, fusion layer, and feature reconstruction. In particular, we build a fully attentional feature encoding backbone to model the long-range dependencies, which is a pure transformer network and has a stronger representation ability compared with the CNNs. Moreover, we design a novel feature fusion strategy based on the L-1-norm for sequence matrices and measure the corresponding activity levels from row and column vector dimensions, which can well retain competitive infrared brightness and distinct visible details. Finally, we testify our SwinFuse with nine state-of-the-art traditional and deep learning methods on three different datasets through subjective observations and objective comparisons, and the experimental results manifest that the proposed SwinFuse obtains surprising fusion performance with strong generalization ability and competitive computational efficiency. The code will be available at https://***/Zhishe-Wang/SwinFuse.

关键词： Deep learning feature normalization image fusion self-attention mechanism Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Application on Vehicle Detector using Laser Ranging image Sensor

Application on Vehicle Detector using Laser Ranging Image Se...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Lin Teng Nobuhiro Watanabe Takashi Izumi Hiroaki Matsuzaki Tomoaki Takahashi Norio Kiryu College of Science and Technology Nihon University Chiba Japan Graduate School of Science and Technology Nihon University Chiba Japan NIPPON SIGNAL CO. LTD. Tokyo Japan

ISBN: (纸本)9781728190495

In traffic control systems, the vehicle detectors play a central role in collecting information. As information gathering equipment, there are many types of current vehicle detectors, such as ultrasonic type, loop coil type, and image type. But there are problems such as reduced accuracy due to temperature and wind, maintainability problems, and reduced accuracy at night. Therefore, in this research, we are considering using a Laser Ranging image Sensor that can obtain an image including the distance as a new vehicle detector. In this paper, we first examined the sensor installation conditions. And then we proposed vehicle detection method for Laser Ranging image Sensor for One-lane detection and Multiple-lanes detection. Finally, we conducted the demonstration experiment of vehicle detection and compared with the few public information of traditional vehicle detectors. From experiment results, we confirmed that for One-lane detection, it is excellent in accuracy. For Multiple-lines detection, it also has sufficient detection accuracy and can be further improving. In addition, as a new vehicle detector, it is excellent in installation and maintenance than traditional vehicle detectors.

关键词： image sensors Temperature sensors Three-dimensional displays Vehicle detection Volume measurement Roads Detectors

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network with Inception Blocks for image Compression Artifact Reduction

Convolutional Neural Network with Inception Blocks for Image...

引用

International Joint Conference on Neural Networks (IJCNN) held as part of the ieee World Congress on computational intelligence (ieee WCCI)

作者： Bhattacharya, Purbaditya Zoelzer, Udo Helmut Schmidt Univ Dept Signal Proc & Commun Hamburg Germany

ISBN: (纸本)9781728169262

A convolutional neural network is proposed for the reduction of artifacts introduced by JPEG compression. In this work the existing DnCNN architecture has been considered as the basis network and it is extended by introducing inception blocks on top of a normal convolution block consisting of convolution, rectified linear unit and batch-normalization layers. Each inception block contains parallel convolution blocks with various dilation factors, essentially performing Atrous convolution. Compression artifacts result in multiple image neighborhoods or blocks having similar or redundant information. In spatial domain the Atrous convolution introduces a larger receptive field while ignoring redundant neighboring pixels due to the dilation, thus helping in a better reconstruction. The proposed network is trained on a small dataset as used by the basis network. Evaluation of this network on the standard test datasets shows a substantial quantitative and qualitative improvement, particularly for higher compression rates.

关键词： Convolutional neural network compression artifact reduction image processing

来源：评论

学校读者我要写书评

暂无评论

Effects of Weighting Schemes on Retrieval Precision

Effects of Weighting Schemes on Retrieval Precision

引用

symposium of image, signal processing, and Artificial Vision (STSIVA)

作者： Fadi Yamout Youssef Mouallem Department of Computer Science International University of Beirut Beirut Lebanon

ISBN: (数字)9798350363203

ISBN: (纸本)9798350363210

Finding relevant information in a vast and growing amount of data has become significant since the arrival of the internet. An Information Retrieval System is described as searching and retrieving a list of documents, such as web pages or other items, in response to a user query. There are many weighting schemes, such as Boolean, Term Frequency or TF, and Term-Frequency-Inverse-Document-Frequency or TFIDF. In Boolean, a ‘1’ indicates the presence of a term in the document, whereas a ‘0’ indicates its absence. In TF, the term is represented by the number of occurrences in a document. TFIDF is the most popular one. It combines TF with an inverse document frequency IDF; IDF gives less weight to terms that frequently occur in many documents. With reference to the information retrieval system literature, TFIDF gives more accurate results on the computationally expensive expenses. Term Frequency is less expensive than TFIDF, and the least expensive one is the Boolean weighting scheme. In this paper, we investigated the effect of different weighting schemes and found out that, in many cases, Boolean and TF performed the same as TFIDF and, in a few cases, outperformed them. The experiments in this paper were conducted on many datasets of variant sizes and types. The dataset documents were indexed using TFIDF, TF, and Boolean. Then, using the queries that come with the dataset, we computed the precision and recall by comparing the results of different weighting schemes; the queries were also indexed using TFIDF, TF, and Boolean weighting schemes. The objective is to show that the use of the Boolean or TF weighting scheme, which is considered not computationally expensive, instead of TFIDF, which is regarded as very computationally expensive, does not significantly affect the results and, in a few cases, gives better results.

关键词： Accuracy computational modeling Web pages Information retrieval Informatics

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach

引用

ieee TRANSACTIONS ON BIOMEDICAL ENGINEERING 2020年第2期67卷 399-410页

作者： He, He Wu, Dongrui Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China

Objective: This paper targets a major challenge in developing practical electroencephalogram (EEG)-based brain-computer interfaces (BCIs): how to cope with individual differences so that better learning performance can be obtained for a new subject, with minimum or even no subject-specific data? Methods: We propose a novel approach to align EEG trials from different subjects in the Euclidean space to make them more similar, and hence improve the learning performance for a new subject. Our approach has three desirable properties: first, it aligns the EEG trials directly in the Euclidean space, and any signal processing, feature extraction, and machine learning algorithms can then be applied to the aligned trials;second, its computational cost is very low;and third, it is unsupervised and does not need any label information from the new subject. Results: Both offline and simulated online experiments on motor imagery classification and event-related potential classification verified that our proposed approach outperformed a state-of-the-art Riemannian space data alignment approach, and several approaches without data alignment. Conclusion: The proposed Euclidean space EEG data alignment approach can greatly facilitate transfer learning in BCIs. Significance: Our proposed approach is effective, efficient, and easy to implement. It could be an essential pre-processing step for EEG-based BCIs.

关键词： Covariance matrices Electroencephalography Task analysis signal processing Machine learning algorithms Microsoft Windows Brain-computer interfaces Brain-computer interface data alignment EEG Riemannian geometry transfer learning

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：