Self-supervised discriminative model prediction for visual tracking

Yuan, D; Geng, G; Shu, X; Liu, Q; Chang, X; He, Z; Shi, G

Self-supervised discriminative model prediction for visual tracking

Yuan, D Geng, G Shu, X Liu, Q Chang, X

He, Z Shi, G

Permalink

Publisher:: Springer Nature
Publication Type:: Journal Article
Citation:: Neural Computing and Applications, 2023, pp. 1-12
Issue Date:: 2023-01-01

Closed Access

	Filename	Description	Size
	s00521-023-09348-5.pdf	Published version	1.71 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Yuan, D
dc.contributor.author	Geng, G
dc.contributor.author	Shu, X
dc.contributor.author	Liu, Q
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	He, Z
dc.contributor.author	Shi, G
dc.date.accessioned	2024-02-28T03:47:02Z
dc.date.available	2024-02-28T03:47:02Z
dc.date.issued	2023-01-01
dc.identifier.citation	Neural Computing and Applications, 2023, pp. 1-12
dc.identifier.issn	0941-0643
dc.identifier.issn	1433-3058
dc.identifier.uri	http://hdl.handle.net/10453/175921
dc.description.abstract	The discriminative model prediction (DiMP) object tracking model is an excellent end-to-end tracking framework and have achieved the best results of its time. However, there are two problems with DiMP in the process of actual use: (1) DiMP is prone to interference from similar objects during the tracking process, and (2) DiMP requires a large amount of labeled data for training. In this paper, we propose two methods to enhance the robustness of interference to similar objects in target tracking: multi-scale region search and Gaussian convolution-based response map processing. Simultaneously, aiming at tackling the issue of requiring a large amount of labeled data for training, we implement self-supervised training based on forward-backward tracking for the DiMP tracking method. Furthermore, a new consistency loss function is designed to better self-supervised training. Extensive experiments show that the enhancements implemented in the DiMP tracking framework can bolster its robustness, and the tracker based on self-supervised training has outstanding tracking performance.
dc.language	en
dc.publisher	Springer Nature
dc.relation.ispartof	Neural Computing and Applications
dc.relation.isbasedon	10.1007/s00521-023-09348-5
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering, 1702 Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	4602 Artificial intelligence
dc.subject.classification	4603 Computer vision and multimedia computation
dc.subject.classification	4611 Machine learning
dc.title	Self-supervised discriminative model prediction for visual tracking
dc.type	Journal Article
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1702 Cognitive Sciences
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2024-02-28T03:47:01Z
pubs.publication-status	Published

Abstract:

The discriminative model prediction (DiMP) object tracking model is an excellent end-to-end tracking framework and have achieved the best results of its time. However, there are two problems with DiMP in the process of actual use: (1) DiMP is prone to interference from similar objects during the tracking process, and (2) DiMP requires a large amount of labeled data for training. In this paper, we propose two methods to enhance the robustness of interference to similar objects in target tracking: multi-scale region search and Gaussian convolution-based response map processing. Simultaneously, aiming at tackling the issue of requiring a large amount of labeled data for training, we implement self-supervised training based on forward-backward tracking for the DiMP tracking method. Furthermore, a new consistency loss function is designed to better self-supervised training. Extensive experiments show that the enhancements implemented in the DiMP tracking framework can bolster its robustness, and the tracker based on self-supervised training has outstanding tracking performance.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/175921