CONVOLUTION

作品数：628被引量：731H指数：11
导出分析报告
相关领域：理学机械工程更多>>
相关作者：朱延娟周来水李陶深何乐生贾积身更多>>
相关机构：华中师范大学南京航空航天大学东南大学云南大学更多>>
相关期刊：更多>>
相关基金：国家自然科学基金中国博士后科学基金国家重点基础研究发展计划国家高技术研究发展计划更多>>
-
在结果中检索

检索结果分析

结果分析中...
选择条件：
  • 期刊=Chinese Journal of Electronicsx
共 条 记 录，以下是1-10
全选清除导出
参考文献引证文献引用追踪
视图：
排序：
Enhancing Entity Relationship Extraction in Dialogue Texts Using Hypergraph and Heterogeneous Graph
《Chinese Journal of Electronics》2025年第1期295-308,共14页Shunmiao Zhang Siyuan Zheng Degen Huang Dan Li 
supported by the National Key Research and Development Program of China(Grant No.2020AAA0108004);the Fujian Province Science and Technology Guiding Project(Grant No.2022H0025)。
Dialogue-based relation extraction(DialogRE)aims to predict relationships between two entities in dialogue.Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dial...
关键词：Dialogue relation extraction Hypergraph convolution Heterogeneous graph convolution 
The Novel Instance Segmentation Method Based on Multi-Level Features and Joint Attention
《Chinese Journal of Electronics》2023年第5期1160-1168,共9页XU Bowen LU Yinan WU Tieru GUO Xiaoxin 
supported by the National Natural Science Foundation of China(61872162,82071995);the Key Research and Development Program of Jilin Province(20210301001GX,20220201141GX);the Natural Science Foundation of Jilin Province(20200201292JC).
Instance segmentation is an important task in computer vision.In order to enhance the multi-level features expression ability of the segmentation networks,a novel module is proposed in this paper.Firstly,we design a w...
关键词：Instance segmentation Feature fusion Attention mechanism Dynamic convolution Deep neural network 
Defects Recognition of Train Wheelset Tread Based on Improved Spiking Neural Network被引量：2
《Chinese Journal of Electronics》2023年第5期941-954,共14页ZHANG Changfan HUANG Congcong HE Jing 
supported by the National Natural Science Foundation of China(52172403,62173137);the Hunan Provincial Natural Science Foundation of China(2021JJ50001);the Project of Hunan Provincial Department of Education(19A137,18A267)。
Surface defect recognition of train wheelset is crucial for the safe operation of the train wheel system.However,due to the diversity and complexity of such defects,it is difficult for existing algorithms to make rapi...
关键词：Defects recognition Spiking neural network Spike train encoding Dilated convolution Channel attention module Wheelset tread 
De-convolution and De-noising of SAR Based GPS Images Using Hybrid Particle Swarm Optimization被引量：1
《Chinese Journal of Electronics》2023年第1期166-176,共11页Rizwan Sadiq Muhammad Bilal Qureshi Muhammad Mohsin Khan 
Synthetic aperture radar(SAR) imaging is an efficient strategy which exploits the properties of microwaves to capture images.A major concern in SAR imaging is the reconstruction of image from back scattered signals in...
关键词：Remote sensing Synthetic aperture radar imaging Wiener filter Particle swarm optimization 
Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight被引量：3
《Chinese Journal of Electronics》2022年第2期387-396,共10页NIU Haoran HE Haitao FENG Jianzhou NIE Junlan ZHANG Yangsen REN Jiadong 
supported by the National Natural Science Foundation of China(61602401,61772449);Scientific and Technological Research Projects of Colleges and Universities in Hebei Province(QN2018074);Nature Scientist Fund of Hebei Province(F2019203157)。
Knowledge graph completion(KGC)can solve the problem of data sparsity in the knowledge graph.A large number of models for the KGC task have been proposed in recent years.However,the underutilisation of the structure i...
关键词：Knowledge graph completion Graph convolutional network Channel attention convolution High-dimensional structure analysis weight 
The Kernel Dynamics of Convolutional Neural Networks in Manifolds
《Chinese Journal of Electronics》2020年第6期1185-1192,共8页WU Wei JING Xiaoyuan DU Wencai 
supported by the National Natural Science Foundation of China(No.61933013,No.U1736211);the Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDA22030301);the Foundation of Macao(No.MF1809,No.MF1713).
We propose a novel expression from manifolds to define Convolutional neural network(CNN).The layered structure is proceeded by integration in limited space continuously,with weights adjusted including value and direct...
关键词：Convolutional neural networks Kernelbased convolution Learning dynamics Neural manifolds 
Advancing Graph Convolution Network with Revised Laplacian Matrix被引量：2
《Chinese Journal of Electronics》2020年第6期1134-1140,共7页WANG Jiahui GUO Yi WANG Zhihong TANG Qifeng WEN Xinxiu 
supported by the National Key Research and Development Program of China(No.2018YFC0807105);the National Natural Science Foundation of China(No.61462073);the Science and Technology Committee of Shanghai Municipality(No.17DZ1101003,No.18511106602,No.18DZ2252300).
Graph convolution networks are extremely efficient on the graph-structure data,which both consider the graph and feature information.Most existing models mainly focus on redefining the complicated network structure,wh...
关键词：Graph convolution network CLUSTERING Label propagation Laplacian matrix Graph structure Fraud detection 
Facial Beauty Prediction Based on Lighted Deep Convolution Neural Network with Feature Extraction Strengthened被引量：2
《Chinese Journal of Electronics》2020年第2期312-321,共10页GAN Junying JIANG Kaiyong TAN Haiying HE Guohui 
supported by the National Natural Science Foundation of China(No.61771347);Basic Research and Applied Basic Research Key Project in General Colleges and Universities of Guangdong Province(No.2018KZDXM073)。
Convolutionneural network(CNN) has significantly pushed forward machine vision,which has achieved very significant results in face recognition, image classification and objection detection,and provides a new method fo...
关键词：Lighted DEEP CONVOLUTION neural network FACIAL BEAUTY PREDICTION Inception model MFM activation layer LSAFBD 
A Short Text Classification Method Based on N-Gram and CNN被引量：23
《Chinese Journal of Electronics》2020年第2期248-254,共7页WANG Haitao HE Jie ZHANG Xiaohong LIU Shufen 
supported by the National Natural Science Foundation of China(No.61503124,No.61572379)。
Text classification is a fundamental task in Nature language process(NLP) application. Most existing research work relied on either explicate or implicit text representation to settle this kind of problems, while thes...
关键词：SHORT TEXT Classification CONVOLUTION NEURAL network N-GRAM CONCENTRATION mechanism 
A Novel Separability Objective Function in CNN for Feature Extraction of SAR Images被引量：4
《Chinese Journal of Electronics》2019年第2期423-429,共7页GAO Fei WANG Meng WANG Jun YANG Erfu ZHOU Huiyu 
funded by the National Natural Science Foundation of China(No.61771027,No.61071139,No.61471019,No.61501011,No.61171122);supported in part under the RSE-NNSFC Joint Project(2017-2019)(No.6161101383)with China University of Petroleum(Huadong);supported by Invest NI/Philips,UK EPSRC(No.EP/N011074/1);Royal Society-Newton Advanced Fellowship(No.NA160342)
Convolutional neural network(CNN) has become a promising method for Synthetic aperture radar(SAR) target recognition. Existing CNN models aim at seeking the best separation between classes, but rarely care about the s...
关键词：SYNTHETIC APERTURE radar(SAR) CONVOLUTION neural network(CNN) Classification Linear SEPARABILITY Objective function 
全选清除导出
共2页<12>
检索报告 对象比较 聚类工具 使用帮助 返回顶部