Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning | |
Gao, Jin1; Wang, Qiang1; Xing, Junliang1; Ling, Haibin2; Hu, Weiming1; Maybank, Stephen3 | |
刊名 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
2020-04-01 | |
卷号 | 42期号:4页码:939-955 |
关键词 | Task analysis Correlation Target tracking Probability distribution Visualization Collaboration Visual tracking Gaussian processes correlation filters transfer learning tracking-by-fusion |
ISSN号 | 0162-8828 |
DOI | 10.1109/TPAMI.2018.2889070 |
通讯作者 | Hu, Weiming(wmhu@nlpr.ia.ac.cn) |
英文摘要 | This paper presents a new Gaussian Processes (GPs)-based particle filter tracking framework. The framework non-trivially extends Gaussian process regression (GPR) to transfer learning, and, following the tracking-by-fusion strategy, integrates closely two tracking components, namely a GPs component and a CFs one. First, the GPs component analyzes and models the probability distribution of the object appearance by exploiting GPs. It categorizes the labeled samples into auxiliary and target ones, and explores unlabeled samples in transfer learning. The GPs component thus captures rich appearance information over object samples across time. On the other hand, to sample an initial particle set in regions of high likelihood through the direct simulation method in particle filtering, the powerful yet efficient correlation filters (CFs) are integrated, leading to the CFs component. In fact, the CFs component not only boosts the sampling quality, but also benefits from the GPs component, which provides re-weighted knowledge as latent variables for determining the impact of each correlation filter template from the auxiliary samples. In this way, the transfer learning based fusion enables effective interactions between the two components. Superior performance on four object tracking benchmarks (OTB-2015, Temple-Color, and VOT2015/2016), and in comparison with baselines and recent state-of-the-art trackers, has demonstrated clearly the effectiveness of the proposed framework. |
资助项目 | Natural Science Foundation of China[61602478] ; Natural Science Foundation of China[61751212] ; Natural Science Foundation of China[61472421] ; Beijing Natural Science Foundation[L172051] ; NSFC-general technology collaborative Fund for basic research[U1636218] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC040] ; CAS External cooperation key project ; Research Project of ForwardX Robotics, Inc. ; US NSF[1350521] ; US NSF[1618398] ; US NSF[1814745] |
WOS关键词 | VISUAL TRACKING ; OBJECT TRACKING ; NETWORKS |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE COMPUTER SOC |
WOS记录号 | WOS:000526541100011 |
资助机构 | Natural Science Foundation of China ; Beijing Natural Science Foundation ; NSFC-general technology collaborative Fund for basic research ; Key Research Program of Frontier Sciences, CAS ; CAS External cooperation key project ; Research Project of ForwardX Robotics, Inc. ; US NSF |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/38907] |
专题 | 自动化研究所_模式识别国家重点实验室_视频内容安全团队 |
通讯作者 | Hu, Weiming |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 2.Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA 3.Birkbeck Coll, Dept Comp Sci & Informat Syst, Malet St, London WC1E 7HX, England |
推荐引用方式 GB/T 7714 | Gao, Jin,Wang, Qiang,Xing, Junliang,et al. Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2020,42(4):939-955. |
APA | Gao, Jin,Wang, Qiang,Xing, Junliang,Ling, Haibin,Hu, Weiming,&Maybank, Stephen.(2020).Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,42(4),939-955. |
MLA | Gao, Jin,et al."Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 42.4(2020):939-955. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论