Deep-neural-networks-based online visual tracking methods have achieved state-of-the-art results. One of the core components of these methods is the memory pool, in which a number of samples consisting of image patches and the corresponding labels are stored to update the online tracking network. Hence, the mechanism of updating the stored samples determines the performance of the tracking method. In this paper, a novel memory mechanism is proposed to control the writing and reading accesses of the memory pool using credit assignment network ${H}$ , which learns features of the target object. This memory mechanism comprises the writing and reading mechanisms. In the writing mechanism, network ${H}$ produces credits for the current tracked object and the samples in the memory pool. This ensures that the reliable samples are written into the memory pool and the unreliable samples are replaced if the memory pool is full. In the reading mechanism, network ${H}$ assigns an importance score to each sample selected to update the online tracking network. The state-of-the-art tracking methods with and without the proposed memory mechanism are evaluated on the CVPR2013 and OTB100 benchmarks. The experimental results demonstrated that the proposed memory mechanism improves tracking performance significantly.

中文翻译：

---

具有深度神经网络的判别视觉跟踪算法的记忆机制

基于深度神经网络的在线视觉跟踪方法已经取得了最先进的结果。这些方法的核心组件之一是内存池，其中存储了许多由图像块和相应标签组成的样本，以更新在线跟踪网络。因此，更新存储样本的机制决定了跟踪方法的性能。在本文中，提出了一种新的内存机制来使用信用分配网络控制内存池的写入和读取访问 ${H}$ ，学习目标对象的特征。该存储机制包括写入和读取机制。在写入机制上，网络 ${H}$ 为当前跟踪的对象和内存池中的样本生成积分。这样可以确保可靠样本写入内存池，如果内存池已满，则替换不可靠样本。在阅读机制中，网络 ${H}$ 为每个选择的样本分配一个重要性分数，以更新在线跟踪网络。在 CVPR2013 和 OTB100 基准测试中评估了使用和不使用建议的内存机制的最先进的跟踪方法。实验结果表明，所提出的记忆机制显着提高了跟踪性能。