liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Convolutional Features for Correlation Filter Based Visual Tracking
Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.
Linköping University, Faculty of Science & Engineering. Linköping University, Department of Electrical Engineering, Computer Vision.ORCID iD: 0000-0002-6096-3648
2015 (English)In: Proceedings of the IEEE International Conference on Computer Vision, IEEE conference proceedings, 2015, 621-629 p.Conference paper, Published paper (Refereed)
Abstract [en]

Visual object tracking is a challenging computer vision problem with numerous real-world applications. This paper investigates the impact of convolutional features for the visual tracking problem. We propose to use activations from the convolutional layer of a CNN in discriminative correlation filter based tracking frameworks. These activations have several advantages compared to the standard deep features (fully connected layers). Firstly, they mitigate the need of task specific fine-tuning. Secondly, they contain structural information crucial for the tracking problem. Lastly, these activations have low dimensionality. We perform comprehensive experiments on three benchmark datasets: OTB, ALOV300++ and the recently introduced VOT2015. Surprisingly, different to image classification, our results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers. Our results further show that the convolutional features provide improved results compared to standard handcrafted features. Finally, results comparable to state-of-theart trackers are obtained on all three benchmark datasets.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2015. 621-629 p.
Series
IEEE International Conference on Computer Vision. Proceedings, ISSN 1550-5499
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-128869DOI: 10.1109/ICCVW.2015.84ISI: 000380434700075ISBN: 978-146738390-5 (print)OAI: oai:DiVA.org:liu-128869DiVA: diva2:933006
Conference
15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015
Available from: 2016-06-02 Created: 2016-06-02 Last updated: 2016-08-26

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Danelljan, MartinHäger, GustavKhan, Fahad ShahbazFelsberg, Michael
By organisation
Faculty of Science & EngineeringComputer Vision
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

Altmetric score

Total: 1254 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf