IEEE Trans Neural Netw Learn Syst. 2022 Nov;33(11):6931-6945. doi: 10.1109/TNNLS.2021.3083933. Epub 2022 Oct 27.
Tracking-by-detection is a very popular framework for single-object tracking that attempts to search the target object within a local search window for each frame. Although such a local search mechanism works well on simple videos, however, it makes the trackers sensitive to extremely challenging scenarios, such as heavy occlusion and fast motion. In this article, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with a tracking-by-detection framework to conduct joint local and global search for robust tracking. Specifically, we extract the features of the target object patch and continuous video frames; then, we concatenate and feed them into a decoder network to generate target-aware global attention maps. More importantly, we resort to adversarial training for better attention prediction. The appearance and motion discriminator networks are designed to ensure its consistency in spatial and temporal views. In the tracking procedure, we integrate target-aware attention with multiple trackers by exploring candidate search regions for robust tracking. Extensive experiments on both short- and long-term tracking benchmark datasets all validated the effectiveness of our algorithm.
基于检测的跟踪是一种非常流行的单目标跟踪框架，它试图在每一帧中对目标对象进行局部搜索窗口搜索。尽管这种局部搜索机制在简单的视频中效果很好，但是它使得跟踪器容易受到极其具有挑战性的场景的影响，例如严重遮挡和快速运动。在本文中，我们提出了一种新颖的通用目标感知注意机制（称为 TANet），并将其与基于检测的跟踪框架集成，以进行联合局部和全局搜索，实现鲁棒跟踪。具体来说，我们提取目标对象补丁和连续视频帧的特征；然后，我们将它们连接起来并将其输入到解码器网络中，以生成目标感知全局注意图。更重要的是，我们借助对抗训练来更好地进行注意力预测。设计外观和运动鉴别器网络以确保其在空间和时间视图上的一致性。在跟踪过程中，我们通过探索候选搜索区域，将目标感知注意力与多个跟踪器集成，以实现鲁棒跟踪。在短和长跟踪基准数据集上的广泛实验均验证了我们算法的有效性。
