skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking

Computer Vision – ECCV 2016, 2016, p.472-488 [Peer Reviewed Journal]

Springer International Publishing AG 2016 ;ISSN: 0302-9743 ;ISBN: 3319464531 ;ISBN: 9783319464534 ;ISBN: 9783319464541 ;ISBN: 331946454X ;EISSN: 1611-3349 ;EISBN: 9783319464541 ;EISBN: 331946454X ;DOI: 10.1007/978-3-319-46454-1_29

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
  • Author: Danelljan, Martin ; Robinson, Andreas ; Shahbaz Khan, Fahad ; Felsberg, Michael
  • Subjects: Convolution Operator ; Fourier Coefficient ; Object Tracking ; Training Sample ; Visual Tracking
  • Is Part Of: Computer Vision – ECCV 2016, 2016, p.472-488
  • Description: Discriminative Correlation Filters (DCF) have demonstrated excellent performance for visual object tracking. The key to their success is the ability to efficiently exploit available negative data by including all shifted versions of a training sample. However, the underlying DCF formulation is restricted to single-resolution feature maps, significantly limiting its potential. In this paper, we go beyond the conventional DCF framework and introduce a novel formulation for training continuous convolution filters. We employ an implicit interpolation model to pose the learning problem in the continuous spatial domain. Our proposed formulation enables efficient integration of multi-resolution deep feature maps, leading to superior results on three object tracking benchmarks: OTB-2015 (+5.1%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} 5.1\,\% end{document} in mean OP), Temple-Color (+4.6%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} 4.6\,\% end{document} in mean OP), and VOT2015 (20%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} 0\,\% end{document} relative reduction in failure rate). Additionally, our approach is capable of sub-pixel localization, crucial for the task of accurate feature point tracking. We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments.
  • Publisher: Cham: Springer International Publishing
  • Language: English
  • Identifier: ISSN: 0302-9743
    ISBN: 3319464531
    ISBN: 9783319464534
    ISBN: 9783319464541
    ISBN: 331946454X
    EISSN: 1611-3349
    EISBN: 9783319464541
    EISBN: 331946454X
    DOI: 10.1007/978-3-319-46454-1_29
  • Source: SWEPUB Freely available online
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait