Holistic object representation-based trackers suffer from performance drop under large appearance change such as deformation and occlusion. In this work, we propose a dynamic part-based tracker and constantly update the target part representation to adapt to object appearance change. Moreover, we design an attention-guided part localization network to directly predict the target part locations, and determine the final bounding box with the distribution of target parts. Our proposed tracker achieves promising results on various benchmarks: VOT2018, OTB100 and GOT-10k

翻译：整体目标代表制跟踪器在变形和隔离等大规模外观变化(如变形和隔离)下因性能下降而受损。在这项工作中,我们提议建立一个动态的半基跟踪器,并不断更新目标代表部分,以适应物体外观变化。此外,我们设计了一个关注引导部分本地化网络,以直接预测目标部分的位置,确定带有目标部分分布的最终捆绑框。我们提议的跟踪器在各种基准(VOT2018、OTB100和MAT-10k)上取得了可喜的成果。