We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transformer blocks, or graph networks. Conventional MOT models are built upon the multi-step modules listed above, and thus the computational cost is high. Our proposed end-to-end MOT model, \textit{TicrossNet}, is composed of a base detector and a cross-attention module only. As a result, the overhead of tracking does not increase significantly even when the number of instances ($N_t$) increases. We show that TicrossNet runs \textit{in real-time}; specifically, it achieves 32.6 FPS on MOT17 and 31.0 FPS on MOT20 (Tesla V100), which includes as many as $>$100 instances per frame. We also demonstrate that TicrossNet is robust to $N_t$; thus, it does not have to change the size of the base detector, depending on $N_t$, as is often done by other models for real-time processing.

翻译：我们提出一个概念上简单、因而运行快速的多目标跟踪模型，该模型无需任何附加模块，如卡尔曼滤波器、匈牙利算法、Transformer 模块或图网络。传统多目标跟踪模型基于上述多步骤模块构建，因此计算成本较高。我们所提出的端到端多目标跟踪模型 \textit{TicrossNet} 仅由一个基础检测器和一个交叉注意力模块组成。因此，即使实例数量（$N_t$）增加，跟踪带来的额外开销也不会显著增长。我们证明 TicrossNet 能够实时运行；具体而言，它在 MOT17 上达到 32.6 FPS，在 MOT20 上达到 31.0 FPS（Tesla V100），且每个帧包含多达 $>100$ 个实例。我们还证明 TicrossNet 对 $N_t$ 具有鲁棒性；因此，它无需像其他模型为实现实时处理而常做的那样，根据 $N_t$ 改变基础检测器的尺寸。