Hedged Deep Tracking
IEEE Conference Proceedings(2016)
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.
更多查看译文
关键词
image sequences,adaptive hedge method,CNN based tracking framework,feature characterization,CNN layer,visual tracking,deep convolutional neural network learning,hierarchical features,hedged deep tracking
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络