Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/77412
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Learning compact binary codes for visual tracking
Author: Li, X.
Shen, C.
Dick, A.
Van Den Hengel, A.
Citation: Proceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 2419-2426
Publisher: IEEE
Publisher Place: United States
Issue Date: 2013
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9780769549897
ISSN: 1063-6919
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)
Statement of
Responsibility: 
Xi Li, Chunhua Shen, Anthony Dick, Anton van den Hengel
Abstract: A key problem in visual tracking is to represent the appearance of an object in a way that is robust to visual changes. To attain this robustness, increasingly complex models are used to capture appearance variations. However, such models can be difficult to maintain accurately and efficiently. In this paper, we propose a visual tracker in which objects are represented by compact and discriminative binary codes. This representation can be processed very efficiently, and is capable of effectively fusing information from multiple cues. An incremental discriminative learner is then used to construct an appearance model that optimally separates the object from its surrounds. Furthermore, we design a hypergraph propagation method to capture the contextual information on samples, which further improves the tracking accuracy. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.
Keywords: Compact Binary Codes; Random Forest; Visual Tracking
Rights: ©IEEE
RMID: 0020132963
DOI: 10.1109/CVPR.2013.313
Description (link): http://www.pamitc.org/cvpr13/
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_77412.pdfAccepted version2.46 MBAdobe PDFView/Open


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