The rich spatio-temporal information is crucial to capture the complicated
target appearance variations in visual tracking. However, most top-performing
tracking algorithms rely on many hand-crafted components for spatio-temporal
information aggregation. Consequently, the spatio-temporal information is far
away from being fully explored. To alleviate this issue, we propose an adaptive
tracker with spatio-temporal transformers (named AQATrack), which adopts simple
autoregressive queries to effectively learn spatio-temporal information without
many hand-designed components. Firstly, we introduce a set of learnable and
autoregressive queries to capture the instantaneous target appearance changes
in a sliding window fashion. Then, we design a novel attention mechanism for
the interaction of existing queries to generate a new query in current frame.
Finally, based on the initial target template and learnt autoregressive
queries, a spatio-temporal information fusion module (STM) is designed for
spatiotemporal formation aggregation to locate a target object. Benefiting from
the STM, we can effectively combine the static appearance and instantaneous
changes to guide robust tracking. Extensive experiments show that our method
significantly improves the tracker's performance on six popular tracking
benchmarks: LaSOT, LaSOText, TrackingNet, GOT-10k, TNL2K, and UAV123.

提出了一个自适应的带有时空转换器的跟踪器（命名为 AQATrack），通过采用简单的自回归查询来有效地学习时空信息，从而改善了目标跟踪中手动设计组件过多的问题，并设计了新颖的注意力机制来生成当前帧的新查询，最终使用空间 - 时间信息融合模块（STM）定位目标对象，实验结果表明，该方法在六个流行的跟踪基准上显著提高了跟踪器的性能：LaSOT、LaSOText、TrackingNet、GOT-10k、TNL2K 和 UAV123。