BriefGPT.xyz
Feb, 2019
可微分的视频文法
Learning Differentiable Grammars for Continuous Data
HTML
PDF
AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo
TL;DR
本文提出一种新颖的算法，能够从实际连续数据如视频中学习形式化的正则语法，以构建捕捉多种可能的顺序结构的生成模型，其效果优于现有最先进的方法，我们计划将代码开源。
Abstract
This paper proposes a novel algorithm which learns a
formal regular grammar
from real-world
continuous data
, such as videos or other streaming data. Learning latent terminals, non-terminals, and productions rules
→