论文标题
艺术家：自回旋轨迹介绍和跟踪得分
ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
论文作者
论文摘要
在线多个对象跟踪（MOT）框架中的核心组件之一是将新检测与现有轨迹相关联，通常是通过评分函数完成的。尽管MOT取得了长足的进步，但设计可靠的评分功能仍然是一个挑战。在本文中，我们引入了一种概率自回旋生成模型，以通过直接测量轨道代表自然运动的可能性来评分轨道提案。我们模型的一个关键属性是它能够产生部分观察结果的曲目的多个可能未来。这使我们不仅可以在检测器未能检测到某些对象很长一段时间内（例如，由于遮挡，通过采样轨迹，以便对误差造成的差距）进行绘制，因此我们不仅可以得分轨迹，而且可以有效地维护现有的轨迹。我们的实验证明了我们在几个MOT基准数据集上进行评分和介入曲目的方法的有效性。另外，我们通过使用它在人类运动预测的具有挑战性的任务中产生未来的表示来表明生成模型的普遍性。
One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets, typically done via a scoring function. Despite the great advances in MOT, designing a reliable scoring function remains a challenge. In this paper, we introduce a probabilistic autoregressive generative model to score tracklet proposals by directly measuring the likelihood that a tracklet represents natural motion. One key property of our model is its ability to generate multiple likely futures of a tracklet given partial observations. This allows us to not only score tracklets but also effectively maintain existing tracklets when the detector fails to detect some objects even for a long time, e.g., due to occlusion, by sampling trajectories so as to inpaint the gaps caused by misdetection. Our experiments demonstrate the effectiveness of our approach to scoring and inpainting tracklets on several MOT benchmark datasets. We additionally show the generality of our generative model by using it to produce future representations in the challenging task of human motion prediction.
