CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
End-to-end Flow Correlation Tracking with Spatial-temporal Attention
Zhu Z(朱政)1,2; Wu W(武伟)1; Zou W(邹伟)1; Yan JJ(闫俊杰)1
2018
Conference NameIEEE Conference on Computer Vision and Pattern Recognition
Conference Date2018
Conference Place盐湖城
Abstract

Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and hardly benefit from motion and inter-frame information. The lack of temporal information degrades the tracking performance during challenges such as partial occlusion and deformation. In this paper, we propose the FlowTrack, which focuses on making use of the rich flow information in consecutive frames to improve the feature representation and the tracking accuracy. The FlowTrack formulates individual components, including optical flow estimation, feature extraction, aggregation and correlation filters tracking as special layers in network. To the best of our knowledge, this is the first work to jointly train flow and tracking task in deep learning framework. Then the historical feature maps at predefined intervals are warped and aggregated with current ones by the guiding of flow. For adaptive aggregation, we propose a novel spatialtemporal attention mechanism. In experiments, the proposed method achieves leading performance on OTB2013, OTB2015, VOT2015 and VOT2016.
 

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23564
Collection精密感知与控制研究中心_精密感知与控制
Corresponding AuthorZou W(邹伟)
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhu Z,Wu W,Zou W,et al. End-to-end Flow Correlation Tracking with Spatial-temporal Attention[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
End-to-end Flow Corr(1325KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu Z(朱政)]'s Articles
[Wu W(武伟)]'s Articles
[Zou W(邹伟)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu Z(朱政)]'s Articles
[Wu W(武伟)]'s Articles
[Zou W(邹伟)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu Z(朱政)]'s Articles
[Wu W(武伟)]'s Articles
[Zou W(邹伟)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: End-to-end Flow Correlation Tracking with Spatial-temporal Attention.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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