Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2010.5539816
Title: Visual tracking via weakly supervised learning from multiple imperfect oracles
Authors: Zhong, B.
Yao, H.
Chen, S.
Ji, R.
Yuan, X. 
Liu, S.
Gao, W.
Issue Date: 2010
Source: Zhong, B., Yao, H., Chen, S., Ji, R., Yuan, X., Liu, S., Gao, W. (2010). Visual tracking via weakly supervised learning from multiple imperfect oracles. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 1323-1330. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2010.5539816
Abstract: Long-term persistent tracking in ever-changing environments is a challenging task, which often requires addressing difficult object appearance update problems. To solve them, most top-performing methods rely on online learning-based algorithms. Unfortunately, one inherent problem of online learning-based trackers is drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, we consider visual tracking in a novel weakly supervised learning scenario where (possibly noisy) labels but no ground truth are provided by multiple imperfect oracles (i.e., trackers), some of which may be mediocre. A probabilistic approach is proposed to simultaneously infer the most likely object position and the accuracy of each tracker. Moreover, an online evaluation strategy of trackers and a heuristic training data selection scheme are adopted to make the inference more effective and fast. Consequently, the proposed method can avoid the pitfalls of purely single tracking approaches and get reliable labeled samples to incrementally update each tracker (if it is an appearance-adaptive tracker) to capture the appearance changes. Extensive comparing experiments on challenging video sequences demonstrate the robustness and effectiveness of the proposed method. ©2010 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/72173
ISBN: 9781424469840
ISSN: 10636919
DOI: 10.1109/CVPR.2010.5539816
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

21
checked on Dec 7, 2017

WEB OF SCIENCETM
Citations

12
checked on Nov 22, 2017

Page view(s)

25
checked on Dec 17, 2017

Google ScholarTM

Check

Altmetric


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