Skip navigation
Skip navigation

Not All Negatives Are Equal: Learning to Track With Multiple Background Clusters

Zhu, Gao; Porikli, Fatih; Li, Hongdong


Conventional tracking-by-detection approaches for visual object tracking often assume that the task at hand is a binary foreground-versus-background classification problem where the background is a single, generic, and all-inclusive class. In contrast, here we argue that the background appearance for the most part possesses a more complicated structure that will benefit from further partitioning into multiple contextual clusters. Our observation is that, although the background class is...[Show more]

CollectionsANU Research Publications
Date published: 2016-10-05
Type: Journal article
Source: IEEE Transactions on Circuits and Systems for Video Technology
DOI: 10.1109/TCSVT.2016.2615518
Access Rights: Open Access


File Description SizeFormat Image
01_Zhu_Not_All_Negatives_Are_Equal%3A_2018.pdf6.12 MBAdobe PDFThumbnail

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator