BriefGPT.xyz
May, 2015
图像字幕的语言模型：习惯和奏效
Language Models for Image Captioning: The Quirks and What Works
HTML
PDF
Jacob Devlin, Hao Cheng, Hao Fang, Saurabh Gupta, Li Deng...
TL;DR
该研究比较了不同的语言模型方法在图像字幕生成中的优缺点，并使用与众不同的语言模型方法，结合这些方法在COCO数据集上取得了新的记录性能。
Abstract
Two recent approaches have achieved state-of-the-art results in
image captioning
. The first uses a pipelined process where a set of candidate words is generated by a
convolutional neural network
(CNN) trained on
→