We propose a novel, simple and highly effective box-level post-processing method to improve the accuracy of video object detection. Our experiments on ImageNet object detection from video (VID) dataset show that our method brings important accuracy gains, especially to more challenging fast-moving object detection, with quite light computational overhead in both settings. Applied to YOLOv3, our system achieves so far the best speed/accuracy trade-off for video object detection. For more details, please refer to our VISAPP paper (https://www.scitepress.org/Papers/2019/72600/72600.pdf).

source