Please use this identifier to cite or link to this item:
|Title:||Visual tracking via weakly supervised learning from multiple imperfect oracles||Authors:||Zhong, B.
|Issue Date:||2010||Citation:||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.
checked on Dec 4, 2019
WEB OF SCIENCETM
checked on Nov 26, 2019
checked on Dec 1, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.