P2T: Part-to-Target Tracking via Deep Regression Learning

doi:10.1109/TIP.2018.2813166

	P2T: Part-to-Target Tracking via Deep Regression Learning
	Gao, Junyu1,2 ; Zhang, Tianzhu1,2 ; Yang, Xiaoshan1,2 ; Xu, Changsheng1,2
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2018-06
卷号	27 期号:6 页码:3074-3086
文章类型	Article
摘要	Most existing part-based tracking methods are part-to-part trackers, which usually have two separated steps including the part matching and target localization. Different from existing methods, in this paper, we propose a novel part-to-target (P2T) tracker in a unified fashion by inferring target location from parts directly. To achieve this goal, we propose a novel deep regression model for P2T regression in an end-to-end framework via convolutional neural networks. The proposed model is designed not only to exploit the part context information to preserve object spatial layout structure, but also to learn part reliability to emphasize part importance for the robust P2T regression. We evaluate the proposed tracker on four challenging benchmark sequences, and extensive experimental results demonstrate that our method performs favorably against state-of-the-art trackers because of the powerful capacity of the proposed deep regression model.
关键词	Visual Tracking Deep Learning Part-based Tracker
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TIP.2018.2813166
关键词[WOS]	ROBUST VISUAL TRACKING ; OBJECT TRACKING ; BENCHMARK ; MODEL
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61432019 ; Key Research Program of Frontier Sciences, CAS(QYZDJ-SSW-JSC039) ; Beijing Natural Science Foundation(4172062) ; 61572498 ; 61532009 ; 61702511 ; 61572296)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000428930600014
引用统计	被引频次：41[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/173211/21999
专题	多模态人工智能系统全国重点实验室_多媒体计算
作者单位	1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Gao, Junyu,Zhang, Tianzhu,Yang, Xiaoshan,et al. P2T: Part-to-Target Tracking via Deep Regression Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(6):3074-3086.
APA	Gao, Junyu,Zhang, Tianzhu,Yang, Xiaoshan,&Xu, Changsheng.(2018).P2T: Part-to-Target Tracking via Deep Regression Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(6),3074-3086.
MLA	Gao, Junyu,et al."P2T: Part-to-Target Tracking via Deep Regression Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.6(2018):3074-3086.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
P2T Part-to-Target T（5803KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览