The 10th international conference on machine vision; C类

Methodology: 非主流方法

2 stages:

1. convert time series data to recurrence plot. 数值*时间长度----------> 时间长度*时间长度.

2. fed into CNN model.

潜在问题:

1. 由time series data 转化成为 recurrence plot是否丢失了信息,丢失了哪些信息------未知

2. cnn分类效果是否比别的好. 文章在在20个数据库上进行了测试,试验结果并没有很明显的提高.

Supplementary knowledge:

1. recurrence plot

PP:Classification of Time-Series Images Using Deep Convolutional Neural Networks的更多相关文章

  1. 《ImageNet Classification with Deep Convolutional Neural Networks》 剖析

    <ImageNet Classification with Deep Convolutional Neural Networks> 剖析 CNN 领域的经典之作, 作者训练了一个面向数量为 ...

  2. ImageNet Classification with Deep Convolutional Neural Networks（译文）转载

    ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geo ...

  3. AlexNet论文翻译-ImageNet Classification with Deep Convolutional Neural Networks

    ImageNet Classification with Deep Convolutional Neural Networks 深度卷积神经网络的ImageNet分类 Alex Krizhevsky ...

  4. 中文版 ImageNet Classification with Deep Convolutional Neural Networks

    ImageNet Classification with Deep Convolutional Neural Networks 摘要 我们训练了一个大型深度卷积神经网络来将ImageNet LSVRC ...

  5. Image Scaling using Deep Convolutional Neural Networks

    Image Scaling using Deep Convolutional Neural Networks This past summer I interned at Flipboard in P ...

  6. Deep learning_CNN_Review：A Survey of the Recent Architectures of Deep Convolutional Neural Networks——2019

    CNN综述文章 的翻译 [2019 CVPR] A Survey of the Recent Architectures of Deep Convolutional Neural Networks 翻 ...

  7. Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

    Understanding the Effective Receptive Field in Deep Convolutional Neural Networks 理解深度卷积神经网络中的有效感受野 ...

  8. 深度卷积神经网络用于图像缩放Image Scaling using Deep Convolutional Neural Networks

    This past summer I interned at Flipboard in Palo Alto, California. I worked on machine learning base ...

  9. [论文阅读] ImageNet Classification with Deep Convolutional Neural Networks(传说中的AlexNet)

    这篇文章使用的AlexNet网络,在2012年的ImageNet(ILSVRC-2012)竞赛中获得第一名,top-5的测试误差为15.3%,相比于第二名26.2%的误差降低了不少. 本文的创新点: ...

随机推荐

  1. 牛客练习赛56 B 小琛和他的学校

    题目链接:https://ac.nowcoder.com/acm/contest/3566/B 思路:一条路可把图分为左右两部分. l_ci, l_peo, r_ci, r_peo, w 分别为左边城 ...

  2. 剑指offer-面试题5-替换空格-字符串

    /* 题目: 请实现一个函数,把字符串中的每个空格替换成'%20'. 例如输入“We are happy",则输出 ”We%20are%happy". */ /* 结题思路: 考虑 ...

  3. UVA1635-唯一分解定理的基本应用2

    原题:https://vjudge.net/problem/UVA-1635 这是一个极其典型的“从素因子角度出发”的题目,下面是我的代码: #include<iostream> #inc ...

  4. vulnhub靶机之DC6实战（wordpress+nmap提权）

    0x00环境 dc6靶机下载地址:https://download.vulnhub.com/dc/DC-6.zip dc6以nat模式在vmware上打开 kali2019以nat模式启动,ip地址为 ...

  5. mybatis中用到的9种设计模式

    1.Builder模式:例如SqlSessionFactoryBuilder.XMLConfigBuilder.XMLMapperBuilder.XMLStatementBuilder.CacheBu ...

  6. mysql 表分区操作

    //不支持动态创建分区CREATE TABLE `rpt_exp_event_bucket_creative_d_across` ( `bucket_id` VARCHAR(200) NOT NULL ...

  7. python报错bs4.FeatureNotFound: Couldn't find a tree builder with the features you requested: lxml.

    qpython运行 原代码:    soup = BeautifulSoup(r.text,'lxml') 报错:bs4.FeatureNotFound: Couldn't find a tree b ...

  8. C#序列化与反序列化学习笔记

    本笔记摘抄自:https://www.cnblogs.com/maitian-lf/p/3670570.html,记录一下学习过程以备后续查用. 序列化是把一个内存中的对象的信息转化成一个可以持久化保 ...

  9. Mybatis常见面试题汇总

    Mybatis常见面试题汇总 最近在复习整理Mybatis的相关知识,针对面试中的典型问题,结合相关书籍和网上相关帖子,做如下整理. ================================= ...

  10. Codeforces Round #624 (Div. 3) F. Moving Points 题解

    第一次写博客 ,请多指教! 翻了翻前面的题解发现都是用树状数组来做,这里更新一个 线段树+离散化的做法: 其实这道题是没有必要用线段树的,树状数组就能够解决.但是个人感觉把线段树用熟了会比树状数组更有 ...