We propose a joint feature and metric learning deep neural network architecture, called the associative affinity network (AAN), as an affinity model for multi-object tracking (MOT) in videos. The AAN learns the associative affinity between tracks and detections across frames in an end-to-end manner. Considering flawed detections, the AAN jointly learns bounding box regression, classification, and affinity regression via the proposed multi-task loss. Contrary to networks that are trained with ranking loss, we directly train a binary classifier to learn the associative affinity of each track-detection pair and use a matching cardinality loss to capture information among candidate pairs. The AAN learns a discriminative affinity model for data association to tackle MOT, and can also perform single-object tracking. Based on the AAN, we propose a simple multi-object tracker that achieves competitive performance on the public MOT16 and MOT17 test datasets.

我们提出了一种联合特征和度量学习深度神经网络架构，称为关联亲和网络 (AAN)，作为视频中多对象跟踪 (MOT) 的亲和模型。AAN 以端到端的方式学习跨帧的轨道和检测之间的关联亲和力。考虑到有缺陷的检测，AAN 通过提出的多任务损失联合学习边界框回归、分类和亲和力回归。与使用排名损失训练的网络相反，我们直接训练一个二元分类器来学习每个轨道检测对的关联亲和度，并使用匹配基数损失来捕获候选对之间的信息。AAN 学习数据关联的判别亲和模型以解决 MOT，并且还可以执行单对象跟踪。基于 AAN，