BriefGPT.xyz
Jan, 2017
迭代消息传递的场景图生成
Scene Graph Generation by Iterative Message Passing
HTML
PDF
Danfei Xu, Yuke Zhu, Christopher B. Choy, Li Fei-Fei
TL;DR
研究使用视觉图像中的基于场景图谱的结构化表示,通过端到端模型建模图像中对象之间的关系,通过消息传递技术可以更好预测对象及其关系, 实验表明该模型显著优于以前的方法。
Abstract
Understanding a
visual scene
goes beyond recognizing individual objects in isolation.
relationships between objects
also constitute rich semantic information about the scene. In this work, we explicitly model the
→