A Ranking Based Attention Approach for Visual Tracking

Shenhui Peng; Sei Ichiro Kamata; Toby P. Breckon

doi:10.1109/ICIP.2019.8803358

A Ranking Based Attention Approach for Visual Tracking

Shenhui Peng, Sei Ichiro Kamata, Toby P. Breckon

Graduate School of Information, Production and Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

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.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Publisher	IEEE Computer Society
Pages	3073-3077
Number of pages	5
ISBN (Electronic)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8803358
Publication status	Published - 2019 Sep
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China Duration: 2019 Sep 22 → 2019 Sep 25

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2019-September
ISSN (Print)	1522-4880

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country	Taiwan, Province of China
City	Taipei
Period	19/9/22 → 19/9/25

Keywords

ConvLSTM
Convolutional tracker
Ranking based attention
Visual tracking

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2019.8803358

Fingerprint Dive into the research topics of 'A Ranking Based Attention Approach for Visual Tracking'. Together they form a unique fingerprint.

Cite this

A Ranking Based Attention Approach for Visual Tracking. / Peng, Shenhui; Kamata, Sei Ichiro; Breckon, Toby P.

2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. IEEE Computer Society, 2019. p. 3073-3077 8803358 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Peng, S, Kamata, SI & Breckon, TP 2019, A Ranking Based Attention Approach for Visual Tracking. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8803358, Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, IEEE Computer Society, pp. 3073-3077, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, Province of China, 19/9/22. https://doi.org/10.1109/ICIP.2019.8803358

@inproceedings{435e042b623f4c5ba6cd7074f6af61b9,

title = "A Ranking Based Attention Approach for Visual Tracking",

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.",

keywords = "ConvLSTM, Convolutional tracker, Ranking based attention, Visual tracking",

author = "Shenhui Peng and Kamata, {Sei Ichiro} and Breckon, {Toby P.}",

note = "Funding Information: This work was supported by JSPS KAKENHI Grant Number 18K11380.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICIP.2019.8803358",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3073--3077",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

}

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.

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 -