Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking
	Yang, Yehui1 ; Xie, Yuan1 ; Zhang, Wensheng1 ; Hu, Wenrui1 ; Tan, Yuanhua 2
发表期刊	NEUROCOMPUTING
	2015-07-21
卷号	2015 期号:160 页码:191-205
文章类型	Article
摘要	This paper presents a robust tracking algorithm by sparsely representing the object at both global and local levels. Accordingly, the algorithm is constructed by two complementary parts: Global Coupled Learning (GCL) part and Local Consistencies Ensuring (LCE) part. The global part is a discriminative model which aims to utilize the holistic features of the object via an over-complete global dictionary and classifier, and the dictionary and classifier are coupled learning to construct an adaptive GCL part. While in LCE part, we explore the object's local features by sparsely coding the object patches via a local dictionary, then both temporal and spatial consistencies of the local patches are ensured to refine the tracking results. Moreover, the GCL and LCE parts are integrated into a Bayesian framework for constructing the final tracker. Experiments on fifteen benchmark challenging sequences demonstrate that the proposed algorithm has more effectiveness and robustness than the alternative ten state-of-the-art trackers. (C) 2015 Elsevier B.V. All rights reserved.
关键词	Visual Tracking Sparse Representation Dictionary Learning Coupled Learning Consistency Ensuring
WOS标题词	Science & Technology ; Technology
关键词[WOS]	ROBUST VISUAL TRACKING ; APPEARANCE MODEL ; OBJECT TRACKING ; REPRESENTATION ; REGRESSION
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000354139100017
引用统计	被引频次：14[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/8073
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Karamay Hongyou Software CO LTD, Karamay 834000, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yang, Yehui,Xie, Yuan,Zhang, Wensheng,et al. Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking[J]. NEUROCOMPUTING,2015,2015(160):191-205.
APA	Yang, Yehui,Xie, Yuan,Zhang, Wensheng,Hu, Wenrui,&Tan, Yuanhua.(2015).Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking.NEUROCOMPUTING,2015(160),191-205.
MLA	Yang, Yehui,et al."Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking".NEUROCOMPUTING 2015.160(2015):191-205.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Global Coupled Learn（16651KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载