TL;DR本文介绍了一种用于视频中物体检测的新架构 SSVD,通过对相邻帧的特征进行聚合和估算运动路径,实现了单阶段物体检测。在 ImageNet VID 数据集上进行的实验证明,该方法比现有的物体检测方法更为有效。
Abstract
Single shot detectors that are potentially faster and simpler than two-stage
detectors tend to be more applicable to object detection in videos.
Nevertheless, the extension of such object detectors from image to video