Attentional Correlation Filter Network for Adaptive Visual Tracking

Research output: Chapter in Book/Report/Conference proceedingConference contribution


  • Jongwon Choi
  • Sangdoo Yun
  • Tobias Fischer
  • Yiannis Demiris
  • Jin Young Choi

Colleges, School and Institutes

External organisations

  • Seoul National University, South Korea
  • Imperial College London


We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency. The subset of filters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional Correlation Filter Network which allows adaptive tracking of dynamic targets. (ii) Utilising an attentional network which shifts the attention to the best candidate modules, as well as predicting the estimated accuracy of currently inactive modules. (iii) Enlarging the variety of correlation filters which cover target drift, blurriness, occlusion, scale changes, and flexible aspect ratio. (iv) Validating the robustness and efficiency of the attentional mechanism for visual tracking through a number of experiments. Our method achieves similar performance to non real-time trackers, and state-of-the-art performance amongst real-time trackers.


Original languageEnglish
Title of host publication2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publication statusPublished - 21 Jul 2017
Event30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) - Honolulu, Hawaii, United States
Duration: 21 Jul 201726 Jul 2017


Conference30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
CountryUnited States
CityHonolulu, Hawaii