BriefGPT.xyz
Apr, 2018
像素的声音
The Sound of Pixels
HTML
PDF
Hang Zhao, Chuang Gan, Andrew Rouditchenko, Carl Vondrick, Josh McDermott...
TL;DR
PixelPlayer是一种利用大量无标注视频进行学习的系统，该系统能够学习定位产生声音的图像区域，并将输入的声音分离成代表每个像素声音的组件。实验结果表明，我们提出的混合和分离框架在音源分离方面优于几种基线模型。
Abstract
We introduce
pixelplayer
, a system that, by leveraging large amounts of unlabeled videos, learns to locate
image regions
which produce sounds and separate the input sounds into a set of components that represents
→