Publication details for Professor Toby BreckonPeng, S., Kamata, S. & Breckon, T.P. (2019), A Ranking based Attention Approach for Visual Tracking, 26th IEEE International Conference on Image Processing (ICIP). Taipei, Taiwan, IEEE, Piscataway, NJ, 3073-3077.
- Publication type: Conference Paper
- ISSN/ISBN: 2381-8549, 9781538662496
- DOI: 10.1109/ICIP.2019.8803358
- Further publication details on publisher web site
- Durham Research Online (DRO) - may include full text
Author(s) from Durham
Correlation filters (CF) combined with pre-trained convolutional
neural network (CNN) feature extractors have shown
an admirable accuracy and speed in visual object tracking.
However, existing CNN-CF based methods still suffer from
the background interference and boundary effects, even when
a cosine window is introduced. This paper proposes a ranking
based or guided attention approach which can reduce
background interference with only forward propagation. This
ranking stores several convolution kernels and scores them.
Subsequently, a convolutional Long Short Time Memory
network (ConvLSTM) is used to update this ranking, which
makes it more robust to the variation and occlusion. Moreover,
a part-based multi-channel convolutional tracker is
proposed to obtain the final response map. Our extensive
experiments on established benchmark datasets show comparable
performance against contemporary tracking approaches.