Visual Tracking Using Attention-Modulated Disintegration and Integration

Jongwon Choi; Hyung Jin Chang; Jiyeoup Jeong; Yiannis Demiris; Jin Young Choi

doi:10.1109/CVPR.2016.468

Visual Tracking Using Attention-Modulated Disintegration and Integration

Jongwon Choi, Hyung Jin Chang, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi

Computer Science

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

143 Citations (Scopus)

Abstract

In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types. In the integration stage it recombines the units to memorize and recognize the target object effectively. With respect to the elementary trackers, we present a novel attentional feature-based correlation filter (AtCF) that focuses on distinctive attentional features. The effectiveness of the proposed algorithm is validated through experimental comparison with state-of-theart methods on widely-used tracking benchmark datasets.

Original language	English
Title of host publication	2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher	IEEE Computer Society
Pages	4321-4330
ISBN (Print)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.468
Publication status	Published - 26 Jun 2016
Event	29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016 - Las Vegas, Nevada, United States Duration: 26 Jun 2016 → 1 Jul 2016

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016
Country/Territory	United States
City	Las Vegas, Nevada
Period	26/06/16 → 1/07/16

Access to Document

10.1109/CVPR.2016.468

Cite this

@inproceedings{af9b54a1679742bdb02dcddba07d5025,

title = "Visual Tracking Using Attention-Modulated Disintegration and Integration",

abstract = "In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types. In the integration stage it recombines the units to memorize and recognize the target object effectively. With respect to the elementary trackers, we present a novel attentional feature-based correlation filter (AtCF) that focuses on distinctive attentional features. The effectiveness of the proposed algorithm is validated through experimental comparison with state-of-theart methods on widely-used tracking benchmark datasets.",

author = "Jongwon Choi and Chang, {Hyung Jin} and Jiyeoup Jeong and Yiannis Demiris and Choi, {Jin Young}",

year = "2016",

month = jun,

day = "26",

doi = "10.1109/CVPR.2016.468",

language = "English",

isbn = "9781467388504",

pages = "4321--4330",

booktitle = "2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",

publisher = "IEEE Computer Society",

address = "United States",

note = "29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

}

Choi, J, Chang, HJ, Jeong, J, Demiris, Y & Choi, JY 2016, Visual Tracking Using Attention-Modulated Disintegration and Integration. in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, pp. 4321-4330, 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016, Las Vegas, Nevada, United States, 26/06/16. https://doi.org/10.1109/CVPR.2016.468

TY - GEN

T1 - Visual Tracking Using Attention-Modulated Disintegration and Integration

AU - Choi, Jongwon

AU - Chang, Hyung Jin

AU - Jeong, Jiyeoup

AU - Demiris, Yiannis

AU - Choi, Jin Young

PY - 2016/6/26

Y1 - 2016/6/26

N2 - In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types. In the integration stage it recombines the units to memorize and recognize the target object effectively. With respect to the elementary trackers, we present a novel attentional feature-based correlation filter (AtCF) that focuses on distinctive attentional features. The effectiveness of the proposed algorithm is validated through experimental comparison with state-of-theart methods on widely-used tracking benchmark datasets.

AB - In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types. In the integration stage it recombines the units to memorize and recognize the target object effectively. With respect to the elementary trackers, we present a novel attentional feature-based correlation filter (AtCF) that focuses on distinctive attentional features. The effectiveness of the proposed algorithm is validated through experimental comparison with state-of-theart methods on widely-used tracking benchmark datasets.

U2 - 10.1109/CVPR.2016.468

DO - 10.1109/CVPR.2016.468

M3 - Conference contribution

SN - 9781467388504

SP - 4321

EP - 4330

BT - 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

PB - IEEE Computer Society

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Visual Tracking Using Attention-Modulated Disintegration and Integration

Abstract

Conference

Access to Document

Fingerprint

Cite this