BriefGPT.xyz
Aug, 2017
视觉跟踪的循环滤波学习
Recurrent Filter Learning for Visual Tracking
HTML
PDF
Tianyu Yang, Antoni B. Chan
TL;DR
本研究提出了一种递归滤波器生成方法来进行视觉跟踪,直接将目标的图像块作为输入,使用递归神经网络来生成一个特定于目标的滤波器,通过将RNN中的全连接层的矩阵乘法扩展到特征图上的卷积运算,对目标的空间结构进行保留和内存优化。
Abstract
Recently using
convolutional neural networks
(CNNs) has gained popularity in
visual tracking
, due to its robust feature representation of images. Recent methods perform online tracking by fine-tuning a pre-traine
→