In this section
@inproceedings{Choi:2017:10.1109/CVPR.2017.513,
author = {Choi, J and Chang, HJ and Yun, S and Fischer, T and Demiris, Y and Choi, JY},
doi = {10.1109/CVPR.2017.513},
publisher = {IEEE},
title = {Attentional correlation filter network for adaptive visual tracking},
url = {http://dx.doi.org/10.1109/CVPR.2017.513},
year = {2017}
}
TY - CPAPER
AB - 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.
AU - Choi,J
AU - Chang,HJ
AU - Yun,S
AU - Fischer,T
AU - Demiris,Y
AU - Choi,JY
DO - 10.1109/CVPR.2017.513
PB - IEEE
PY - 2017///
SN - 1063-6919
TI - Attentional correlation filter network for adaptive visual tracking
UR - http://dx.doi.org/10.1109/CVPR.2017.513
UR - http://ieeexplore.ieee.org/document/8099996/
UR - http://hdl.handle.net/10044/1/45078
ER -
