Correlation filters combined with deep features have delivered impressive results in visual tracking task. However, existing approaches treat deep features produced by different network layers independently, limiting their representation power. To address this issue, this article proposes a multi-task deep dual correlation filters (MDDCF) based method for robust visual tracking. First, a new multi-task learning scheme is designed to take full advantage of the multi-level features of deep networks, where target representation with individual features is regarded as a single task. As such, the interdependencies between different levels of features can be better explored. Second, we reformulate the objective function of the dual correlation filters and propose a new alternating optimization method, allowing joint training of the correlation filters and network parameters. Third, we design an effective object template update scheme which can well capture the target appearance variations. Extensive experimental evaluations on seven benchmark datasets show that the proposed MDDCF tracker performs favorably against state-of-the-art methods.

中文翻译：

---

用于视觉跟踪的多任务深度双相关滤波器


相关滤波器与深度特征相结合，在视觉跟踪任务中取得了令人印象深刻的结果。然而，现有方法独立处理不同网络层产生的深层特征，限制了它们的表示能力。为了解决这个问题，本文提出了一种基于多任务深度双相关滤波器（MDDCF）的鲁棒视觉跟踪方法。首先，设计了一种新的多任务学习方案，以充分利用深度网络的多级特征，其中具有单独特征的目标表示被视为单个任务。因此，可以更好地探索不同级别特征之间的相互依赖性。其次，我们重新制定了双相关滤波器的目标函数，并提出了一种新的交替优化方法，允许联合训练相关滤波器和网络参数。第三，我们设计了一种有效的对象模板更新方案，可以很好地捕获目标外观变化。对七个基准数据集的广泛实验评估表明，所提出的 MDDCF 跟踪器的性能优于最先进的方法。