TY - GEN
T1 - A Ranking Based Attention Approach for Visual Tracking
AU - Peng, Shenhui
AU - Kamata, Sei Ichiro
AU - Breckon, Toby P.
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number 18K11380.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - 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.
AB - 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.
KW - ConvLSTM
KW - Convolutional tracker
KW - Ranking based attention
KW - Visual tracking
UR - http://www.scopus.com/inward/record.url?scp=85076803839&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076803839&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2019.8803358
DO - 10.1109/ICIP.2019.8803358
M3 - Conference contribution
AN - SCOPUS:85076803839
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 3073
EP - 3077
BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PB - IEEE Computer Society
T2 - 26th IEEE International Conference on Image Processing, ICIP 2019
Y2 - 22 September 2019 through 25 September 2019
ER -