论文标题
PAMI-AD：在监视视频中利用部分注意和运动信息的活动检测器
PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videos
论文作者
论文摘要
监视视频中的活动检测是由小物体，复杂的活动类别，其未修剪性质等引起的一项具有挑战性的任务。由于建议不准确，分类较差或后期过程不足，现有方法通常受到性能的限制。在这项工作中，我们建议在以人为本和以车辆为中心的活动的未修剪监视视频中进行全面有效的活动检测系统。它由四个模块，即对象定位器，提案过滤器，活动分类器和活动炼油厂组成。对于以人为本的活动，提出了一种新型的零件注意机制来探索不同身体部位的详细特征。至于以车辆为中心的活动，我们提出了一种本地化掩蔽方法，以共同编码运动和前景注意特征。我们对大规模活动检测数据集进行了实验，并为两组活动取得了最佳结果。此外，我们的团队赢得了Trecvid 2021 Actev挑战赛的第一名。
Activity detection in surveillance videos is a challenging task caused by small objects, complex activity categories, its untrimmed nature, etc. Existing methods are generally limited in performance due to inaccurate proposals, poor classifiers or inadequate post-processing method. In this work, we propose a comprehensive and effective activity detection system in untrimmed surveillance videos for person-centered and vehicle-centered activities. It consists of four modules, i.e., object localizer, proposal filter, activity classifier and activity refiner. For person-centered activities, a novel part-attention mechanism is proposed to explore detailed features in different body parts. As for vehicle-centered activities, we propose a localization masking method to jointly encode motion and foreground attention features. We conduct experiments on the large-scale activity detection datasets VIRAT, and achieve the best results for both groups of activities. Furthermore, our team won the 1st place in the TRECVID 2021 ActEV challenge.
