Visual tracking via weakly supervised learning from multiple imperfect oracles

CORC > 厦门大学 > 数学科学－已发表论文

	Visual tracking via weakly supervised learning from multiple imperfect oracles
	Zhong, Bineng ; Yao, Hongxun ; Chen, Sheng ; Ji, Rongrong ; Chin, Tat-Jun ; Wang, Hanzi ; Zhong BN(钟必能) ; Ji RR(纪荣嵘) ; Wang HZ(王菡子)
刊名	http://dx.doi.org/10.1016/j.patcog.2013.10.002
	2014
英文摘要	Natural Science Foundation of China [61202299, 61170179]; China Postdoctoral Science Foundation [2011M501081]; Fundamental Research Funds for the Central Universities [JB-ZR1219]; Scientific Research Foundation of Huaqiao University [11BS109]; Xiamen Science & Technology Planning Project of China [3502Z20116005]; Natural Science Foundation of Fujian Province [2013J05092]; Notwithstanding many years of progress, visual tracking is still a difficult but important problem. Since most top-performing tracking methods have their strengths and weaknesses and are suited for handling only a certain type of variation, one of the next challenges is to integrate all these methods and address the problem of long-term persistent tracking in ever-changing environments. Towards this goal, 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., different trackers). These trackers naturally have intrinsic diversity due to their different design strategies, and we propose a probabilistic method to simultaneously infer the most likely object position by considering the outputs of all trackers, and estimate the accuracy of each tracker. An online evaluation strategy of trackers and a heuristic training data selection scheme are adopted to make the inference more effective and efficient. Consequently, the proposed method can avoid the pitfalls of purely single tracking methods and get reliably labeled samples to incrementally update each tracker (if it is an appearance-adaptive tracker) to capture the appearance changes. Extensive experiments on challenging video sequences demonstrate the robustness and effectiveness of the proposed method. Crown Copyright (C) 2013 Published by Elsevier Ltd. All rights reserved.
语种	英语
出版者	ELSEVIER SCI LTD
内容类型	期刊论文
源URL	[http://dspace.xmu.edu.cn/handle/2288/91365]
专题	数学科学－已发表论文
推荐引用方式 GB/T 7714	Zhong, Bineng,Yao, Hongxun,Chen, Sheng,et al. Visual tracking via weakly supervised learning from multiple imperfect oracles[J]. http://dx.doi.org/10.1016/j.patcog.2013.10.002,2014.
APA	Zhong, Bineng.,Yao, Hongxun.,Chen, Sheng.,Ji, Rongrong.,Chin, Tat-Jun.,...&王菡子.(2014).Visual tracking via weakly supervised learning from multiple imperfect oracles.http://dx.doi.org/10.1016/j.patcog.2013.10.002.
MLA	Zhong, Bineng,et al."Visual tracking via weakly supervised learning from multiple imperfect oracles".http://dx.doi.org/10.1016/j.patcog.2013.10.002 (2014).