Hedged Deep Tracking

被引：616

作者：

Qi, Yuankai ^{[1
]}

Zhang, Shengping ^{[1
]}

Qin, Lei ^{[2
]}

Yao, Hongxun ^{[1
]}

Huang, Qingming ^{[1
,3
]}

Lim, Jongwoo ^{[4
]}

Yang, Ming-Hsuan ^{[5
]}

机构：

[1] Harbin Inst Technol, Harbin, Peoples R China

[2] Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China

[3] Univ Chinese Acad Sci, Beijing, Peoples R China

[4] Hanyang Univ, Seoul, South Korea

[5] Univ Calif Merced, Merced, CA USA

来源：

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2016年

基金：

美国国家科学基金会; 中国国家自然科学基金;

关键词：

D O I：

10.1109/CVPR.2016.466

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In recent years, several methods have been developed to utilize hierarchical features learned from a deep convolutional neural network (CNN) for visual tracking. However, as features from a certain CNN layer characterize an object of interest from only one aspect or one level, the performance of such trackers trained with features from one layer (usually the second to last layer) can be further improved. In this paper, we propose a novel CNN based tracking framework, which takes full advantage of features from different CNN layers and uses an adaptive Hedge method to hedge several CNN based trackers into a single stronger one. Extensive experiments on a benchmark dataset of 100 challenging image sequences demonstrate the effectiveness of the proposed algorithm compared to several state-of-the-art trackers.

引用

页码：4303 / 4311

页数：9