论文标题
TransTrack：带有变压器的多个对象跟踪
TransTrack: Multiple Object Tracking with Transformer
论文作者
论文摘要
在这项工作中，我们提出了TransTrack，这是一个简单但有效的方案，可以解决多个对象跟踪问题。 TransTrack利用Transformer体系结构，这是一种基于注意的查询键机制。它将对象功能从上一个帧中应用于当前帧的查询，并引入了一组学习的对象查询以启用检测新启用对象。它通过单镜头完成对象检测和对象关联来构建一种新颖的关节检测和跟踪范式，从而简化了逐探测方法中复杂的多步骤设置。在MOT17和MOT20基准上，TransTrack分别达到74.5 \％和64.5 \％MOTA，与最新方法具有竞争力。我们希望TransTrack为多个对象跟踪提供新颖的视角。该代码可在：\ url {https://github.com/peizesun/transtrack}中获得。
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object features from the previous frame as a query of the current frame and introduces a set of learned object queries to enable detecting new-coming objects. It builds up a novel joint-detection-and-tracking paradigm by accomplishing object detection and object association in a single shot, simplifying complicated multi-step settings in tracking-by-detection methods. On MOT17 and MOT20 benchmark, TransTrack achieves 74.5\% and 64.5\% MOTA, respectively, competitive to the state-of-the-art methods. We expect TransTrack to provide a novel perspective for multiple object tracking. The code is available at: \url{https://github.com/PeizeSun/TransTrack}.
