Attentional correlation filter network for adaptive visual tracking

File Description SizeFormat 
1996-stamped.pdfFile embargoed until 01 January 100003.3 MBAdobe PDF    Request a copy
Title: Attentional correlation filter network for adaptive visual tracking
Author(s): Choi, J
Chang, HJ
Yun, S
Fischer, T
Demiris, Y
Choi, JY
Item Type: Conference Paper
Abstract: 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.
Publication Date: 22-Jul-2017
Date of Acceptance: 27-Feb-2017
URI: http://hdl.handle.net/10044/1/45078
Publisher: IEEE
Copyright Statement: This paper is embargoed until publication.
Sponsor/Funder: Commission of the European Communities
Funder's Grant Number: 612139
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition
Publication Status: Accepted
Start Date: 2017-07-22
Finish Date: 2017-07-26
Conference Place: Honolulu, Hawaii, US
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering



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

Creative Commons