基本信息来源于合作网站,原文需代理用户跳转至来源网站获取       
摘要:
Recently,deep learning has achieved great success in visual tracking.The goal of this paper is to review the state-of-the-art tracking methods based on deep learning.First,we categorize the existing deep learning based trackers into three classes according to network structure,network function and network training.For each categorize,we analyze papers in different categories.Then,we conduct extensive experiments to compare the representative methods on the popular OTB-100,TC-128 and VOT2015 benchmarks.Based on our observations.We conclude that:(1)The usage of the convolutional neural network(CNN)model could significantly improve the tracking performance.(2)The trackers with deep features perform much better than those with low-level hand-crafted features.(3)Deep features from different convolutional layers have different characteristics and the effective combination of them usually results in a more robust tracker.(4)The deep visual trackers using end-to-end networks usually perform better than the trackers merely using feature extraction networks.(5)For visual tracking,the most suitable network training method is to per-train networks with video information and online fine-tune them with subsequent observations.Finally,we summarize our manuscript and highlight our insights,and point out the further trends for deep visual tracking.
推荐文章
Diffusion in garnet: a review
High temperature and high pressure
Diffusion
Garnet
Point defects
Deep web接口查询能力估计
查询接口
查询能力
Deep Web数据源自动分类
Deep Web
查询接口
朴素贝叶斯分类
一种Deep Web聚焦爬虫爬行策略
结构化Deep Web数据源
聚焦爬虫
决策树分类器
内容分析
关键词云
关键词热度
相关文献总数  
(/次)
(/年)
文献信息
篇名 Deep Learning Trackers Review and Challenge
来源期刊 信息隐藏与隐私保护杂志(英文) 学科 工学
关键词 DEEP LEARNING CNN OBJECT TRACKING online LEARNING
年,卷(期) 2019,(1) 所属期刊栏目
研究方向 页码范围 23-33
页数 11页 分类号 TP3
字数 语种
DOI
五维指标
传播情况
(/次)
(/年)
引文网络
引文网络
二级参考文献  (0)
共引文献  (0)
参考文献  (0)
节点文献
引证文献  (0)
同被引文献  (0)
二级引证文献  (0)
2019(0)
  • 参考文献(0)
  • 二级参考文献(0)
  • 引证文献(0)
  • 二级引证文献(0)
研究主题发展历程
节点文献
DEEP
LEARNING
CNN
OBJECT
TRACKING
online
LEARNING
研究起点
研究来源
研究分支
研究去脉
引文网络交叉学科
相关学者/机构
期刊影响力
信息隐藏与隐私保护杂志(英文)
季刊
2637-4234
江苏省南京市浦口区东大路2号东大科技园A
出版文献量(篇)
15
总下载数(次)
2
总被引数(次)
0
论文1v1指导