Faster-ADNet for Visual Tracking

doi:10.1587/transinf.2018EDL8214

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

	Faster-ADNet for Visual Tracking
	Zhang, Tiansa 1,2; Huo, Chunlei2 ; Zhou, Zhiqiang 1; Wang, Bo 1
发表期刊	IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
ISSN	1745-1361
	2019-03-01
卷号	E102D 期号:3 页码:684-687
通讯作者	Zhou, Zhiqiang(zhzhzhou@bit.edu.cn)
摘要	By taking advantages of deep learning and reinforcement learning, ADNet (Action Decision Network) outperforms other approaches. However, its speed and performance are still limited by factors such as unreliable confidence score estimation and redundant historical actions. To address the above limitations, a faster and more accurate approach named Faster-ADNet is proposed in this paper. By optimizing the tracking process via a status re-identification network, the proposed approach is more efficient and 6 times faster than ADNet. At the same time, the accuracy and stability are enhanced by historical actions removal. Experiments demonstrate the advantages of Faster-ADNet.
关键词	visual tracking deep learning status re-identification
DOI	10.1587/transinf.2018EDL8214
关键词[WOS]	OBJECT TRACKING
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[L172053] ; Beijing Natural Science Foundation[L172053]
项目资助者	Beijing Natural Science Foundation
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000460116300037
出版者	IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
七大方向——子方向分类	目标检测、跟踪与识别
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/24999
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
通讯作者	Zhou, Zhiqiang
作者单位	1.Beijing Inst Technol, Sch Automat, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
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	Zhang, Tiansa,Huo, Chunlei,Zhou, Zhiqiang,et al. Faster-ADNet for Visual Tracking[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,2019,E102D(3):684-687.
APA	Zhang, Tiansa,Huo, Chunlei,Zhou, Zhiqiang,&Wang, Bo.(2019).Faster-ADNet for Visual Tracking.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,E102D(3),684-687.
MLA	Zhang, Tiansa,et al."Faster-ADNet for Visual Tracking".IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E102D.3(2019):684-687.