PACR: Pixel Attention in Classification and Regression for Visual Object Tracking

Da Li, Haoxiang Chai, Qin Wei (), Yao Zhang and Yunhan Xiao
Additional contact information
Da Li: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
Haoxiang Chai: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
Qin Wei: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
Yao Zhang: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
Yunhan Xiao: School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China

Mathematics, 2023, vol. 11, issue 6, 1-14

Abstract: Anchor-free-based trackers have achieved remarkable performance in single visual object tracking in recent years. Most anchor-free trackers consider the rectangular fields close to the target center as the positive sample used in the training phase, while they always use the maximum of the corresponding map to determine the location of the target in the tracking phase. Thus, this will make the tracker inconsistent between the training and tracking phase. To solve this problem, we propose a pixel-attention module (PAM), which ensures the consistency of the training and tracking phase through a self-attention module. Moreover, we put forward a new refined branch named Acc branch to inherit the benefit of the PAM. The score of Acc branch can tune the classification and the regression of the tracking target more precisely. We conduct extensive experiments on challenging benchmarks such as VOT2020, UAV123, DTB70, OTB100, and a large-scale benchmark LaSOT. Compared with other anchor-free trackers, our tracker gains excellent performance in small-scale datasets. In UAV benchmarks such as UAV123 and DTB70, the precision of our tracker increases 4.3% and 1.8%, respectively, compared with the SOTA in anchor-free trackers.

Keywords: object tracking; anchor free; pixel attention; refined branch (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/6/1406/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/6/1406/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:6:p:1406-:d:1097184

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().