Need:

  1. With the ever-growth large-scale video in the mobile phone, so what will everyone get from these video? There are many videos contain something very interesting like a short comedy video. So if someone find something interesting in the video and want know more about it, they may not search it in the internet and find the information after watching this video due the poor memory. So if the advertiser have put some advertisements in the video ahead of time, it will be more convenient for the user to get some information. That’s very useful for the advertisers and the users.
  2. There are many videos in users’ phone. Maybe most of them are meaningful time mark. So someone want to look for some useful tools to tagging the meaningful object or want to know the object information. Then our video tagging systems will be very efficient for this work.

Approach:

  1. The video tagging project can be divided into two steps. The first one is the key frame localization. The second one is the object classification or object detection.
  2. The key frame localization can be realized by some conventional method like the HOG features split or some other method. This is a litter challenge because there is no very efficient way to get the really accuracy key frame. And I think it is a program optimization problem.
  3. The object classification can be realized by the deep convolutional neural network classifier or some other deep learning state-of-the-arts method. The problem is the labels may be not enough. So it can be a research problem.

Benefit:

  1. Everyone can be convenient to get some merchandise information by the tagged video which is processed by the mobile end application.
  2. Some people will summarize the meaningful moments and find some meaningful object.

Competitors:

There a video tagging system which has been released in the internet after my survey. The Website name is “Clarifai”. They can tag the video and get the object temporal information. And the classification accuracy is very high. So it is our main competitor.

10/18/2015

Fuchen Long

Video tagging systems based on DNNs的更多相关文章

  1. Video processing systems and methods

    BACKGROUND The present invention relates to video processing systems. Advances in imaging technology ...

  2. Designing IP-Based Video Conferencing Systems: Dealing with Lip Synchronization(唇音同步)

    转自:http://www.ciscopress.com/articles/article.asp?p=705533&seqNum=6 Correlating Timebases Using ...

  3. Modeling of Indoor Positioning Systems Based on Location Fingerprinting

    Kamol Kaemarungsi and Prashant Krishnamurthy Telecommunications Program School of Information Scienc ...

  4. Video Target Tracking Based on Online Learning—TLD单目标跟踪算法详解

    视频目标跟踪问题分析         视频跟踪技术的主要目的是从复杂多变的的背景环境中准确提取相关的目标特征,准确地识别出跟踪目标,并且对目标的位置和姿态等信息精确地定位,为后续目标物体行为分析提供足 ...

  5. Video Target Tracking Based on Online Learning—TLD多目标跟踪算法

    TLD算法回顾 TLD(Tracking-Learning-Detection)是英国萨里大学的一个捷克籍博士生Zdenek Kalal在其攻读博士学位期间提出的一种新的单目标长时间(long ter ...

  6. Video Target Tracking Based on Online Learning—深度学习在目标跟踪中的应用

    摘要 近年来,深度学习方法在物体跟踪领域有不少成功应用,并逐渐在性能上超越传统方法.本文先对现有基于深度学习的目标跟踪算法进行了分类梳理,后续会分篇对各个算法进行详细描述. 看上方给出的3张图片,它们 ...

  7. 自然语言15.1_Part of Speech Tagging 词性标注

    QQ:231469242 欢迎喜欢nltk朋友交流 https://en.wikipedia.org/wiki/Part-of-speech_tagging In corpus linguistics ...

  8. 词性标注 parts of speech tagging

    In corpus linguistics, part-of-speech tagging (POS tagging or POST), also called grammatical tagging ...

  9. (分享)视频压缩Free Video Compressor 汉化版/中文版【全网唯一】

    介绍:Free Video Compressor 是一个免费视频压缩软件,可以帮您有效的压缩视频.电影文件的体积大小,减小占用的磁盘空间,使之更容易放到手机中保存播放Free Video Compre ...

随机推荐

  1. Java流中的map算子和flatMap算子的区别

    map算子和flatMap算子 map和flatMap都是映射(转换),那么他们之间究竟有什么区别呢? 1.我们先简单了解下map算子: @org.junit.Test public void tes ...

  2. RNN,GRU,LSTM

    2019-08-29 17:17:15 问题描述:比较RNN,GRU,LSTM. 问题求解: 循环神经网络 RNN 传统的RNN是维护了一个隐变量 ht 用来保存序列信息,ht 基于 xt 和 ht- ...

  3. 《java编程思想》对象导论

    1.抽象过程 所有编程语言都提供抽象机制.可以认为,人们所能够解决的问题的复杂性直接取决于抽象的类型和质量,所谓的'类型'是指“所抽象的是什么?”汇编语言是对底层机器的轻微抽象. java的基本 特性 ...

  4. [poj1797]Heavy Transportation<最大生成树prim&kruskal>

    题目链接:http://poj.org/problem?id=1797 题意:给定n个点,m条边,每条边连接两点切有权值.求点1到点n的路径的上的最小边的值最大... 翻别人博客找到的题,方法挺多的, ...

  5. c++ 常量/有符号数和无符号数

    一.宏定义 #define 和常量 const 1. const关键字 const是constant的简写,只要一个变量前面用const来修饰,就意味着该变量里的数据可以被访问,不能被修改.也就是说c ...

  6. 相见恨晚的 Git 命令动画演示,一看就懂!

    虽然 Git 是一个强大的工具,但是我觉得大部分人都会同意我说的:它也可以是一个--噩梦!我一直觉得,使用 Git 的时候把操作过程在脑海里视觉化会非常有用:当我执行某个命令的时候,分支之间是如何交互 ...

  7. Jenkins集成时报错 hudson.remoting.Channel$CallSiteStackTrace: Remote call to JNLP4-connect connection from xxx.xxx.xxx.xxx/xxx.xxx.xxx.xxx:32034

    Started by user test Running as SYSTEM Building remotely on home_windows (mbhCloud_UI_Test) in works ...

  8. vue中的js引入图片,使用require相关问题

    vue中的js引入图片,必须require进来 或者引用网络地址 <template> <div class="home"> <img alt=&qu ...

  9. Java工程中如何读取配置文件中参数信息

    Java中读取配置文件中参数: 方法一:通过JDK中Properties来实现对配置文件的读取. Properties主要用于读取Java的配置文件,不同的编程语言有自己所支持的配置文件,配置文件中很 ...

  10. Python模块---制作属于自己的有声小说

    操作环境 Python版本: anaconda3 python3.7.4 操作系统: Ubuntu19.10 编译器: pycharm社区版 用到的模块: pyttsx3,requests pysst ...