Global-local feature-mixed network with template update for visual tracking

Li Zhao, Chenxiang Fan, Min Li, Zhonglong Zheng, Xiaoqin Zhang

Abstract: Highlights•A new tracking model blends global and local information, emphasizing local features.•The residual Transformer-based tracker augments features across multiple layers, enhancing robustness.•The tracker uses a template update strategy that enlarges the weight of the first frame.•The tracker excels on short- and long-term benchmarks, with fewer parameters and real-time performance.