TL;DR该文综合研究和比较了视频人员重识别的四种不同的时间建模方法,包括时间汇聚,时间关注,RNN 和 3D 卷积神经网络,并提出了一个采用时间卷积的注意力生成网络,用于在帧之间提取时间信息。在 MARS 数据集上进行评估,并通过一大部分超越了最新技术的方法。
Abstract
video-based person reid is an important task, which has received much
attention in recent years due to the increasing demand in surveillance and
camera networks. A typical video-based person reid system consists