A Ranking Based Attention Approach for Visual Tracking

Shenhui Peng, Sei Ichiro Kamata, Toby P. Breckon

研究成果: Conference contribution

1 引用 (Scopus)

抜粋

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.

元の言語English
ホスト出版物のタイトル2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
出版者IEEE Computer Society
ページ3073-3077
ページ数5
ISBN(電子版)9781538662496
DOI
出版物ステータスPublished - 2019 9
イベント26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
継続期間: 2019 9 222019 9 25

出版物シリーズ

名前Proceedings - International Conference on Image Processing, ICIP
2019-September
ISSN(印刷物)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
Taiwan, Province of China
Taipei
期間19/9/2219/9/25

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

フィンガープリント A Ranking Based Attention Approach for Visual Tracking' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Peng, S., Kamata, S. I., & Breckon, T. P. (2019). A Ranking Based Attention Approach for Visual Tracking. : 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings (pp. 3073-3077). [8803358] (Proceedings - International Conference on Image Processing, ICIP; 巻数 2019-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2019.8803358