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
Conference NameInternational Conference on Image Processing
Source PublicationImage Processing (ICIP), 2016 IEEE International Conference on
Pages2381-8549
Conference Date2016-09-01
Conference PlacePhoenix, USA
AbstractIn 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.
KeywordLong Short Term Memory  Structured Svm  Temporally Correlated Feature Learning   visual Tracking
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12676
Collection智能感知与计算研究中心
Corresponding AuthorKaiqi Huang
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Qiaozhe Li,Xin Zhao,Kaiqi Huang. Learning Temporally Correlated Representations Using Lstms for Visual Tracking[C],2016:2381-8549.
Files in This Item:
File Name/Size DocType Version Access License
LEARNING TEMPORALLY (752KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qiaozhe Li]'s Articles
[Xin Zhao]'s Articles
[Kaiqi Huang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qiaozhe Li]'s Articles
[Xin Zhao]'s Articles
[Kaiqi Huang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qiaozhe Li]'s Articles
[Xin Zhao]'s Articles
[Kaiqi Huang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: LEARNING TEMPORALLY CORRELATED REPRESENTATIONS USING LSTMS FOR VISUAL TRACKING.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.