摘要:
Image size after convolusion: $\frac{n-k+2p}{s}+1$ where n is the width (or height) of the image, k is the kernel size, p is the padding, s is the str 阅读全文
摘要:
Weizmann Dataset 摘自 2016-Review of Action Recognition and Detection Methods 【这篇综述里有较全面的数据集介绍】 The Weizman dataset was recorded by static camera with c 阅读全文