A Ranking based Attention Approach for Visual Tracking

Peng, S.; Kamata, S.; Breckon, T.P.

Abstract

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.

Citation

Peng, S., Kamata, S., & Breckon, T. (2019, September). A Ranking based Attention Approach for Visual Tracking. Presented at 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 26th IEEE International Conference on Image Processing (ICIP)
• Start Date: Sep 22, 2019
• End Date: Sep 25, 2019
• Acceptance Date: Apr 30, 2019
• Publication Date: Sep 1, 2019
• Deposit Date: Jun 4, 2019
• Publicly Available Date: Nov 12, 2019
• Pages: 3073-3077
• Series ISSN: 2381-8549
• Book Title: 2019 IEEE International Conference on Image Processing (ICIP) ; proceedings.
• DOI: https://doi.org/10.1109/icip.2019.8803358
• Public URL: https://durham-repository.worktribe.com/output/1142059