Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Graph mode-based contextual kernels for robust SVM tracking
Author: Li, X.
Dick, A.
Wang, H.
Shen, C.
Van Den Hengel, A.
Citation: 2011 IEEE International Conference on Computer Vision, 2011: pp.1156-1163
Publisher: IEEE
Publisher Place: USA
Issue Date: 2011
Series/Report no.: IEEE International Conference on Computer Vision
ISBN: 9781457711015
ISSN: 1550-5499
Conference Name: International Conference on Computer Vision (13th : 2011 : Barcelona, Spain)
Statement of
Xi Li, Anthony Dick, Hanzi Wang, Chunhua Shen, Anton van den Hengel
Abstract: Visual tracking has been typically solved as a binary classification problem. Most existing trackers only consider the pairwise interactions between samples, and thereby ignore the higher-order contextual interactions, which may lead to the sensitivity to complicated factors such as noises, outliers, background clutters and so on. In this paper, we propose a visual tracker based on support vector machines (SVMs), for which a novel graph mode-based contextual kernel is designed to effectively capture the higher-order contextual information from samples. To do so, we first create a visual graph whose similarity matrix is determined by a baseline visual kernel. Second, a set of high-order contexts are discovered in the visual graph. The problem of discovering these high-order contexts is solved by seeking modes of the visual graph. Each graph mode corresponds to a vertex community termed as a high-order context. Third, we construct a contextual kernel that effectively captures the interaction information between the high-order contexts. Finally, this contextual kernel is embedded into SVMs for robust tracking. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.
Rights: Copyright © 2011 by IEEE.
RMID: 0020111193
DOI: 10.1109/ICCV.2011.6126364
Description (link):
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_70396.pdfRestricted Access3.33 MBAdobe PDFView/Open

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