Online MIL tracking with instance-level semi-supervised learning

CORC > 厦门大学 > 信息技术－已发表论文

	Online MIL tracking with instance-level semi-supervised learning
	Chen, Si ; Li, Shaozi ; Su, Songzhi ; Tian, Qi ; Ji, Rongrong ; Li SZ(李绍滋) ; Su SZ(苏松志) ; Ji RR(纪荣嵘)
刊名	http://dx.doi.org/10.1016/j.neucom.2014.02.031
	2014-09-02
关键词	VISUAL TRACKING PAIRWISE CONSTRAINTS OBJECT DETECTION FEATURES MODEL
英文摘要	National Nature Science Foundation of China [61373076, 61202143, 61201359]; Fundamental Research Funds for the Central Universities [2013121026, 2011121052]; 985 Project of Xiamen University; Natural Science Foundation of Fujian Province [2013J05100, 2012J05126, 2011J01367]; Key Projects Fund of Science and Technology in Xiamen [3502Z20123017]; Research Fund for the Doctoral Program of Higher Education of China [201101211120024]; Special Fund for Developing Shenzhen's Strategic Emerging Industries [JCYJ20120614-164600201]; Hunan Provincial Natural Science Foundation [12JJ2040]; Hunan Province Research Foundation of Education Committee [09A046]; In this paper we propose an online multiple instance boosting algorithm with instance-level semi-supervised learning, termed SemiMILBoost, to achieve robust object tracking. Our work revisits the multiple instance learning (MIL) formulation to alleviate the drifting problem in tracking, which addresses two key issues in the existing MIL based tracking-by-detection methods, i.e., the unselective treatment of instances in the positive bag during weak classifier updating and the lack of object prior knowledge in instance modeling. We tackle both issues in a principled way by using a robust SemiMILBoost algorithm, which treats instances in the positive bag as unlabeled while the ones in the negative bag as negative. To improve the discriminability of weak classifiers online, we iteratively update them with the pseudo-labels and importance of all instances in the positive bag, which are predicted by employing the instance-level semi-supervised learning technique with object prior knowledge during boosting. Experimental results demonstrate that our proposed algorithm outperforms the state-of-the-art tracking methods on several challenging video sequences. (C) 2014 Elsevier B.V. All rights reserved.
语种	英语
出版者	ELSEVIER SCIENCE BV
内容类型	期刊论文
源URL	[http://dspace.xmu.edu.cn/handle/2288/92661]
专题	信息技术－已发表论文
推荐引用方式 GB/T 7714	Chen, Si,Li, Shaozi,Su, Songzhi,et al. Online MIL tracking with instance-level semi-supervised learning[J]. http://dx.doi.org/10.1016/j.neucom.2014.02.031,2014.
APA	Chen, Si.,Li, Shaozi.,Su, Songzhi.,Tian, Qi.,Ji, Rongrong.,...&纪荣嵘.(2014).Online MIL tracking with instance-level semi-supervised learning.http://dx.doi.org/10.1016/j.neucom.2014.02.031.
MLA	Chen, Si,et al."Online MIL tracking with instance-level semi-supervised learning".http://dx.doi.org/10.1016/j.neucom.2014.02.031 (2014).