Learning attentional recurrent neural network for visual tracking
Learning attentional recurrent neural network for visual tracking
复制标题
DOI：
10.1109/icme.2017.8019422
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Qiurui Wang;C. Yuan;Zhihui Lin
中科院分区：
文献类型：
--
作者：
Qiurui Wang;C. Yuan;Zhihui Lin
我们提出了一种新颖的用于视觉跟踪的在线注意力循环神经网络（ARNN）模型，该模型利用边界框内卷积神经网络（CNN）的特征图来识别此目标是否是先前帧中出现的目标。对目标的不同部分和不同尺度的对象特征都采用了注意力机制。前者的注意力模型能够选择重要区域以更好地跟踪目标，而后者则学习对多尺度特征进行加权以实现准确的对象定位。我们将循环网络与基于区域和基于尺度的注意力机制联合训练。实验中的出色表现验证了我们所提出的ARNN的有效性，并表明ARNN优于最先进的跟踪方法。
We propose a novel online Attentional Recurrent Neural Network (ARNN) model for visual tracking, which exploits the feature maps of Convolutional Neural Network (CNN) inside a bounding box to identify whether this target is the one appeared in previous frames. Attention mechanism is adopted for both different parts of targets and different scales of object features. The former attention model is able to select important regions to better trace the target while the latter one learns to weight the multiple scale features for accurate object location. We jointly train the recurrent network with the region based and scale based attention mechanism. The outstanding performances in the experiments validate the effectiveness of our proposed ARNN and show that ARNN outperforms the state-of-the-art tracking methods.