.png){kind=icon}
返回
Multi-task l0 gradient minimization for visual tracking
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2014.12.021.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In most object tracking algorithms based on sparse representation, the optimization problem is often formulated as an l(1) or l(2) minimization problem, because its primal l(0)-norm minimization problem is NP-hard. In this paper, a visual tracking method is proposed based upon l(0)-norm minimization which directly seeks solution to the primal l(0) problem. To avoid solving a large number of l(0) minimization problems, we introduce to encode all samples simultaneously in a multi-task manner, which means that the number of minimization problem to be solved is only one, and an algorithm is presented to solve the minimization problem. Our tracking algorithm is then implemented under the framework of particle filter. Experiments on different challenging video sequences demonstrate that our method can achieve robust tracking results. (C) 2014 Elsevier B.V. All rights reserved.
Keyword:
l(0-)norm minimization
l(1)-norm minimization
Visual tracking
Multi-task
Sparse coding
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Role of microRNA-21 in the formation of insulin-producing cells from pancreatic progenitor cells
PREAI
分享收藏Improvement of the silver/silver chloride reference electrode and its application to pH measurement.png)
Talanta
TalantaIF0
PREAI
分享收藏
分享收藏
查看更多内容