BriefGPT.xyz
May, 2015
观察和学习：从视频中半监督学习目标检测器
Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos
HTML
PDF
Ishan Misra, Abhinav Shrivastava, Martial Hebert
TL;DR
本文提出一种半监督的方法，用于在长视频中定位多个未知的物体实例，通过这种方法可以有效地进行对象检测和跟踪，同时实现对大量静态物体实例的识别。
Abstract
We present a
semi-supervised approach
that localizes multiple unknown object instances in
long videos
. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object inst
→