CASIA OpenIR  > 智能感知与计算研究中心
Learning Temporally Correlated Representations Using Lstms for Visual Tracking
Qiaozhe Li; Xin Zhao; Kaiqi Huang
2016
会议名称International Conference on Image Processing
会议录名称Image Processing (ICIP), 2016 IEEE International Conference on
页码2381-8549
会议日期2016-09-01
会议地点Phoenix, USA
摘要In this paper, we propose to learn object representations with inference from temporal correlation in videos to achieve effective visual tracking. Unlike traditional methods which perform feature learning either at image level or based on intuitive temporal constraint, we employ the recurrent network with Long Short Term Memory (LSTM) units to directly learn temporally correlated representations of the objects in long sequences. The recurrent network is pre-trained offline with auxiliary data and then online optimized to adapt to the target-specific object. A structured SVM is employed to account for the temporally correlated object appearance as well as distinguish the object from background distraction. Experiment results not only show that the appearance and dynamic patterns of the objects can be characterized via temporally correlated feature learning, but also demonstrate that the proposed tracking algorithm performs favorably against the state-of-the-art methods.
关键词Long Short Term Memory  Structured Svm  Temporally Correlated Feature Learning   visual Tracking
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12676
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Qiaozhe Li,Xin Zhao,Kaiqi Huang. Learning Temporally Correlated Representations Using Lstms for Visual Tracking[C],2016:2381-8549.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
LEARNING TEMPORALLY (752KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Qiaozhe Li]的文章
[Xin Zhao]的文章
[Kaiqi Huang]的文章
百度学术
百度学术中相似的文章
[Qiaozhe Li]的文章
[Xin Zhao]的文章
[Kaiqi Huang]的文章
必应学术
必应学术中相似的文章
[Qiaozhe Li]的文章
[Xin Zhao]的文章
[Kaiqi Huang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: LEARNING TEMPORALLY CORRELATED REPRESENTATIONS USING LSTMS FOR VISUAL TRACKING.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。